Description
Book Synopsis.- EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans.
.- HybridFormer: Bridging Local and Global Spatio-Temporal Dynamics for Efficient Skeleton-Based Action Recognition.
.- MPL: Lifting 3D Human Pose from Multi-view 2D Poses.
.- THP3D: Text-Driven Multi-Granularity 3D Human Parsing.
.- ROMEO: Revisiting Optimization Methods for Reconstructing 3D HumanObject Interaction Models From Images.
.- Leveraging key-points Encoded Human Pose Images for Human Activity Recognition.
.- Enhancing Thermal MOT: A Novel Box Association Method Leveraging Thermal Identity and Motion Similarity.
.- Multi-Camera Industrial Open-Set Person Re-Identification and Tracking.
.- Enhanced Action Quality Assessment with Two-Stream Pose and Video Feature Integration.
.- PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation.
.- Enhancing Gait Recognition: Data Augmentation via Physics-Based Biomechanical Simulation.
.- Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGB.
.- VATE: a Large Scale Multimodal Spontaneous Dataset for Affective Evaluation.
.- Guidelines for Query and Gallery Image Extraction in Person ReIdentification Systems.
.- Pose-independent 3D Anthropometry from Sparse Data.
.- Exploring 3D Face Reconstruction and Fusion Methods for Face Verification: A Case-Study in Video Surveillance.
.- FlexControl: Flexible and Efficient Full-Body Controllable Text-to-Motion Generation.
.- Coarse to Fine Human Mesh Recovery with Transformers.
.- Motion Reconstruction via Human Anatomy Diffusion from Sparse Tracking.
.- A vision-based framework for human behavior understanding in industrial assembly lines.
.- Boosting Pose Estimators via Cross-Representation Distillation.
.- Upper-Body Pose-based Gaze Estimation for Privacy-Preserving 3D Gaze Target Detection.
