Tootfinder

Pragmatic Frames Evoked by Gestures: A FrameNet Brasil Approach to Multimodality in Turn Organization
Helen de Andrade Abreu, Tiago Timponi Torrent, Ely Edison da Silva Matos
https://arxiv.org/abs/2509.09804

Pragmatic Frames Evoked by Gestures: A FrameNet Brasil Approach to Multimodality in Turn Organization
This paper proposes a framework for modeling multimodal conversational turn organization via the proposition of correlations between language and interactive gestures, based on analysis as to how pragmatic frames are conceptualized and evoked by communicators. As a means to provide evidence for the analysis, we developed an annotation methodology to enrich a multimodal dataset (annotated for semantic frames) with pragmatic frames modeling conversational turn organization. Although conversationa…

Modal definability in Euclidean modal logics
Philippe Balbiani, Tinko Tinchev
https://arxiv.org/abs/2508.10813 https://arxiv.org/pdf/2508.10813

Modal definability in Euclidean modal logics
This paper is about the computability of the modal definability problem in classes of frames determined by Euclidean modal logics. We characterize those Euclidean modal logics such that the classes of frames they determine give rise to an undecidable modal definability problem.

Canonical Frames for Bracket Generating Rank 2 Distributions which are not Goursat
Nicklas Day, Igor Zelenko
https://arxiv.org/abs/2508.09307 https://arxiv…

Canonical Frames for Bracket Generating Rank 2 Distributions which are not Goursat
We complete a uniform construction of canonical absolute parallelism for bracket generating rank $2$ distributions with $5$-dimensional cube on $n$-dimensional manifold with $n\geq 5$ by showing that the condition of maximality of class that was assumed previously by Doubrov-Zelenko for such a construction holds automatically at generic points. This also gives analogous constructions in the case when the cube is not $5$-dimensional but the distribution is not Goursat through the procedure of it…

Automatically describe data and models as text using the {report} package. #rstats

Characterizations of dual of K-frames in quaternionic Hilbert spaces
Chander Shekhar
https://arxiv.org/abs/2508.08263 https://arxiv.org/pdf/2508.08263

Characterizations of dual of K-frames in quaternionic Hilbert spaces
Dual of K-frames in a right quaternionic Hilbert space has been recently introduced and studied by Ellouz[1]. In this paper, we study duals of K-frames and prove a characterization of a K-dual in terms of the canonical K-dual of a K-frame in the case when the range of K is not necessarily closed. Moreover, we defined and studied the Approximate K- Dual of a K-frame in a right quaternionic Hilbert space and proved various results for their existence.

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
Luke Rivard, Sun Sun, Hongyu Guo, Wenhu Chen, Yuntian Deng
https://arxiv.org/abs/2507.08800

NeuralOS: Towards Simulating Operating Systems via Neural Generative Models
We introduce NeuralOS, a neural framework that simulates graphical user interfaces (GUIs) of operating systems by directly predicting screen frames in response to user inputs such as mouse movements, clicks, and keyboard events. NeuralOS combines a recurrent neural network (RNN), which tracks computer state, with a diffusion-based neural renderer that generates screen images. The model is trained on a large-scale dataset of Ubuntu XFCE recordings, which include both randomly generated interacti…

🦾 Robotic frames offer new insights into honeybee behavior and honey storage
#science

Robotic frames offer new insights into honeybee behavior and honey storage
EPFL researchers are developing robotic beehive frames that help locate honey stores inside of beehives over time, without relying on cameras. The aim is to develop new observation tools to study honeybee behavior that better fit the bees' natural way to occupy space compared to current methods.

Rapid Manufacturing of Lightweight Drone Frames Using Single-Tow Architected Composites
Md Habib Ullah Khan, Kaiyue Deng, Ismail Mujtaba Khan, Kelvin Fu
https://arxiv.org/abs/2509.09024

Rapid Manufacturing of Lightweight Drone Frames Using Single-Tow Architected Composites
The demand for lightweight and high-strength composite structures is rapidly growing in aerospace and robotics, particularly for optimized drone frames. However, conventional composite manufacturing methods struggle to achieve complex 3D architectures for weight savings and rely on assembling separate components, which introduce weak points at the joints. Additionally, maintaining continuous fiber reinforcement remains challenging, limiting structural efficiency. In this study, we demonstrate t…

Amazon: Gleich zwei Smart Glasses mit Display in Entwicklung
Amazon entwickelt angeblich Smart Glasses für Verbraucher und Paketboten und plant zudem, die Echo Frames mit einer Kamera auszustatten.
https://www.

Interpreting quantum reference frame transformations through a simple example
Esteban Castro-Ruiz, Thomas D. Galley, Leon Loveridge
https://arxiv.org/abs/2508.09540 https://

Interpreting quantum reference frame transformations through a simple example
Quantum reference frame transformations have been proposed to provide a means by which to translate descriptions of quantum systems relative to each other. At present, there are several differing frameworks for describing quantum reference frames, with concomitantly different transformation rules. Here, we investigate a simple example of three qubit systems with $\mathbb{Z}_2$ symmetry in order to analyze physical and conceptual distinctions between three contemporary approaches to quantum refe…

Bio-Generative Design Morphology with Radiolaria: An application of a Nature-Based Generative Shape Grammar for Geometrical Design of Space Frames
Michael Kleiss, Seyedehaysan Mokhtarimousavi, Sida Dai, Mostafa Alani
https://arxiv.org/abs/2508.08572

Bio-Generative Design Morphology with Radiolaria: An application of a Nature-Based Generative Shape Grammar for Geometrical Design of Space Frames
This paper presents a study on using Radiolaria as a basis for generation of space-based geometry for structural design with shape grammars. Radiolaria has been a source of inspiration for architectural design with its intricate structural features and geometric patterns (Lim, 2012). We use the basis of the Radiolaria geometry to create a generative shape grammar as a computational system; then use the shape grammar to create spatial configurations for potential applications in design of 3D spa…

OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perception
Junho Koh, Youngwoo Lee, Jungho Kim, Dongyoung Lee, Jun Won Choi
https://arxiv.org/abs/2507.08644

OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perception
Multi-view camera-based 3D perception can be conducted using bird's eye view (BEV) features obtained through perspective view-to-BEV transformations. Several studies have shown that the performance of these 3D perception methods can be further enhanced by combining sequential BEV features obtained from multiple camera frames. However, even after compensating for the ego-motion of an autonomous agent, the performance gain from temporal aggregation is limited when combining a large number of imag…

Abelian and Dihedral equiangular tight frames of redundancy $2$
Assaf Goldberger, Radel Ben Av, Xuemei Chen, Kasso A. Okoudjou
https://arxiv.org/abs/2509.01753 https://

