Affinity Contrastive Learning for Skeleton-based Human Activity Understanding
In skeleton-based human activity understanding, existing methods often adopt the contrastive learning paradigm to construct a discriminative feature space. However, many of these approaches fail to exploit the structural inter-class similarities and overlook the impact of anomalous positive samples. In this study, we introduce ACLNet, an Affinity Contrastive Learning Network that explores the intricate clustering relationships among human activity classes to improve feature discrimination. Specifically, we propose an affinity metric to refine similarity measurements, thereby forming activity superclasses that provide more informative contrastive signals. A dynamic temperature schedule is also introduced to adaptively adjust the penalty strength for various superclasses. In addition, we employ a margin-based contrastive strategy to improve the separation of hard positive and negative samples within classes. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, Kinetics-Skeleton, PKU-MMD, FineGYM, and CASIA-B demonstrate the superiority of our method in skeleton-based action recognition, gait recognition, and person re-identification. The source code is available at https://github.com/firework8/ACLNet.
Code (0)
등록된 구현이 없습니다.
Tasks
Person Re-IdentificationContrastive LearningAction RecognitionGait RecognitionSimilar Papers 제목 키워드 기반
DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding
Despite LiDAR (Light Detection and Ranging) being an effective privacy-preserving alternative to RGB cameras to perceive human activities, it remains largely underexplored in the context of multi-modal contrastive pre-tr…
Activity RecognitionHuman Activity RecognitionMoment RetrievalPerson Re-Identification+2Contrastive Self-Supervised Learning for Skeleton Representations
Human skeleton point clouds are commonly used to automatically classify and predict the behaviour of others. In this paper, we use a contrastive self-supervised learning method, SimCLR, to learn representations that capt…
Graph Neural Networkmotion predictionSelf-Supervised LearningSGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic
Group Activity Understanding is predominantly studied as Group Activity Recognition (GAR) task. However, existing GAR benchmarks suffer from coarse-grained activity vocabularies and the only data form in single-view, whi…
Activity RecognitionGroup Activity RecognitionTemporal Group Activity LocalizationLearning by Aligning 2D Skeleton Sequences and Multi-Modality Fusion
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 AlignmentContrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition
Human Activity Recognition is a field of research where input data can take many forms. Each of the possible input modalities describes human behaviour in a different way, and each has its own strengths and weaknesses. W…
Activity RecognitionContrastive LearningHuman Activity RecognitionRetrieval+1