SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
Existing zero-shot skeleton-based action recognition methods utilize projection networks to learn a shared latent space of skeleton features and semantic embeddings. The inherent imbalance in action recognition datasets, characterized by variable skeleton sequences yet constant class labels, presents significant challenges for alignment. To address the imbalance, we propose SA-DVAE -- Semantic Alignment via Disentangled Variational Autoencoders, a method that first adopts feature disentanglement to separate skeleton features into two independent parts -- one is semantic-related and another is irrelevant -- to better align skeleton and semantic features. We implement this idea via a pair of modality-specific variational autoencoders coupled with a total correction penalty. We conduct experiments on three benchmark datasets: NTU RGB+D, NTU RGB+D 120 and PKU-MMD, and our experimental results show that SA-DAVE produces improved performance over existing methods. The code is available at https://github.com/pha123661/SA-DVAE.
Code (1)
Tasks
Action RecognitionDisentanglementGeneralized Zero Shot skeletal action recognitionSkeleton Based Action RecognitionZero Shot Skeletal Action RecognitionZero-shot skeleton-based action recognitionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
Zero-shot action recognition, which addresses the issue of scalability and generalization in action recognition and allows the models to adapt to new and unseen actions dynamically, is an important research topic in comp…
Action RecognitionMetric LearningSkeleton Based Action RecognitionZero-Shot Action Recognition+1TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition
We firstly present a diffusion-based action recognition with zero-shot learning for skeleton inputs. In zero-shot skeleton-based action recognition, aligning skeleton features with the text features of action labels is e…
Action RecognitionSkeleton Based Action RecognitionText MatchingTriplet+3Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation
We introduce Skeleton-Cache, the first training-free test-time adaptation framework for skeleton-based zero-shot action recognition (SZAR), aimed at improving model generalization to unseen actions during inference. Skel…
Zero-Shot Action RecognitionTest-time AdaptationSyntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition
We introduce SynSE, a novel syntactically guided generative approach for Zero-Shot Learning (ZSL). Our end-to-end approach learns progressively refined generative embedding spaces constrained within and across the involv…
Action RecognitionGeneralized Zero-Shot LearningGeneralized Zero Shot skeletal action recognitionPOS+2Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognition
Skeleton-based zero-shot action recognition aims to recognize unknown human actions based on the learned priors of the known skeleton-based actions and a semantic descriptor space shared by both known and unknown categor…
Action RecognitionAttributeZero-Shot Action RecognitionZero Shot Skeletal Action Recognition