Paper-Conference

UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training
Despite decades of research on data collection and model architectures, current gaze estimation models encounter significant challenges …
PDF Cite Code
UniGaze: Towards Universal Gaze Estimation via Large-scale Pre-Training
Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization
Online test-time adaptation addresses the train-test domain gap by adapting the model on unlabeled streaming test inputs before making …
Cite
Robust Long-term Test-Time Adaptation for 3D Human Pose Estimation through Motion Discretization
Generative Modeling of Shape-Dependent Self-Contact Human Poses
One can hardly model self-contact of human poses without considering underlying body shapes. For example, the pose of rubbing a belly …
PDF Cite Code
Generative Modeling of Shape-Dependent Self-Contact Human Poses
AssemblyHands-X: Modeling 3D Hand-Body Coordination for Understanding Bimanual Human Activities
Bimanual human activities inherently involve coordinated movements of both hands and body. However, the impact of this coordination in …
PDF Cite DOI
AssemblyHands-X: Modeling 3D Hand-Body Coordination for Understanding Bimanual Human Activities
EgoInstruct: An Egocentric Video Dataset of Face-to-face Instructional Interactions with Multi-modal LLM Benchmarking
Analyzing instructional interactions between an instructor and a learner who are co-present in the same physical space is a critical …
PDF Cite
EgoInstruct: An Egocentric Video Dataset of Face-to-face Instructional Interactions with Multi-modal LLM Benchmarking
Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions
As AI systems become increasingly integrated into human lives, endowing them with robust social intelligence has emerged as a critical …
PDF Cite DOI
Can MLLMs Read the Room? A Multimodal Benchmark for Verifying Truthfulness in Multi-Party Social Interactions
Affordance-Guided Diffusion Prior for 3D Hand Reconstruction
How can we reconstruct 3D hand poses when large portions of the hand are heavily occluded by itself or by objects? Humans often resolve …
PDF Cite DOI
Affordance-Guided Diffusion Prior for 3D Hand Reconstruction
Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance
This paper presents a novel inertial localization framework named Egocentric Action-aware Inertial Localization (EAIL), which leverages …
PDF Cite Code
Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance
Data-driven Head Motion Generation through Natural Gaze-Head Coordination
We present the first data-driven approach to model temporal gaze-head coordination from large-scale in-the-wild facial videos. To …
PDF Cite Project DOI
Data-driven Head Motion Generation through Natural Gaze-Head Coordination
ChartQC: Question Classification from Human Attention Data on Charts
Understanding how humans interact with information visualizations is crucial for improving user experience and designing effective …
PDF Cite DOI
ChartQC: Question Classification from Human Attention Data on Charts