Tootfinder

Feature Geometry for Stereo Sidescan and Forward-looking Sonar
Kalin Norman, Joshua G. Mangelson
https://arxiv.org/abs/2507.05410 https://

Feature Geometry for Stereo Sidescan and Forward-looking Sonar
In this paper, we address stereo acoustic data fusion for marine robotics and propose a geometry-based method for projecting observed features from one sonar to another for a cross-modal stereo sonar setup that consists of both a forward-looking and a sidescan sonar. Our acoustic geometry for sidescan and forward-looking sonar is inspired by the epipolar geometry for stereo cameras, and we leverage relative pose information to project where an observed feature in one sonar image will be found i…

DepthGait: Multi-Scale Cross-Level Feature Fusion of RGB-Derived Depth and Silhouette Sequences for Robust Gait Recognition
Xinzhu Li, Juepeng Zheng, Yikun Chen, Xudong Mao, Guanghui Yue, Wei Zhou, Chenlei Lv, Ruomei Wang, Fan Zhou, Baoquan Zhao
https://arxiv.org/abs/2508.03397

DepthGait: Multi-Scale Cross-Level Feature Fusion of RGB-Derived Depth and Silhouette Sequences for Robust Gait Recognition
Robust gait recognition requires highly discriminative representations, which are closely tied to input modalities. While binary silhouettes and skeletons have dominated recent literature, these 2D representations fall short of capturing sufficient cues that can be exploited to handle viewpoint variations, and capture finer and meaningful details of gait. In this paper, we introduce a novel framework, termed DepthGait, that incorporates RGB-derived depth maps and silhouettes for enhanced gait r…

BS-1-to-N: Diffusion-Based Environment-Aware Cross-BS Channel Knowledge Map Generation for Cell-Free Networks
Zhuoyin Dai, Di Wu, Yong Zeng, Xiaoli Xu, Xinyi Wang, Zesong Fei
https://arxiv.org/abs/2507.23236

BS-1-to-N: Diffusion-Based Environment-Aware Cross-BS Channel Knowledge Map Generation for Cell-Free Networks
Channel knowledge map (CKM) inference across base stations (BSs) is the key to achieving efficient environmentaware communications. This paper proposes an environmentaware cross-BS CKM inference method called BS-1-to-N based on the generative diffusion model. To this end, we first design the BS location embedding (BSLE) method tailored for cross-BS CKM inference to embed BS location information in the feature vector of CKM. Further, we utilize the cross- and self-attention mechanism for the pro…

Comparative Evaluation of Acoustic Feature Extraction Tools for Clinical Speech Analysis
Anna Seo Gyeong Choi, Alexander Richardson, Ryan Partlan, Sunny Tang, Sunghye Cho
https://arxiv.org/abs/2506.01129

Comparative Evaluation of Acoustic Feature Extraction Tools for Clinical Speech Analysis
This study compares three acoustic feature extraction toolkits (OpenSMILE, Praat, and Librosa) applied to clinical speech data from individuals with schizophrenia spectrum disorders (SSD) and healthy controls (HC). By standardizing extraction parameters across the toolkits, we analyzed speech samples from 77 SSD and 87 HC participants and found significant toolkit-dependent variations. While F0 percentiles showed high cross-toolkit correlation (r=0.962 to 0.999), measures like F0 standard devia…

Modality-Aware Feature Matching: A Comprehensive Review of Single- and Cross-Modality Techniques
Weide Liu, Wei Zhou, Jun Liu, Ping Hu, Jun Cheng, Jungong Han, Weisi Lin
https://arxiv.org/abs/2507.22791

Modality-Aware Feature Matching: A Comprehensive Review of Single- and Cross-Modality Techniques
Feature matching is a cornerstone task in computer vision, essential for applications such as image retrieval, stereo matching, 3D reconstruction, and SLAM. This survey comprehensively reviews modality-based feature matching, exploring traditional handcrafted methods and emphasizing contemporary deep learning approaches across various modalities, including RGB images, depth images, 3D point clouds, LiDAR scans, medical images, and vision-language interactions. Traditional methods, leveraging de…