Abelian and Dihedral equiangular tight frames of redundancy $2$
This paper studies group frames ($G$-frames) where the unitary group representation can be projective. When the group is abelian, for most combinations $N, n$, we show that $ETF(N,n)$ can only exist for genuinely projective group representations. In particular, cyclic-group frames for such parameters do not exist. We also give a characterization of all dihedral tight frames and dihedral $ETF(2n,n)$, using which, we conclude that regular dihedral $ETF(2n,n)$ must be genuinely projective. Followi…

Mixed states for reference frames transformations
Gaetano Fiore, Fedele Lizzi
https://arxiv.org/abs/2507.05758 https://arxiv.org/pdf/…

Mixed states for reference frames transformations
We discuss the concept of transformations among reference frames (classical or quantum). Usually transformations among classical reference frames have sharply defined parameters; geometrically they can be considered as pure states in the parameters' space, and they form a group. It is however possible that the distributions in the parameters' space are mixed state; such states form a semigroup. Similarly, transformations among quantum reference frames can be either pure or mixed. This gives ris…

A note concerning frames and geometric inequalities
Jeff Ledford, Kevin Rivera-Ayala, Emma Schroeder
https://arxiv.org/abs/2509.05611 https://arxiv.org/pdf…

A note concerning frames and geometric inequalities
One may associate several frames to a given polytope, such as its collection of vertices, edges, or facet normal vectors. In this note, we use these frames to generate geometric inequalities for the simplex in $\mathbb{R}^d$ and polytopes with $d+2$ vertices in dimension 2 and 3.

A new dataset and comparison for multi-camera frame synthesis
Conall Daly, Anil Kokaram
https://arxiv.org/abs/2508.09068 https://arxiv.org/pdf/2508.09068…

A new dataset and comparison for multi-camera frame synthesis
Many methods exist for frame synthesis in image sequences but can be broadly categorised into frame interpolation and view synthesis techniques. Fundamentally, both frame interpolation and view synthesis tackle the same task, interpolating a frame given surrounding frames in time or space. However, most frame interpolation datasets focus on temporal aspects with single cameras moving through time and space, while view synthesis datasets are typically biased toward stereoscopic depth estimation …

#EpsteinClientList

Designing optimal dual frames for $\ell^p-$average error optimization
Shankhadeep Mondal, Deguang Han, R. N. Mohapatra
https://arxiv.org/abs/2508.07158 https://

Designing optimal dual frames for $\ell^p-$average error optimization
In this paper, we investigates the problem of optimal dual frame selection for signal reconstruction in the presence of erasures. Unlike traditional approaches relying on left inverses, we evaluate performance through the norms of error operators, using the Frobenius norm, spectral radius, and numerical radius as measures. Our central focus is the characterization of dual frames that minimize the $\ell^p-$average under these error operator measurements over all possible erasure patterns. We pro…

Fourier frames on smooth surfaces with nonvanishing Gaussian curvature
Xinyu Chen, Bochen Liu
https://arxiv.org/abs/2507.05777 https://

Fourier frames on smooth surfaces with nonvanishing Gaussian curvature
It is known that a small spherical cap (rigorously its surface measure) admits Fourier frames, while the whole sphere does not. In this paper, we prove more general results. Consequences indclude that a small spherical cap in $\mathbb{R}^d$ near the north pole cannot have a frame spectrum near the $x_d$-axis, and $S$ does not admit any Fourier frame if its interior contains a closed hemisphere. We also resolve the endpoint case, that is, a hemisphere does not admit any Fourier frame. This answe…

SurgPub-Video: A Comprehensive Surgical Video Dataset for Enhanced Surgical Intelligence in Vision-Language Model
Yaoqian Li, Xikai Yang, Dunyuan Xu, Yang Yu, Litao Zhao, Xiaowei Hu, Jinpeng Li, Pheng-Ann Heng
https://arxiv.org/abs/2508.10054

SurgPub-Video: A Comprehensive Surgical Video Dataset for Enhanced Surgical Intelligence in Vision-Language Model
Vision-Language Models (VLMs) have shown significant potential in surgical scene analysis, yet existing models are limited by frame-level datasets and lack high-quality video data with procedural surgical knowledge. To address these challenges, we make the following contributions: (i) SurgPub-Video, a comprehensive dataset of over 3,000 surgical videos and 25 million annotated frames across 11 specialties, sourced from peer-reviewed clinical journals, (ii) SurgLLaVA-Video, a specialized VLM for…

Galois equiangular tight frames from Galois self-dual codes
Junmin An, Jon-Lark Kim
https://arxiv.org/abs/2507.15448 https://arxiv.or…

Galois equiangular tight frames from Galois self-dual codes
Greaves et al. (2022) extended frames over real or complex numbers to frames over finite fields. In this paper, we study the theory of frames over finite fields by incorporating the Galois inner products introduced by Fan and Zhang (2017), which generalize the Euclidean and Hermitian inner products. We define a class of frames, called Galois frames over finite fields, along with related notions such as Galois Gram matrices, Galois frame operators, and Galois equiangular tight frames (Galois ETF…

Xi : Uncertainty Supervision for Robust Speaker Embedding
Junjie Li, Kong Aik Lee, Duc-Tuan Truong, Tianchi Liu, Man-Wai Mak
https://arxiv.org/abs/2509.05993 https://

Xi+: Uncertainty Supervision for Robust Speaker Embedding
There are various factors that can influence the performance of speaker recognition systems, such as emotion, language and other speaker-related or context-related variations. Since individual speech frames do not contribute equally to the utterance-level representation, it is essential to estimate the importance or reliability of each frame. The xi-vector model addresses this by assigning different weights to frames based on uncertainty estimation. However, its uncertainty estimation model is …

A Game-Theoretic Foundation for Bitcoin's Price: A Security-Utility Equilibrium
Liang Chen
https://arxiv.org/abs/2508.06071 https://arxiv.org/pdf/2508.…

A Game-Theoretic Foundation for Bitcoin's Price: A Security-Utility Equilibrium
This paper introduces a structural game-theoretic model to value decentralized digital assets like Bitcoin. Instead of relying on speculative beliefs, it frames the asset's price within a Rational-Expectations Security-Utility Nash Equilibrium (RESUNE). This equilibrium is a fixed point where the market-clearing price dictates the hash rate through a free-entry mining model, which in turn endogenously sets the network's security. The security, defined as one minus the probability of a 51% attac…

It’s going down.
https://frames.social/@2001x24/statuses/01K3MNF0XWDHEE9EKSYXSWH1SY

