Pith. sign in

REVIEW 6 cited by

Graph Contrastive Learning for Skeleton-based Action Recognition

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2301.10900 v2 pith:SXMHT435 submitted 2023-01-26 cs.CV

Xiaohu Huang , Hao Zhou , Jian Wang , Haocheng Feng , Junyu Han , Errui Ding , Jingdong Wang , Xinggang Wang
show 2 more authors
Wenyu Liu Bin Feng
This is my paper · ORCID
classification cs.CV
keywords contextgraphskeletongclactionlearningcontrastivegcnsrecognition
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In the field of skeleton-based action recognition, current top-performing graph convolutional networks (GCNs) exploit intra-sequence context to construct adaptive graphs for feature aggregation. However, we argue that such context is still \textit{local} since the rich cross-sequence relations have not been explicitly investigated. In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences. In specific, SkeletonGCL associates graph learning across sequences by enforcing graphs to be class-discriminative, \emph{i.e.,} intra-class compact and inter-class dispersed, which improves the GCN capacity to distinguish various action patterns. Besides, two memory banks are designed to enrich cross-sequence context from two complementary levels, \emph{i.e.,} instance and semantic levels, enabling graph contrastive learning in multiple context scales. Consequently, SkeletonGCL establishes a new training paradigm, and it can be seamlessly incorporated into current GCNs. Without loss of generality, we combine SkeletonGCL with three GCNs (2S-ACGN, CTR-GCN, and InfoGCN), and achieve consistent improvements on NTU60, NTU120, and NW-UCLA benchmarks. The source code will be available at \url{https://github.com/OliverHxh/SkeletonGCL}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A skeleton-based action recognition method combining Gaussian-kernel joint dependency refinement with a Hilbert-Schmidt Independence Criterion objective achieves state-of-the-art results on NTU60, NTU120, and NW-UCLA.

  2. Stitch Contrast and Segment_Learning a Human Action Segmentation Model Using Trimmed Skeleton Videos

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Using stitched skeleton clips for contrastive pre-training lets a segmentation model transfer from trimmed source data to untrimmed target videos, with reported mIoU gains over sliding-window baselines.

  3. Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition

    cs.CV 2024-11 conditional novelty 6.0 of 10

    ProtoGCN, a GCN with a prototype reconstruction memory and class-specific contrastive loss, achieves state-of-the-art accuracy on NTU-60, NTU-120, Kinetics-Skeleton, and FineGYM.

  4. DuoCLR: Dual-Surrogate Contrastive Learning for Skeleton-based Human Action Segmentation

    cs.CV 2025-09 conditional novelty 5.0 of 10

    DuoCLR pretrains on trimmed skeleton sequences using Shuffle-and-Warp multi-action permutations and two surrogate tasks, significantly improving action segmentation on untrimmed videos.

  5. Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition

    cs.CV 2024-11 conditional novelty 5.0 of 10

    TSE-GCN uses symmetry-aware graph reactivation and per-frame deformable temporal convolution to reach 90.0 and 91.1 percent on NTU RGB+D 120 with 4.4 million parameters.

  6. SMART-Vision: Survey of Modern Action Recognition Techniques in Vision

    cs.CV 2025-01 conditional novelty 4.0 of 10

    The SMART-Vision survey organizes vision-based human action recognition into a hybrid Venn-diagram taxonomy and reviews the emerging open-set/open-world HAR literature.

Pith tools