CapRecover: A Cross-Modality Feature Inversion Attack Framework on Vision Language Models
Kedong Xiu, Saiqian Zhang
https://arxiv.org/abs/2507.22828 https://

CapRecover: A Cross-Modality Feature Inversion Attack Framework on Vision Language Models
As Vision-Language Models (VLMs) are increasingly deployed in split-DNN configurations--with visual encoders (e.g., ResNet, ViT) operating on user devices and sending intermediate features to the cloud--there is a growing privacy risk from semantic information leakage. Existing approaches to reconstructing images from these intermediate features often result in blurry, semantically ambiguous images. To directly address semantic leakage, we propose CapRecover, a cross-modality inversion framewor…

Advancing Lung Disease Diagnosis in 3D CT Scans
Qingqiu Li, Runtian Yuan, Junlin Hou, Jilan Xu, Yuejie Zhang, Rui Feng, Hao Chen
https://arxiv.org/abs/2507.00993

Advancing Lung Disease Diagnosis in 3D CT Scans
To enable more accurate diagnosis of lung disease in chest CT scans, we propose a straightforward yet effective model. Firstly, we analyze the characteristics of 3D CT scans and remove non-lung regions, which helps the model focus on lesion-related areas and reduces computational cost. We adopt ResNeSt50 as a strong feature extractor, and use a weighted cross-entropy loss to mitigate class imbalance, especially for the underrepresented squamous cell carcinoma category. Our model achieves a Macr…

PromotionGo at SemEval-2025 Task 11: A Feature-Centric Framework for Cross-Lingual Multi-Emotion Detection in Short Texts
Ziyi Huang, Xia Cui
https://arxiv.org/abs/2507.08499

PromotionGo at SemEval-2025 Task 11: A Feature-Centric Framework for Cross-Lingual Multi-Emotion Detection in Short Texts
This paper presents our system for SemEval 2025 Task 11: Bridging the Gap in Text-Based Emotion Detection (Track A), which focuses on multi-label emotion detection in short texts. We propose a feature-centric framework that dynamically adapts document representations and learning algorithms to optimize language-specific performance. Our study evaluates three key components: document representation, dimensionality reduction, and model training in 28 languages, highlighting five for detailed anal…

Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
Kumud Tripathi, Chowdam Venkata Kumar, Pankaj Wasnik
https://arxiv.org/abs/2506.01365

Attention Is Not Always the Answer: Optimizing Voice Activity Detection with Simple Feature Fusion
Voice Activity Detection (VAD) plays a key role in speech processing, often utilizing hand-crafted or neural features. This study examines the effectiveness of Mel-Frequency Cepstral Coefficients (MFCCs) and pre-trained model (PTM) features, including wav2vec 2.0, HuBERT, WavLM, UniSpeech, MMS, and Whisper. We propose FusionVAD, a unified framework that combines both feature types using three fusion strategies: concatenation, addition, and cross-attention (CA). Experimental results reveal that …

Confidence-driven Gradient Modulation for Multimodal Human Activity Recognition: A Dynamic Contrastive Dual-Path Learning Approach
Panpan Ji, Junni Song, Hang Xiao, Hanyu Liu, Chao Li
https://arxiv.org/abs/2507.02826

Confidence-driven Gradient Modulation for Multimodal Human Activity Recognition: A Dynamic Contrastive Dual-Path Learning Approach
Sensor-based Human Activity Recognition (HAR) is a core technology that enables intelligent systems to perceive and interact with their environment. However, multimodal HAR systems still encounter key challenges, such as difficulties in cross-modal feature alignment and imbalanced modality contributions. To address these issues, we propose a novel framework called the Dynamic Contrastive Dual-Path Network (DCDP-HAR). The framework comprises three key components. First, a dual-path feature extra…

Interpretable Bayesian Tensor Network Kernel Machines with Automatic Rank and Feature Selection
Afra Kilic, Kim Batselier
https://arxiv.org/abs/2507.11136 …