Geometry of supergravity and the Batalin--Vilkovisky formulation of the $\mathcal N=1$ theory in ten dimensions
Julian Kupka, Charles Strickland-Constable, Fridrich Valach
https://arxiv.org/abs/2508.06398

Geometry of supergravity and the Batalin--Vilkovisky formulation of the $\mathcal N=1$ theory in ten dimensions
We provide full details of a BV formulation of $\mathcal N=1$ supergravity in ten dimensions, to all orders in fermions, built from the generalised geometry description of the theory. In contrast to standard treatments, we introduce neither the degrees of freedom corresponding to orthonormal frames for the metric nor the local Lorentz symmetries that remove them again. Instead, we observe that the field space has a fibred structure, with the fermionic degrees of freedom spanning the fibres. We …

A Cross-Perspective Annotated Dataset for Dynamic Object-Level Attention Modeling in Cloud Gaming
Hongqin Lei, Haowei Tang, Zhe Zhang
https://arxiv.org/abs/2508.06077 https://…

A Cross-Perspective Annotated Dataset for Dynamic Object-Level Attention Modeling in Cloud Gaming
Cloud gaming has gained popularity as it provides high-quality gaming experiences on thin hardware, such as phones and tablets. Transmitting gameplay frames at high resolutions and ultra-low latency is the key to guaranteeing players' quality of experience (QoE). Numerous studies have explored deep learning (DL) techniques to address this challenge. The efficiency of these DL-based approaches is highly affected by the dataset. However, existing datasets usually focus on the positions of objects…

Small thing I noticed today: splitting `.mkv` files using `ffmpeg` via the `-ss` and `-t` options works great, but the resulting `.mkv` file contains the wrong number of frames in the metadata. Evidently the total frames from the source file gets written into the metadata instead of the resulting frames post-splitting which is annoying. Not a deal breaker, but kind of annoying...easy to fix with a quick run through `mkvmerge` but still just weird.

Final outputs.
Not at nice as I'd hoped but it's all I could get out of it with my current skillset.
Might go out to the field s00n:tm: tt get better frames (further away from cities n stuff) though.

KFFocus: Highlighting Keyframes for Enhanced Video Understanding
Ming Nie, Chunwei Wang, Hang Xu, Li Zhang
https://arxiv.org/abs/2508.08989 https://arxiv.o…

KFFocus: Highlighting Keyframes for Enhanced Video Understanding
Recently, with the emergence of large language models, multimodal LLMs have demonstrated exceptional capabilities in image and video modalities. Despite advancements in video comprehension, the substantial computational demands of long video sequences lead current video LLMs (Vid-LLMs) to employ compression strategies at both the inter-frame level (e.g., uniform sampling of video frames) and intra-frame level (e.g., condensing all visual tokens of each frame into a limited number). However, thi…

From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models
Grazia Sveva Ascione, Nicol\`o Tamagnone
https://arxiv.org/abs/2509.09303

From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models
Classifying patents by their relevance to the UN Sustainable Development Goals (SDGs) is crucial for tracking how innovation addresses global challenges. However, the absence of a large, labeled dataset limits the use of supervised learning. Existing methods, such as keyword searches, transfer learning, and citation-based heuristics, lack scalability and generalizability. This paper frames patent-to-SDG classification as a weak supervision problem, using citations from patents to SDG-tagged sci…

🫳
🎤

#ParkerSolarProbe was in the right place at the right time in September 2022: It passed through a magnetic reconnection region in the Sun's corona. #SolarOrbiter observed the event from a distance. Study led by

Bio-Inspired Hybrid Map: Spatial Implicit Local Frames and Topological Map for Mobile Cobot Navigation
Tuan Dang, Manfred Huber
https://arxiv.org/abs/2507.04649

Bio-Inspired Hybrid Map: Spatial Implicit Local Frames and Topological Map for Mobile Cobot Navigation
Navigation is a fundamental capacity for mobile robots, enabling them to operate autonomously in complex and dynamic environments. Conventional approaches use probabilistic models to localize robots and build maps simultaneously using sensor observations. Recent approaches employ human-inspired learning, such as imitation and reinforcement learning, to navigate robots more effectively. However, these methods suffer from high computational costs, global map inconsistency, and poor generalization…

Series A, Episode 01 - The Way Back
[JENNA looks through the bars at the prisoner, then walks back through the holding cell. BLAKE is asleep on a single bed. Someone is stealing his watch while he sleeps. It is VILA. VILA attempts to steal something from BLAKE'S pocket. BLAKE wakes up and pushes VILA to the floor.]
VILA: Easy! Take it easy! I hate personal violence, especially when I'm the person.

Listened in to the Academy Software Foundation's virtual townhall about the Open Review Initiative. I knew that project because they provide very useful ffmpeg command lines and they're doing all the encoding tests to figure out good quality settings and obscure parameters.
Learnings from the presentation: prores by ffmpeg is sadly pretty crappy compared to the real prores from Apple. There's the OpenAPV codec that is gearing up to be an open-source alternative:

Developing a Multi-Modal Machine Learning Model For Predicting Performance of Automotive Hood Frames
Abhishek Indupally, Satchit Ramnath
https://arxiv.org/abs/2508.20358 https:/…

Developing a Multi-Modal Machine Learning Model For Predicting Performance of Automotive Hood Frames
Is there a way for a designer to evaluate the performance of a given hood frame geometry without spending significant time on simulation setup? This paper seeks to address this challenge by developing a multimodal machine-learning (MMML) architecture that learns from different modalities of the same data to predict performance metrics. It also aims to use the MMML architecture to enhance the efficiency of engineering design processes by reducing reliance on computationally expensive simulations…

It is only a matter of time until noem, homan, dhs, ice and potus realize dropping people out of aircraft is cheaper than housing or moving them.
Unless they already have.
Rumors are the US is engaging in death flights. Already there are some known flight paths of ice flights turning around over bodies of water.
The US Congress and international community seem to be the only things that can stop this.

