Contrastive Positive Mining for Unsupervised 3D Action Representation Learning
Recent contrastive based 3D action representation learning has made great progress. However, the strict positive/negative constraint is yet to be relaxed and the use of non-self positive is yet to be explored. In this paper, a Contrastive Positive Mining (CPM) framework is proposed for unsupervised skeleton 3D action representation learning. The CPM identifies non-self positives in a contextual queue to boost learning. Specifically, the siamese encoders are adopted and trained to match the similarity distributions of the augmented instances in reference to all instances in the contextual queue. By identifying the non-self positive instances in the queue, a positive-enhanced learning strategy is proposed to leverage the knowledge of mined positives to boost the robustness of the learned latent space against intra-class and inter-class diversity. Experimental results have shown that the proposed CPM is effective and outperforms the existing state-of-the-art unsupervised methods on the challenging NTU and PKU-MMD datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityRepresentation LearningSelf-supervised Skeleton-based Action RecognitionSimilar Papers 제목 키워드 기반
3D Human Action Representation Learning via Cross-View Consistency Pursuit
In this work, we propose a Cross-view Contrastive Learning framework for unsupervised 3D skeleton-based action Representation (CrosSCLR), by leveraging multi-view complementary supervision signal. CrosSCLR consists of bo…
Action RecognitionContrastive LearningRepresentation LearningSelf-supervised Skeleton-based Action RecognitionUCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining
High-quality phrase representations are essential to finding topics and related terms in documents (a.k.a. topic mining). Existing phrase representation learning methods either simply combine unigram representations in a…
Contrastive LearningRepresentation LearningUCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining
High-quality phrase representations are essential to finding topics and related terms in documents (a.k.a. topic mining). Existing phrase representation learning methods either simply combine unigram representations in…
Contrastive LearningRepresentation LearningContrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
In recent years, self-supervised representation learning for skeleton-based action recognition has been developed with the advance of contrastive learning methods. The existing contrastive learning methods use normal aug…
Action RecognitionContrastive LearningFew-Shot Skeleton-Based Action RecognitionRepresentation Learning+4Improving Unsupervised Relation Extraction by Augmenting Diverse Sentence Pairs
Unsupervised relation extraction (URE) aims to extract relations between named entities from raw text without requiring manual annotations or pre-existing knowledge bases. In recent studies of URE, researchers put a nota…
Contrastive LearningDiversityRelationRelation Extraction+2