Pith. sign in

REVIEW 1 cited by

USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation

Not yet reviewed by Pith; the record is open.

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 2412.09220 v2 pith:DZ6YXJNT submitted 2024-12-12 cs.CV

classification cs.CV
keywords denselearningactionrepresentationtasksdecorrelationfeaturerepresentations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative samples, which increases the difficulty of model training. Furthermore, these methods primarily concentrate on learning a global representation for recognition and retrieval tasks, while overlooking the rich and detailed local representations that are crucial for dense prediction tasks. To alleviate these issues, we introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation, called USDRL, which employs feature decorrelation across temporal, spatial, and instance domains in a multi-grained manner to reduce redundancy among dimensions of the representations to maximize information extraction from features. Additionally, we design a Dense Spatio-Temporal Encoder (DSTE) to capture fine-grained action representations effectively, thereby enhancing the performance of dense prediction tasks. Comprehensive experiments, conducted on the benchmarks NTU-60, NTU-120, PKU-MMD I, and PKU-MMD II, across diverse downstream tasks including action recognition, action retrieval, and action detection, conclusively demonstrate that our approach significantly outperforms the current state-of-the-art (SOTA) approaches. Our code and models are available at https://github.com/wengwanjiang/USDRL.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Towards Efficient General Feature Prediction in Masked Skeleton Modeling

    cs.CV 2025-09 conditional novelty 6.0 of 10

    GFP predicts hierarchical high-level features from a jointly trained lightweight target network instead of reconstructing joint coordinates, speeding up masked skeleton pretraining 6.2x while improving downstream accuracy.

Pith tools