Interesting thing about tomorrow's tarot show, rendering now, is that I upgraded from Blender 4.0 to blender 4.4 and it's quite a bit nicer to look at the timeline editor.
Was sad to find that the render time was up though. From about 3 seconds per frame usually to more like 12!?
Trying it with an old version I see that the lights and textures look way better with 4.4 than 4.0 though. A substantial step up in the way the show looks without me even doing anything other than waiting four times longer per frame.
Seems to be heavily dependent upon lighting now. The slow frames are like 12 seconds but the fast frames with minimal lighting and close up on the video are more like 2.
Looks too beautiful now to go back though. Upgraded my cloud-remote render machines too. We will render on four machines tonight. FOUR! The power of it all.
g3.4xlarge is no faster than g3.large but g6.xlarge seems to be twice the speed.
But hard to be sure really coz of the massive variance in time depending on the lighting.
Anyway, great show coming tomorrow. Sometimes I wonder what the hell I'm trying to do with it but tomorrow's show is the answer. Hide the angry bitter political rant behind a strange CGI tarot show. When the rant comes together well I like it.
https://wordcloudtarot.com/@wordcloudtarot/statuses/01JYFF0GQV1680Z0VG0YTFZDTP

#Framed #1213
🎥 🟥 🟩 ⬛ ⬛ ⬛ ⬛
https://framed.wtf
Framed - One Frame Challenge #216
🎥 🟩 ⬛ ⬛ ⬛ ⬛ ⬛

Improved Receiver Chain Performance via Error Location Inference
Michael Greenwood, Robert Hunter
https://arxiv.org/abs/2509.08869 https://arxiv.org/pdf/25…

Improved Receiver Chain Performance via Error Location Inference
Modern spacecraft communication systems rely on concatenated error correction schemes, typically combining convolutional and Reed-Solomon (RS) codes. This paper presents a decoder-side method that uses a machine learning model to estimate the likelihood of byte-level corruption in received data frames. These estimates are used to mark erasures prior to RS decoding, enhancing its correction capacity without requiring changes to spacecraft hardware or encoding standards. The approach enables impr…

An ode to internal cable routing - Liam Mercer at road.cc
#cycling

Degree of Kripke-incompleteness of Tense Logics
Qian Chen
https://arxiv.org/abs/2507.04533 https://arxiv.org/pdf/2507.04533

Degree of Kripke-incompleteness of Tense Logics
The degree of Kripke-incompleteness of a logic $L$ in some lattice $\mathcal{L}$ of logics is the cardinality of logics in $\mathcal{L}$ which share the same class of Kripke-frames with $L$. A celebrated result on Kripke-incompleteness is Blok's dichotomy theorem for the degree of Kripke-incompleteness in $\mathsf{NExt}(\mathsf{K})$: every modal logic $L\in\mathsf{NExt}(\mathsf{K})$ is of the degree of Kripke-incompleteness $1$ or $2^{\aleph_0}$. In this work, we show that the dichotomy theorem…

Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning
Osama Mohammed, Jiaxin Pan, Mojtaba Nayyeri, Daniel Hern\'andez, Steffen Staab
https://arxiv.org/abs/2508.03251

Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning
Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles accelerate, brake, and change lanes relative to one another over consecutive frames. Likewise, detecting financial fraud hinges on following the flow of funds through successive transactions as they propagate through the network. Unlike classic time-series forecasting, these settings demand reasoning over who interacts…

Semantic Frame Interpolation
Yijia Hong, Jiangning Zhang, Ran Yi, Yuji Wang, Weijian Cao, Xiaobin Hu, Zhucun Xue, Yabiao Wang, Chengjie Wang, Lizhuang Ma
https://arxiv.org/abs/2507.05173

Semantic Frame Interpolation
Generating intermediate video content of varying lengths based on given first and last frames, along with text prompt information, offers significant research and application potential. However, traditional frame interpolation tasks primarily focus on scenarios with a small number of frames, no text control, and minimal differences between the first and last frames. Recent community developers have utilized large video models represented by Wan to endow frame-to-frame capabilities. However, the…

Well, the good news is that it’s over. Run/walk staying in HR zone 2 and I think I was walking more than running. My fitness is 💩 right now. The humidity about killed me, even at 0730. I should have gone out earlier.
I’m at my in-laws place in Tennessee for the holiday weekend, of which this beautiful neighborhood has so few mature trees. As such, the sun gleefully poured out its angry menace upon me the entire time and I suffered. I am meant for cold weather.

Anybody have access to an oscilloscope with a 100baseTX Ethernet decoder on it? Curious how fast commercial protocol decodes are compared to mine.
I'd love benchmarks:
* 2 channels, 10M points, 500 Msps, on P/N
* Simple edge trigger, saturated or nearly saturated link
* Decode to Ethernet frames
How many waveforms per second / seconds per waveform do you get?

Geometry Matters in Planar Storyplans
Alexander Dobler, Maximilian Holzm\"uller, Martin N\"ollenburg
https://arxiv.org/abs/2508.12747 https://arx…

Geometry Matters in Planar Storyplans
A storyplan visualizes a graph $G=(V,E)$ as a sequence of $\ell$ frames $Γ_1, \dots, Γ_\ell$, each of which is a drawing of the induced subgraph $G[V_i]$ of a vertex subset $V_i \subseteq V$. Moreover, each vertex $v \in V$ is contained in a single consecutive sequence of frames $Γ_i, \dots, Γ_j$, all vertices and edges contained in consecutive frames are drawn identically, and the union of all frames is a drawing of $G$. In GD 2022, the concept of planar storyplans was introduced, in which…

Robustness to noise and erasures of Gabor frames in finite dimensions
Palina Salanevich, Nigel Q. D. Strachan
https://arxiv.org/abs/2509.01325 https://arxi…

Robustness to noise and erasures of Gabor frames in finite dimensions
In this paper, we investigate the robustness of structured frames to measurement noise and erasures, with the focus on Gabor frames $(g, Λ)$ with arbitrary sets of time-frequency shifts $Λ$. This property of frames is important in many signal processing applications, from wireless communication to phase retrieval and quantization. We aim to analyze the dependence of the frame bounds of such frames on their structure and cardinality and provide constructions of nearly tight Gabor frames with s…

Semi-local observables, edge modes and quantum reference frames in quantum electromagnetism: an algebraic approach
Christopher J. Fewster, Daan W. Janssen, Kasia Rejzner
https://arxiv.org/abs/2508.20939

Semi-local observables, edge modes and quantum reference frames in quantum electromagnetism: an algebraic approach
Boundaries and corners of spacetime play a vital role in understanding physical concepts including entanglement entropy, the infrared problem in QFT and quantum gravity. Standard local quantum field theory struggles to accommodate such boundary-sensitive observables. In this paper we develop an algebraic framework for \emph{semi-local quantum electromagnetism} on finite Cauchy lenses: a class of compact spacetimes with boundaries and corner. At the classical level, we establish a decomposition …

Pangenome-guided sequence assembly via binary optimisation
Josh Cudby, James Bonfield, Chenxi Zhou, Richard Durbin, Sergii Strelchuk
https://arxiv.org/abs/2508.08200 https://

Pangenome-guided sequence assembly via binary optimisation
De novo genome assembly is challenging in highly repetitive regions; however, reference-guided assemblers often suffer from bias. We propose a framework for pangenome-guided sequence assembly, which can resolve short-read data in complex regions without bias towards a single reference genome. Our method frames assembly as a graph traversal optimisation problem, which can be implemented on quantum computers. The pipeline first annotates pangenome graphs with estimated copy numbers for each node,…