Interpretable Bayesian Tensor Network Kernel Machines with Automatic Rank and Feature Selection
Tensor Network (TN) Kernel Machines speed up model learning by representing parameters as low-rank TNs, reducing computation and memory use. However, most TN-based Kernel methods are deterministic and ignore parameter uncertainty. Further, they require manual tuning of model complexity hyperparameters like tensor rank and feature dimensions, often through trial-and-error or computationally costly methods like cross-validation. We propose Bayesian Tensor Network Kernel Machines, a fully probabil…

C3RL: Rethinking the Combination of Channel-independence and Channel-mixing from Representation Learning
Shusen Ma, Yun-Bo Zhao, Yu Kang
https://arxiv.org/abs/2507.17454

C3RL: Rethinking the Combination of Channel-independence and Channel-mixing from Representation Learning
Multivariate time series forecasting has drawn increasing attention due to its practical importance. Existing approaches typically adopt either channel-mixing (CM) or channel-independence (CI) strategies. CM strategy can capture inter-variable dependencies but fails to discern variable-specific temporal patterns. CI strategy improves this aspect but fails to fully exploit cross-variable dependencies like CM. Hybrid strategies based on feature fusion offer limited generalization and interpretabi…

"We think of generating source code from a prompt as an AI-powered feature of modern IDEs, but the general problem has a rich history in research efforts and domain-specific programming systems." Join William Benton at this year's Berlin Buzzwords to hear him talk about the history of program synthesis, its relationship to the history of AI, and the lessons we can learn from it today.
Learn more:

Transmutation of $^{16}$O and $^{20}$Ne at the Large Hadron Collider
Govert Nijs, Wilke van der Schee
https://arxiv.org/abs/2507.01659 https://

Transmutation of $^{16}$O and $^{20}$Ne at the Large Hadron Collider
In July 2025 the Large Hadron Collider (LHC) will collide $^{16}$O$^{16}$O and $^{20}$Ne$^{20}$Ne isotopes in a quest to understand the physics of ultrarelativistic light ion collisions. One particular feature is that there are many smaller isotopes with the exact same charge over mass ratio that potentially can be produced and contaminate the beam composition. Using the Trajectum framework together with the GEMINI code we provide an estimate of the production cross-section and its consequences…

Self-Supervised Spatial Correspondence Across Modalities
Ayush Shrivastava, Andrew Owens
https://arxiv.org/abs/2506.03148 https://arx…

Self-Supervised Spatial Correspondence Across Modalities
We present a method for finding cross-modal space-time correspondences. Given two images from different visual modalities, such as an RGB image and a depth map, our model identifies which pairs of pixels correspond to the same physical points in the scene. To solve this problem, we extend the contrastive random walk framework to simultaneously learn cycle-consistent feature representations for both cross-modal and intra-modal matching. The resulting model is simple and has no explicit photo-con…

Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization
Chia-Ming Lee, Bo-Cheng Qiu, Ting-Yao Chen, Ming-Han Sun, Fang-Ying Lin, Jung-Tse Tsai, I-An Tsai, Yu-Fan Lin, Chih-Chung Hsu
https://arxiv.org/abs/2507.19858

Taming Domain Shift in Multi-source CT-Scan Classification via Input-Space Standardization
Multi-source CT-scan classification suffers from domain shifts that impair cross-source generalization. While preprocessing pipelines combining Spatial-Slice Feature Learning (SSFL++) and Kernel-Density-based Slice Sampling (KDS) have shown empirical success, the mechanisms underlying their domain robustness remain underexplored. This study analyzes how this input-space standardization manages the trade-off between local discriminability and cross-source generalization. The SSFL++ and KDS pipel…

Multi-partonic interactions, iterated discontinuities and the virtuality expansion in deep inelastic scattering
Zeno Capatti, Lucien Huber, Michael Ruf
https://arxiv.org/abs/2506.16489

