4 accepted papers
Mainstream 3D human pose estimation methods directly predict 3D coordinates of joints from 2D keypoints, suffering from severe depth ambiguity. Pose textual descriptions contain abundant semantic information, which facilitates the model to learn the spatial relationship among different body parts, p
Pre-trained vision-language models (PVLMs) and pseudo-labeling have proven effective in open-vocabulary object detection (OVD). However, when PVLMs trained on image-text data are adapted for OVD tasks, they often encounter challenges with region-text misalignment, resulting in low-quality pseudo-lab…
Approximation-based spectral graph neural networks, which construct graph filters with function approximation, have shown substantial performance in graph learning tasks. Despite their great success, existing works primarily employ polynomial approximation to construct the filters, whereas another s…
"Multi-view hand reconstruction is a critical task for applications in virtual reality and human-computer interaction, but it remains a formidable challenge. Although existing multi-view hand reconstruction methods achieve remarkable accuracy, they typically come with an intensive computational burd…