Another cool and useful package from @…: {emphatic} augments the output of data.frames, matrices and simple vectors in R by adding user-defined ANSI highlighting. https://c…

Relational entanglement entropies and quantum reference frames in gauge theories
Goncalo Araujo-Regado, Philipp A. Hoehn, Francesco Sartini
https://arxiv.org/abs/2506.23459

Relational entanglement entropies and quantum reference frames in gauge theories
It has been shown that defining gravitational entanglement entropies relative to quantum reference frames (QRFs) intrinsically regularizes them. Here, we demonstrate that such relational definitions also have an advantage in lattice gauge theories, where no ultraviolet divergences occur. To this end, we introduce QRFs for the gauge group via Wilson lines on a lattice with global boundary, realizing edge modes on the bulk entangling surface. Overcoming challenges of previous nonrelational approa…

Retain or Reframe? A Computational Framework for the Analysis of Framing in News Articles and Reader Comments
Matteo Guida, Yulia Otmakhova, Eduard Hovy, Lea Frermann
https://arxiv.org/abs/2507.04612

Retain or Reframe? A Computational Framework for the Analysis of Framing in News Articles and Reader Comments
When a news article describes immigration as an "economic burden" or a "humanitarian crisis," it selectively emphasizes certain aspects of the issue. Although \textit{framing} shapes how the public interprets such issues, audiences do not absorb frames passively but actively reorganize the presented information. While this relationship between source content and audience response is well-documented in the social sciences, NLP approaches often ignore it, detecting frames in articles and response…

Tabular intermediate logics comparison
Pawe{\l} Rz\k{a}\.zewski, Micha{\l} Stronkowski
https://arxiv.org/abs/2509.06841 https://arxiv.org/pdf/2509.06841

Tabular intermediate logics comparison
Tabular intermediate logics are intermediate logics characterized by finite posets treated as Kripke frames. For a poset $\mathbb{P}$, let $L(\mathbb{P})$ denote the corresponding tabular intermediate logic. We investigate the complexity of the following decision problem $\mathsf{LogContain}$: given two finite posets $\mathbb P$ and $\mathbb Q$, decide whether $L(\mathbb P) \subseteq L(\mathbb Q)$. By Jankov's and de Jongh's theorem, the problem $\mathsf{LogContain}$ is related to the problem…

The Time Someone Plagiarized Calvin & Hobbes and Nobody Noticed or Cared
#comics

Effectively Identifying Wi-Fi Devices through State Transitions
Melissa Safari, Abhishek K. Mishra, Mathieu Cunche
https://arxiv.org/abs/2507.02478 https:/…

Effectively Identifying Wi-Fi Devices through State Transitions
Wi-Fi management frames reveal structured communication patterns that persist even under randomization of MAC addresses. Prior approaches to associating randomized MAC addresses with devices primarily focus on probe requests, overlooking the broader set of management frames and their transition dynamics. This narrow focus limits their robustness in dense, real-world environments with high device mobility, where probe activity alone fails to yield stable and distinctive signatures. In this paper…

HyTIP: Hybrid Temporal Information Propagation for Masked Conditional Residual Video Coding
Yi-Hsin Chen, Yi-Chen Yao, Kuan-Wei Ho, Chun-Hung Wu, Huu-Tai Phung, Martin Benjak, J\"orn Ostermann, Wen-Hsiao Peng
https://arxiv.org/abs/2508.02072

HyTIP: Hybrid Temporal Information Propagation for Masked Conditional Residual Video Coding
Most frame-based learned video codecs can be interpreted as recurrent neural networks (RNNs) propagating reference information along the temporal dimension. This work revisits the limitations of the current approaches from an RNN perspective. The output-recurrence methods, which propagate decoded frames, are intuitive but impose dual constraints on the output decoded frames, leading to suboptimal rate-distortion performance. In contrast, the hidden-to-hidden connection approaches, which propaga…

Submodules of $H^2(\mathbb{T}^2)$ and Frames by Pairs of Bounded Commuting Operators
Victor Bailey, Carlos Cabrelli
https://arxiv.org/abs/2507.04992 https:…

Submodules of $H^2(\mathbb{T}^2)$ and Frames by Pairs of Bounded Commuting Operators
Recent work in Dynamical Sampling has been centered on characterizing frames obtained by the orbit of a vector under a bounded operator. We prove a necessary and sufficient condition for a pair of bounded commuting operators on a separable infinite-dimensional Hilbert space to generate a frame by unilateral iterations on a single vector. Applying the theory on submodules of the Hardy module $H^2(\mathbb{T}^2)$, we characterize these frames in terms of their relation to the two-variable Jordan b…

When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and Adversarial Audio Spoof Detection
Bin Hu, Kunyang Huang, Daehan Kwak, Meng Xu, Kuan Huang
https://arxiv.org/abs/2509.07323

When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and Adversarial Audio Spoof Detection
The rapid advancement of AI has enabled highly realistic speech synthesis and voice cloning, posing serious risks to voice authentication, smart assistants, and telecom security. While most prior work frames spoof detection as a binary task, real-world attacks often involve hybrid utterances that mix genuine and synthetic speech, making detection substantially more challenging. To address this gap, we introduce the Hybrid Spoofed Audio Dataset (HSAD), a benchmark containing 1,248 clean and 41,0…

Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
Shaoguang Wang (The Hong Kong University of Science and Technology), Jianxiang He (The Hong Kong University of Science and Technology), Yijie Xu (The Hong Kong University of Science and Technology), Ziyang Chen (The Hong Kong University of Science and Technology), Weiyu Guo (The Hong Kong University of Science and Technology), Hui Xiong (The Hong Kong University of Science and Technology)

Less is More: Token-Efficient Video-QA via Adaptive Frame-Pruning and Semantic Graph Integration
The practical application of Multimodal Large Language Models (MLLMs) to Video Question Answering (Video-QA) is severely hindered by the high token cost of processing numerous video frames. While increasing the number of sampled frames is a common strategy, we observe a "less is more" phenomenon where excessive frames can paradoxically degrade performance due to context dilution. Concurrently, state-of-the-art keyframe selection methods, while effective, still yield significant temporal redunda…

Simply connectedness of spaces of tight frames
Augustin-Liviu Mare
https://arxiv.org/abs/2508.02484 https://arxiv.org/pdf/2508.02484

Simply connectedness of spaces of tight frames
Complex tight frames can be canonically viewed as elements of a complex Stiefel manifold. We present a class of spaces of such frames which are simply connected relative to the subspace topology. To this class belongs the space of finite unit-norm tight frames.

