paper-with-me

홈 › Papers

PYSKL: a toolbox for skeleton-based video understanding

2022-04-02 · arXiv 2022 4 · Haodong Duan

A placeholder for the tech report.

📄 PDF Abstract BibTeX

Code (1)

kennymckormick/pyskl pytorch

Tasks

Skeleton Based Action RecognitionVideo Understanding

Similar Papers 제목 키워드 기반

PYSKL: Towards Good Practices for Skeleton Action Recognition

2022-05-19 · Haodong Duan, Jiaqi Wang, Kai Chen, Dahua Lin

We present PYSKL: an open-source toolbox for skeleton-based action recognition based on PyTorch. The toolbox supports a wide variety of skeleton action recognition algorithms, including approaches based on GCN and CNN. I…

Action RecognitionSkeleton Based Action Recognition

Learning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion

2023-05-31 · Quoc-Huy Tran, Muhammad Ahmed, Murad Popattia, M. Hassan Ahmed 외

This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where seq…

RetrievalSelf-Supervised LearningVideo Alignment

Skeletons Speak Louder than Text: A Motion-Aware Pretraining Paradigm for Video-Based Person Re-Identification

2025-11-17 · Rifen Lin, Alex Jinpeng Wang, Jiawei Mo, Min Li arxiv

Multimodal pretraining has revolutionized visual understanding, but its impact on video-based person re-identification (ReID) remains underexplored. Existing approaches often rely on video-text pairs, yet suffer from two…

Person Re-IdentificationRepresentation LearningContrastive Learning

Causal Discovery Toolbox: Uncover causal relationships in Python

2019-03-06 · Diviyan Kalainathan, Olivier Goudet

This paper presents a new open source Python framework for causal discovery from observational data and domain background knowledge, aimed at causal graph and causal mechanism modeling. The 'cdt' package implements the e…

Causal Discovery

T-MOR: Learning Motion-Aware Skeleton Representations for Human Action Recognition

2026-06-19 · Di Yang, Mahmoud Ali, Quan Kong, Gianpiero Francesca 외 arxiv

Vision-language models such as CLIP have recently achieved strong performance on a wide range of visual understanding tasks. However, most existing models rely primarily on appearance-level supervision from images or vid…

Action ClassificationContrastive LearningAction UnderstandingAction Recognition