Multi-partonic interactions, iterated discontinuities and the virtuality expansion in deep inelastic scattering
We introduce a perturbative model that accounts for the contribution of multi-partonic interactions to collider observables. A key feature of this multi-parton model is that cross sections are organised in terms of building blocks that are separately infrared-finite in virtue of the KLN theorem. We find compact expressions for these building blocks in terms of double discontinuities of Feynman-type integrals obtained by endowing a vacuum graph with additional topological information. The framew…

How the spin-phase variability of cyclotron lines shapes the pulsed fraction spectra: insights from 4U 1538-52
Dimitrios K. Maniadakis, Ekaterina Sokolova-Lapa, Antonino D'A\`i, Elena Ambrosi, Carlo Ferrigno, Giancarlo Cusumano, Alessio Anitra, Luciano Burderi, Melania Del Santo, Tiziana Di Salvo, Felix F\"urst, Rosario Iaria, Valentina La Parola, Christian Malacaria, Peter Kretschmar, Fabio Pintore, Ciro Pinto, Guillermo Andres Rodriguez Castillo

How the spin-phase variability of cyclotron lines shapes the pulsed fraction spectra: insights from 4U 1538-52
We study the energy-dependent pulse profile of 4U 1538-52 and its phase-dependent spectral variability, with emphasis on the behavior around the cyclotron resonant scattering feature at around 21 keV. We analyze all available NuSTAR observations of 4U 1538-52. We decompose energy-resolved pulse profiles into Fourier harmonics to study their energy dependence. Specifically, we compute pulsed fraction spectra, cross-correlation and lag spectra, identifying discontinuities and linking them to feat…

SplashNet: Split-and-Share Encoders for Accurate and Efficient Typing with Surface Electromyography
Nima Hadidi, Jason Chan, Ebrahim Feghhi, Jonathan Kao
https://arxiv.org/abs/2506.12356

SplashNet: Split-and-Share Encoders for Accurate and Efficient Typing with Surface Electromyography
Surface electromyography (sEMG) at the wrists could enable natural, keyboard-free text entry, yet the state-of-the-art emg2qwerty baseline still misrecognizes $51.8\%$ of characters in the zero-shot setting on unseen users and $7.0\%$ after user-specific fine-tuning. We trace many of these errors to mismatched cross-user signal statistics, fragile reliance on high-order feature dependencies, and the absence of architectural inductive biases aligned with the bilateral nature of typing. To addres…

Slot Attention with Re-Initialization and Self-Distillation
Rongzhen Zhao, Yi Zhao, Juho Kannala, Joni Pajarinen
https://arxiv.org/abs/2507.23755 https://a…

Slot Attention with Re-Initialization and Self-Distillation
Unlike popular solutions based on dense feature maps, Object-Centric Learning (OCL) represents visual scenes as sub-symbolic object-level feature vectors, termed slots, which are highly versatile for tasks involving visual modalities. OCL typically aggregates object superpixels into slots by iteratively applying competitive cross attention, known as Slot Attention, with the slots as the query. However, once initialized, these slots are reused naively, causing redundant slots to compete with inf…

DeepPlantCRE: A Transformer-CNN Hybrid Framework for Plant Gene Expression Modeling and Cross-Species Generalization
Yingjun Wu, Jingyun Huang, Liang Ming, Pengcheng Deng, Maojun Wang, Zeyu Zhang
https://arxiv.org/abs/2505.09883

DeepPlantCRE: A Transformer-CNN Hybrid Framework for Plant Gene Expression Modeling and Cross-Species Generalization
The investigation of plant transcriptional regulation constitutes a fundamental basis for crop breeding, where cis-regulatory elements (CREs), as the key factor determining gene expression, have become the focus of crop genetic improvement research. Deep learning techniques, leveraging their exceptional capacity for high-dimensional feature extraction and nonlinear regulatory relationship modeling, have been extensively employed in this field. However, current methodologies present notable limi…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new/
[2/3]:
IPA-CHILDES & G2P : Feature-Rich Resources for Cross-Lingual Phonology and Phonemic Language Mode...