Diffusion-Shock PDEs for Deep Learning on Position-Orientation Space
Finn M. Sherry, Kristina Schaefer, Remco Duits
https://arxiv.org/abs/2509.06405 https://

Diffusion-Shock PDEs for Deep Learning on Position-Orientation Space
We extend Regularised Diffusion-Shock (RDS) filtering from Euclidean space R2 [1] to position-orientation space $\mathbb{M}_2 \cong \mathbb{R}^2 \times S^1$. This has numerous advantages, e.g. making it possible to enhance and inpaint crossing structures, since they become disentangled when lifted to $\mathbb{M}_2$. We create a version of the algorithm using gauge frames to mitigate issues caused by lifting to a finite number of orientations. This leads us to study generalisations of diffusion,…

QoE Optimization for Semantic Self-Correcting Video Transmission in Multi-UAV Networks
Xuyang Chen, Chong Huang, Daquan Feng, Lei Luo, Yao Sun, Xiang-Gen Xia
https://arxiv.org/abs/2507.06717

QoE Optimization for Semantic Self-Correcting Video Transmission in Multi-UAV Networks
Real-time unmanned aerial vehicle (UAV) video streaming is essential for time-sensitive applications, including remote surveillance, emergency response, and environmental monitoring. However, it faces challenges such as limited bandwidth, latency fluctuations, and high packet loss. To address these issues, we propose a novel semantic self-correcting video transmission framework with ultra-fine bitrate granularity (SSCV-G). In SSCV-G, video frames are encoded into a compact semantic codebook spa…

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Hyungjin Chung, Hyelin Nam, Jiyeon Kim, Hyojun Go, Byeongjun Park, Junho Kim, Joonseok Lee, Seongsu Ha, Byung-Hoon Kim
https://arxiv.org/abs/2509.08016

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail leads to prohibitive computational costs and performance degradation from long context lengths. We introduce Video Parallel Scaling (VPS), an inference-time method that expands a model's perceptual bandwidth without increasing its context window. VPS operates by running multiple parallel inference streams, each processing a unique, disjoint subset of …

EVDI : Event-based Video Deblurring and Interpolation via Self-Supervised Learning
Chi Zhang, Xiang Zhang, Chenxu Jiang, Gui-Song Xia, Lei Yu
https://arxiv.org/abs/2509.08260 h…

EVDI++: Event-based Video Deblurring and Interpolation via Self-Supervised Learning
Frame-based cameras with extended exposure times often produce perceptible visual blurring and information loss between frames, significantly degrading video quality. To address this challenge, we introduce EVDI++, a unified self-supervised framework for Event-based Video Deblurring and Interpolation that leverages the high temporal resolution of event cameras to mitigate motion blur and enable intermediate frame prediction. Specifically, the Learnable Double Integral (LDI) network is designed …

Sequence space representations of Beurling-Bj\"orck spaces via Gabor frames and Wilson bases
Andreas Debrouwere, Lenny Neyt
https://arxiv.org/abs/2508.05565 https://…

Sequence space representations of Beurling-Björck spaces via Gabor frames and Wilson bases
We establish sequence space representations of a broad class of Beurling-Björck spaces $\mathcal{S}^{(ω)}_{(η)}$ and $\mathcal{S}^{\{ω\}}_{\{η\}}$. We develop two different approaches: a non-constructive one based on Gabor frames and the structure theory of Fréchet spaces, and a constructive one using Wilson bases, under stronger assumptions on the defining weight functions $ω$ and $η$. As an application, we provide an isomorphic classification of the spaces $\mathcal{S}^{(ω)}_{(η)}$ …

FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization
Sara Behnamian, Rasoul Khaksarinezhad, Andreas Langer
https://arxiv.org/abs/2509.08670

FractalPINN-Flow: A Fractal-Inspired Network for Unsupervised Optical Flow Estimation with Total Variation Regularization
We present FractalPINN-Flow, an unsupervised deep learning framework for dense optical flow estimation that learns directly from consecutive grayscale frames without requiring ground truth. The architecture centers on the Fractal Deformation Network (FDN) - a recursive encoder-decoder inspired by fractal geometry and self-similarity. Unlike traditional CNNs with sequential downsampling, FDN uses repeated encoder-decoder nesting with skip connections to capture both fine-grained details and long…

DiWA: Diffusion Policy Adaptation with World Models
Akshay L Chandra, Iman Nematollahi, Chenguang Huang, Tim Welschehold, Wolfram Burgard, Abhinav Valada
https://arxiv.org/abs/2508.03645

DiWA: Diffusion Policy Adaptation with World Models
Fine-tuning diffusion policies with reinforcement learning (RL) presents significant challenges. The long denoising sequence for each action prediction impedes effective reward propagation. Moreover, standard RL methods require millions of real-world interactions, posing a major bottleneck for practical fine-tuning. Although prior work frames the denoising process in diffusion policies as a Markov Decision Process to enable RL-based updates, its strong dependence on environment interaction rema…

Enhancing Multi-Exposure High Dynamic Range Imaging with Overlapped Codebook for Improved Representation Learning
Keuntek Lee, Jaehyun Park, Nam Ik Cho
https://arxiv.org/abs/2507.01588

Enhancing Multi-Exposure High Dynamic Range Imaging with Overlapped Codebook for Improved Representation Learning
High dynamic range (HDR) imaging technique aims to create realistic HDR images from low dynamic range (LDR) inputs. Specifically, Multi-exposure HDR imaging uses multiple LDR frames taken from the same scene to improve reconstruction performance. However, there are often discrepancies in motion among the frames, and different exposure settings for each capture can lead to saturated regions. In this work, we first propose an Overlapped codebook (OLC) scheme, which can improve the capability of t…

On the relation between perspective-neutral, algebraic, and effective quantum reference frames
Philipp A. Hoehn, Julian De Vuyst, Artur Tsobanjan
https://arxiv.org/abs/2507.14131 …

On the relation between perspective-neutral, algebraic, and effective quantum reference frames
The framework of internal quantum reference frames (QRFs) constitutes a universal toolset for dealing with symmetries in quantum theory and has led to new revelations in quantum gravity, gauge theories and foundational physics. Multiple approaches have emerged, sometimes differing in scope and the way symmetries are implemented, raising the question as to their relation. Here, we investigate the relation between three approaches to QRFs for gauge symmetries, namely the effective semiclassical, …

Rescaling of unconditional Schauder frames in Hilbert spaces and completely bounded maps
Anton Tselishchev
https://arxiv.org/abs/2508.02802 https://arxiv.o…

