Tootfinder

From Flat to Feeling: A Feasibility and Impact Study on Dynamic Facial Emotions in AI-Generated Avatars
Pegah Salehi, Sajad Amouei Sheshkal, Vajira Thambawita, P{\aa}l Halvorsen
https://arxiv.org/abs/2506.13477

From Flat to Feeling: A Feasibility and Impact Study on Dynamic Facial Emotions in AI-Generated Avatars
Dynamic facial emotion is essential for believable AI-generated avatars; however, most systems remain visually inert, limiting their utility in high-stakes simulations such as virtual training for investigative interviews with abused children. We introduce and evaluate a real-time architecture fusing Unreal Engine 5 MetaHuman rendering with NVIDIA Omniverse Audio2Face to translate vocal prosody into high-fidelity facial expressions on photorealistic child avatars. We implemented a distributed t…

DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
Hayat Ullah, Muhammad Ali Shafique, Abbas Khan, Arslan Munir
https://arxiv.org/abs/2507.12426

DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action Recognition
The landscape of video recognition has evolved significantly, shifting from traditional Convolutional Neural Networks (CNNs) to Transformer-based architectures for improved accuracy. While 3D CNNs have been effective at capturing spatiotemporal dynamics, recent Transformer models leverage self-attention to model long-range spatial and temporal dependencies. Despite achieving state-of-the-art performance on major benchmarks, Transformers remain computationally expensive, particularly with dense …

FacialMotionID: Identifying Users of Mixed Reality Headsets using Abstract Facial Motion Representations
Adriano Castro, Simon Hanisch, Matin Fallahi, Thorsten Strufe
https://arxiv.org/abs/2507.11138

FacialMotionID: Identifying Users of Mixed Reality Headsets using Abstract Facial Motion Representations
Facial motion capture in mixed reality headsets enables real-time avatar animation, allowing users to convey non-verbal cues during virtual interactions. However, as facial motion data constitutes a behavioral biometric, its use raises novel privacy concerns. With mixed reality systems becoming more immersive and widespread, understanding whether face motion data can lead to user identification or inference of sensitive attributes is increasingly important. To address this, we conducted a stu…

Detecting In-Person Conversations in Noisy Real-World Environments with Smartwatch Audio and Motion Sensing
Alice Zhang, Callihan Bertley, Dawei Liang, Edison Thomaz
https://arxiv.org/abs/2507.12002

Detecting In-Person Conversations in Noisy Real-World Environments with Smartwatch Audio and Motion Sensing
Social interactions play a crucial role in shaping human behavior, relationships, and societies. It encompasses various forms of communication, such as verbal conversation, non-verbal gestures, facial expressions, and body language. In this work, we develop a novel computational approach to detect a foundational aspect of human social interactions, in-person verbal conversations, by leveraging audio and inertial data captured with a commodity smartwatch in acoustically-challenging scenarios. To…

ADRD: LLM-Driven Autonomous Driving Based on Rule-based Decision Systems
Fanzhi Zeng, Siqi Wang, Chuzhao Zhu, Li Li
https://arxiv.org/abs/2506.14299 https:…

ADRD: LLM-Driven Autonomous Driving Based on Rule-based Decision Systems
How to construct an interpretable autonomous driving decision-making system has become a focal point in academic research. In this study, we propose a novel approach that leverages large language models (LLMs) to generate executable, rule-based decision systems to address this challenge. Specifically, harnessing the strong reasoning and programming capabilities of LLMs, we introduce the ADRD(LLM-Driven Autonomous Driving Based on Rule-based Decision Systems) framework, which integrates three co…

Search for very-high-energy photon clusters and transients outside the galactic plane in the Fermi-LAT data
M. S. Pshirkov, A. S. Kovankin
https://arxiv.org/abs/2506.12833

Search for very-high-energy photon clusters and transients outside the galactic plane in the Fermi-LAT data
We present a search for spatio-temporal clusters in 16 years of Fermi-LAT very high-energy (VHE; $E>100$ GeV) data using the DBSCAN algorithm, focusing on high Galactic latitude ($|b|>10^{\circ}$) clusters with $\geq5$ events and transient doublets (two events within $\leq 3$ days). Of 107 detected clusters, two correspond to previously unidentified VHE sources: weak BL Lacertae objects 4FGL J0039.1-2219 and 4FGL J0212.2-0219, promising targets for next-generation VHE observatories. D…

Extreme AGN feedback in the fossil galaxy group SDSSTG 4436
D. Eckert, F. Gastaldello, L. Lovisari, S. McGee, T. Pasini, M. Brienza, K. Kolokythas, E. O'Sullivan, A. Simionescu, M. Sun, M. Ayromlou, M. A. Bourne, Y. Chen, W. Cui, S. Ettori, A. Finoguenov, G. Gozaliasl, R. Kale, F. Mernier, B. D. Oppenheimer, G. Schellenberger, R. Seppi, E. Tempel

Extreme AGN feedback in the fossil galaxy group SDSSTG 4436
Supermassive black hole feedback is the currently favoured mechanism to regulate the star formation rate of galaxies and prevent the formation of ultra-massive galaxies ($M_\star>10^{12}M_\odot$). However, the mechanism through which the outflowing energy is transferred to the surrounding medium strongly varies from one galaxy evolution model to another, such that a unified model for AGN feedback does not currently exist. The hot atmospheres of galaxy groups are highly sensitive laboratories of…

MERba: Multi-Receptive Field MambaVision for Micro-Expression Recognition
Xinglong Mao, Shifeng Liu, Sirui Zhao, Tong Xu, Enhong Chen
https://arxiv.org/abs/2506.14468

MERba: Multi-Receptive Field MambaVision for Micro-Expression Recognition
Micro-expressions (MEs) are brief, involuntary facial movements that reveal genuine emotions, holding significant potential in psychological diagnosis and criminal investigations. Despite notable advances in automatic ME recognition (MER), existing methods still struggle to jointly capture localized muscle activations and global facial dependencies, both critical for recognizing subtle emotional cues. To tackle this challenge, we propose MERba, a novel multi-receptive field architecture tailore…

DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation
Ekta Balkrishna Gavas, Chinmay Hegde, Nasir Memon, Sudipta Banerjee
https://arxiv.org/abs/2507.13292

DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation
Accurate age verification can protect underage users from unauthorized access to online platforms and e-commerce sites that provide age-restricted services. However, accurate age estimation can be confounded by several factors, including facial makeup that can induce changes to alter perceived identity and age to fool both humans and machines. In this work, we propose DiffClean which erases makeup traces using a text-guided diffusion model to defend against makeup attacks. DiffClean improves ag…

SyncTalk : High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting
Ziqiao Peng, Wentao Hu, Junyuan Ma, Xiangyu Zhu, Xiaomei Zhang, Hao Zhao, Hui Tian, Jun He, Hongyan Liu, Zhaoxin Fan
https://arxiv.org/abs/2506.14742

SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splatting
Achieving high synchronization in the synthesis of realistic, speech-driven talking head videos presents a significant challenge. A lifelike talking head requires synchronized coordination of subject identity, lip movements, facial expressions, and head poses. The absence of these synchronizations is a fundamental flaw, leading to unrealistic results. To address the critical issue of synchronization, identified as the ''devil'' in creating realistic talking heads, we introduce SyncTalk++, which…