SAM4D: Segment Anything in Camera and LiDAR Streams
Jianyun Xu, Song Wang, Ziqian Ni, Chunyong Hu, Sheng Yang, Jianke Zhu, Qiang Li
https://arxiv.org/abs/2506.21547

SAM4D: Segment Anything in Camera and LiDAR Streams
We present SAM4D, a multi-modal and temporal foundation model designed for promptable segmentation across camera and LiDAR streams. Unified Multi-modal Positional Encoding (UMPE) is introduced to align camera and LiDAR features in a shared 3D space, enabling seamless cross-modal prompting and interaction. Additionally, we propose Motion-aware Cross-modal Memory Attention (MCMA), which leverages ego-motion compensation to enhance temporal consistency and long-horizon feature retrieval, ensuring …

Sommerfeld Enhancement from Quantum Forces for Dark Matter
Steven Ferrante, Maxim Perelstein, Bingrong Yu
https://arxiv.org/abs/2507.12522 https://

Sommerfeld Enhancement from Quantum Forces for Dark Matter
Quantum forces are long-range interactions that arise only at the loop level. In this work, we study the Sommerfeld enhancement of dark matter (DM) annihilation cross sections caused by quantum forces. One notable feature of quantum forces is that they are subject to coherent enhancement in the presence of a background of mediator particles, which occurs in many situations in cosmology. We show that this effect has important implications for the Sommerfeld enhancement and DM physics. For the fi…

Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries
Pengfei Cai, Yan Song, Qing Gu, Nan Jiang, Haoyu Song, Ian McLoughlin
https://arxiv.org/abs/2507.16343

Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries
Most existing sound event detection~(SED) algorithms operate under a closed-set assumption, restricting their detection capabilities to predefined classes. While recent efforts have explored language-driven zero-shot SED by exploiting audio-language models, their performance is still far from satisfactory due to the lack of fine-grained alignment and cross-modal feature fusion. In this work, we propose the Detect Any Sound Model (DASM), a query-based framework for open-vocabulary SED guided by …

Cross-Modality Masked Learning for Survival Prediction in ICI Treated NSCLC Patients
Qilong Xing, Zikai Song, Bingxin Gong, Lian Yang, Junqing Yu, Wei Yang
https://arxiv.org/abs/2507.06994

Cross-Modality Masked Learning for Survival Prediction in ICI Treated NSCLC Patients
Accurate prognosis of non-small cell lung cancer (NSCLC) patients undergoing immunotherapy is essential for personalized treatment planning, enabling informed patient decisions, and improving both treatment outcomes and quality of life. However, the lack of large, relevant datasets and effective multi-modal feature fusion strategies pose significant challenges in this domain. To address these challenges, we present a large-scale dataset and introduce a novel framework for multi-modal feature fu…

Training-Free Voice Conversion with Factorized Optimal Transport
Alexander Lobashev, Assel Yermekova, Maria Larchenko
https://arxiv.org/abs/2506.09709 http…

Training-Free Voice Conversion with Factorized Optimal Transport
This paper introduces Factorized MKL-VC, a training-free modification for kNN-VC pipeline. In contrast with original pipeline, our algorithm performs high quality any-to-any cross-lingual voice conversion with only 5 second of reference audio. MKL-VC replaces kNN regression with a factorized optimal transport map in WavLM embedding subspaces, derived from Monge-Kantorovich Linear solution. Factorization addresses non-uniform variance across dimensions, ensuring effective feature transformation.…

CATVis: Context-Aware Thought Visualization
Tariq Mehmood, Hamza Ahmad, Muhammad Haroon Shakeel, Murtaza Taj
https://arxiv.org/abs/2507.11522 https://

CATVis: Context-Aware Thought Visualization
EEG-based brain-computer interfaces (BCIs) have shown promise in various applications, such as motor imagery and cognitive state monitoring. However, decoding visual representations from EEG signals remains a significant challenge due to their complex and noisy nature. We thus propose a novel 5-stage framework for decoding visual representations from EEG signals: (1) an EEG encoder for concept classification, (2) cross-modal alignment of EEG and text embeddings in CLIP feature space, (3) captio…