Rescaling of unconditional Schauder frames in Hilbert spaces and completely bounded maps
We prove that if every element $u$ in a Hilbert space $H$ admits a representation as unconditionally convergent series $$u=\sum_{k=1}^\infty \langle u, y_k\rangle x_k,$$ then there exist nonzero scalars $\{α_k\}_{k=1}^\infty$ such that both sequences $\{α_k x_k\}_{k=1}^\infty$ and $\{\overlineα_k^{-1}y_k\}_{k=1}^\infty$ are frames. Our result has the following equivalent reformulation: if $Φ:\ell^\infty\to B(H)$ is a bounded linear map such that for every element of the unit vector basis $e…

Large effects from quantum reference frames
Martin Bojowald, Luis Martinez
https://arxiv.org/abs/2506.14721 https://arxiv.org/pdf/250…

Large effects from quantum reference frames
Reference frames are used to parameterize measurements of physical effects, but since their practical realization uses material objects, they may affect observations performed in a combined quantum state of the measured system together with the frame. Here, a procedure is used that makes it possible to describe non-monotonic reference scales in a quantum treatment, revealing large quantum effects in the measured system whenever a reference frame encounters a turning point. Subtle quantum correl…

FB-Diff: Fourier Basis-guided Diffusion for Temporal Interpolation of 4D Medical Imaging
Xin You, Runze Yang, Chuyan Zhang, Zhongliang Jiang, Jie Yang, Nassir Navab
https://arxiv.org/abs/2507.04547

FB-Diff: Fourier Basis-guided Diffusion for Temporal Interpolation of 4D Medical Imaging
The temporal interpolation task for 4D medical imaging, plays a crucial role in clinical practice of respiratory motion modeling. Following the simplified linear-motion hypothesis, existing approaches adopt optical flow-based models to interpolate intermediate frames. However, realistic respiratory motions should be nonlinear and quasi-periodic with specific frequencies. Intuited by this property, we resolve the temporal interpolation task from the frequency perspective, and propose a Fourier b…

Optimal K dual frames and pairs in the presence of erasures
Shankhadeep Mondal, Deguang Han, R. N. Mohapatra
https://arxiv.org/abs/2508.01964 https://arxiv…

Optimal K dual frames and pairs in the presence of erasures
This paper explores the structure of optimal K-dual frames for a given K-frame and optimal K-dual pairs, within the context of erasures which occur during the transmission of frame coefficients. We address two distinct erasure scenarios and examine their impact on the reconstruction process. The optimality criteria are defined in terms of minimizing the spectral radius and the operator norm of the associated error operators. Through this approach, we provide a comprehensive framework for unders…

When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking
Weiran Li, Yeqiang Liu, Qiannan Guo, Yijie Wei, Hwa Liang Leo, Zhenbo Li
https://arxiv.org/abs/2507.06400

When Trackers Date Fish: A Benchmark and Framework for Underwater Multiple Fish Tracking
Multiple object tracking (MOT) technology has made significant progress in terrestrial applications, but underwater tracking scenarios remain underexplored despite their importance to marine ecology and aquaculture. We present Multiple Fish Tracking Dataset 2025 (MFT25), the first comprehensive dataset specifically designed for underwater multiple fish tracking, featuring 15 diverse video sequences with 408,578 meticulously annotated bounding boxes across 48,066 frames. Our dataset captures var…

RefTok: Reference-Based Tokenization for Video Generation
Xiang Fan, Xiaohang Sun, Kushan Thakkar, Zhu Liu, Vimal Bhat, Ranjay Krishna, Xiang Hao
https://arxiv.org/abs/2507.02862 …

RefTok: Reference-Based Tokenization for Video Generation
Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectively capture the temporal dependencies and redundancies inherent in videos. To address this limitation, we introduce RefTok, a novel reference-based tokenization method capable of capturing complex temporal dynamics and contextual information. Our method encodes and decodes sets of frames conditioned on an unquantized re…

Cyclic frames in finite-dimensional Hilbert spaces
Ole Christensen, Navneet Redhu, Niraj K. Shukla
https://arxiv.org/abs/2508.17088 https://arxiv.org/pdf/2…

Cyclic frames in finite-dimensional Hilbert spaces
Generalizing a definition by Kalra \cite{Kalra}, the purpose of this paper is to analyze cyclic frames in finite-dimensional Hilbert spaces. Cyclic frames form a subclass of the dynamical frames introduced and analyzed in detail by Aldroubi et al. in \cite{ACM} and subsequent papers; they are particularly interesting due to their attractive properties in the context of erasure problems. By applying an alternative approach, we are able to shed new light on general dynamical frames as well as…

UrbanTwin: High-Fidelity Synthetic Replicas of Roadside Lidar Datasets
Muhammad Shahbaz, Shaurya Agarwal
https://arxiv.org/abs/2509.06781 https://arxiv.org…

UrbanTwin: High-Fidelity Synthetic Replicas of Roadside Lidar Datasets
This article presents UrbanTwin datasets - high-fidelity, realistic replicas of three public roadside lidar datasets: LUMPI, V2X-Real-IC, and TUMTraf-I. Each UrbanTwin dataset contains 10K annotated frames corresponding to one of the public datasets. Annotations include 3D bounding boxes, instance segmentation labels, and tracking IDs for six object classes, along with semantic segmentation labels for nine classes. These datasets are synthesized using emulated lidar sensors within realistic dig…

Wavelet Coorbit Spaces over Local Fields
Kumar Abhinav, Hartmut F\"uhr, Qaiser Jahan
https://arxiv.org/abs/2508.07242 https://arxiv.org/pdf/2508.07242…

Wavelet Coorbit Spaces over Local Fields
This paper studies wavelet coorbit spaces on disconnected local fields $K$, associated to the quasi-regular representation of $G = K \rtimes K^*$ acting on $L^2(K)$. We show that coorbit space theory applies in this context, and identify the homogeneous Besov spaces $\dot{B}_{α,s,t}(K)$ as coorbit spaces. We identify a particularly convenient space $\mathcal{S}_0(K)$ of wavelets that give rise to tight wavelet frames via the action of suitable, easily determined discrete subsets $R \subset G$,…

MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration
George Ciubotariu, Zhuyun Zhou, Zongwei Wu, Radu Timofte
https://arxiv.org/abs/2509.06803 https://…

MIORe & VAR-MIORe: Benchmarks to Push the Boundaries of Restoration
We introduce MIORe and VAR-MIORe, two novel multi-task datasets that address critical limitations in current motion restoration benchmarks. Designed with high-frame-rate (1000 FPS) acquisition and professional-grade optics, our datasets capture a broad spectrum of motion scenarios, which include complex ego-camera movements, dynamic multi-subject interactions, and depth-dependent blur effects. By adaptively averaging frames based on computed optical flow metrics, MIORe generates consistent moti…

Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage
Markiyan Kostiv, Anatolii Adamovskyi, Yevhen Cherniavskyi, Mykyta Varenyk, Ostap Viniavskyi, Igor Krashenyi, Oles Dobosevych
https://arxiv.org/abs/2507.05229

Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage
Multi-object tracking (MOT) aims to maintain consistent identities of objects across video frames. Associating objects in low-frame-rate videos captured by moving unmanned aerial vehicles (UAVs) in actual combat scenarios is complex due to rapid changes in object appearance and position within the frame. The task becomes even more challenging due to image degradation caused by cloud video streaming and compression algorithms. We present how instance association learning from single-frame annota…

Discretization of Continuous Frames by Quasi-Monte Carlo Methods
Jan Zimmermann, Andreas Klotz, Nicki Holighaus
https://arxiv.org/abs/2507.00618 https://…

Discretization of Continuous Frames by Quasi-Monte Carlo Methods
We introduce a discretization scheme for continuous localized frames using quasi-Monte Carlo integration and discrepancy theory. By generalizing classical concepts, we define a discrepancy measure on the entire phase space $\mathbb{R}^2$ and establish a corresponding Koksma-Hlawka inequality. This approach enables control over the density of the discretized frame and ensures the universality of the sampling set, relying only on the discrepancy of the sampling set and on the Sobolev-type seminor…

Moment Sampling in Video LLMs for Long-Form Video QA
Mustafa Chasmai, Gauri Jagatap, Gouthaman KV, Grant Van Horn, Subhransu Maji, Andrea Fanelli
https://arxiv.org/abs/2507.00033 …

Moment Sampling in Video LLMs for Long-Form Video QA
Recent advancements in video large language models (Video LLMs) have significantly advanced the field of video question answering (VideoQA). While existing methods perform well on short videos, they often struggle with long-range reasoning in longer videos. To scale Video LLMs for longer video content, frame sub-sampling (selecting frames at regular intervals) is commonly used. However, this approach is suboptimal, often leading to the loss of crucial frames or the inclusion of redundant inform…

4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture
Yutian Chen, Shi Guo, Tianshuo Yang, Lihe Ding, Xiuyuan Yu, Jinwei Gu, Tianfan Xue
https://arxiv.org/abs/2507.05163

4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture
Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are limited to frame rates below 30 FPS (frames per second), and a direct 4D reconstruction of high-speed motion from low FPS input may lead to undesirable results. In this work, we propose a high-speed 4D capturing system only using low FPS cameras, through novel capturing and processing modules. On the capturing side, …

Random Operator-Valued Frames in Hilbert Spaces
James Tian
https://arxiv.org/abs/2508.01914 https://arxiv.org/pdf/2508.01914…

Random Operator-Valued Frames in Hilbert Spaces
This paper develops a framework for operator-valued random variables on separable Hilbert spaces. Random operators are defined as measurable maps into the space of bounded operators, with measurability understood in the strong operator sense. Under a coercivity condition on i.i.d. random positive contractions, an iterative scheme is introduced and shown to converge both in mean square and almost surely. The limit is identified, and the resulting family of iterated random operators forms a rando…

TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation
Zonglin Lyu, Chen Chen
https://arxiv.org/abs/2507.04984 https://

TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation
Video Frame Interpolation (VFI) aims to predict the intermediate frame $I_n$ (we use n to denote time in videos to avoid notation overload with the timestep $t$ in diffusion models) based on two consecutive neighboring frames $I_0$ and $I_1$. Recent approaches apply diffusion models (both image-based and video-based) in this task and achieve strong performance. However, image-based diffusion models are unable to extract temporal information and are relatively inefficient compared to non-diffusi…

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
Zizun Li, Jianjun Zhou, Yifan Wang, Haoyu Guo, Wenzheng Chang, Yang Zhou, Haoyi Zhu, Junyi Chen, Chunhua Shen, Tong He
https://arxiv.org/abs/2509.05296

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool
We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To address this, we first introduce a sliding window mechanism that ensures sufficient information exchange among frames within the window, thereby improving the quality of geometric predictions without large computation. In addition, we leverage a compact repres…

DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset
Mustafa Sakhai, Kaung Sithu, Min Khant Soe Oke, Maciej Wielgosz
https://arxiv.org/abs/2509.04117 https://

DVS-PedX: Synthetic-and-Real Event-Based Pedestrian Dataset
Event cameras like Dynamic Vision Sensors (DVS) report micro-timed brightness changes instead of full frames, offering low latency, high dynamic range, and motion robustness. DVS-PedX (Dynamic Vision Sensor Pedestrian eXploration) is a neuromorphic dataset designed for pedestrian detection and crossing-intention analysis in normal and adverse weather conditions across two complementary sources: (1) synthetic event streams generated in the CARLA simulator for controlled "approach-cross" scenes u…

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
Ayan Banerjee, Josep Llad\'os, Umapada Pal, Anjan Dutta
https://arxiv.org/abs/2509.04123 https://

TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
Text-to-story visualization is challenging due to the need for consistent interaction among multiple characters across frames. Existing methods struggle with character consistency, leading to artifact generation and inaccurate dialogue rendering, which results in disjointed storytelling. In response, we introduce TaleDiffusion, a novel framework for generating multi-character stories with an iterative process, maintaining character consistency, and accurate dialogue assignment via postprocessin…

Durian: Dual Reference-guided Portrait Animation with Attribute Transfer
Hyunsoo Cha, Byungjun Kim, Hanbyul Joo
https://arxiv.org/abs/2509.04434 https://ar…

Durian: Dual Reference-guided Portrait Animation with Attribute Transfer
We present Durian, the first method for generating portrait animation videos with facial attribute transfer from a given reference image to a target portrait in a zero-shot manner. To enable high-fidelity and spatially consistent attribute transfer across frames, we introduce dual reference networks that inject spatial features from both the portrait and attribute images into the denoising process of a diffusion model. We train the model using a self-reconstruction formulation, where two frames…

6-DoF Object Tracking with Event-based Optical Flow and Frames
Zhichao Li, Arren Glover, Chiara Bartolozzi, Lorenzo Natale
https://arxiv.org/abs/2508.14776 https://

6-DoF Object Tracking with Event-based Optical Flow and Frames
Tracking the position and orientation of objects in space (i.e., in 6-DoF) in real time is a fundamental problem in robotics for environment interaction. It becomes more challenging when objects move at high-speed due to frame rate limitations in conventional cameras and motion blur. Event cameras are characterized by high temporal resolution, low latency and high dynamic range, that can potentially overcome the impacts of motion blur. Traditional RGB cameras provide rich visual information tha…