mlsanityData to 14 Oct 2026

SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders

arXiv 2407.13460 ↗First posted 18 Jul 2024cs.CV cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 20 of its 29 references that are in the map. First posted on arXiv 18 Jul 2024.

Builds on

20 of 29 references.

References · 20

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,209
  7. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 686
  8. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 533
  9. 2021Revisiting Skeleton-based Action Recognitioncited by 257
  10. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  11. 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
  12. 2020A Review of Generalized Zero-Shot Learning Methodscited by 159
8 more
  1. 2017PKU-MMD: A Large Scale Benchmark for Continuous Multi-Modal Human Action Understandingcited by 101
  2. 2019Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddingscited by 101
  3. 2013Deep Learning of Representations: Looking Forwardcited by 84
  4. 2017Intel RealSense Stereoscopic Depth Camerascited by 83
  5. 2017Learning Robust Visual-Semantic Embeddingscited by 56
  6. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  7. 2021Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognitioncited by 24
  8. 2023Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximizationcited by 24

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 10.

19 papers.

Sort:

By area:

  1. 2024Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognitioncited by 13
  2. 2024Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognitioncited by 9
  3. 20253D Skeleton-Based Action Recognition: A Reviewcited by 6
  4. 2025Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognitioncited by 6
  5. 2025Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognitioncited by 3
  6. 2025Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptationcited by 3
  7. 2026SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognitioncited by 3
  8. 2026Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognitioncited by 2
  9. 2024Homogeneous Dynamics Space for Heterogeneous Humanscited by 1
  10. 2025SkeletonAgent: An Agentic Interaction Framework for Skeleton-based Action Recognitioncited by 1
  11. 2025DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognitioncited by 1
  12. 2026SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognitioncited by 1
7 more
  1. 2026Toward Universal Skeleton-Based Action Recognition across Heterogeneous Skeletons and Open Vocabulariescited by 0
  2. 2026Action Motifs: Self-Supervised Hierarchical Representation of Human Body Movementscited by 0
  3. 2026PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognitioncited by 0
  4. 2026Cross-Domain Human Action Recognition from Multiview Motion and Textual Descriptionscited by 0
  5. 2026Partial Skeleton Visibility for Action Recognition: A Constrained Field-of-View Approachcited by 0
  6. 2026GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognitioncited by 0
  7. 2026Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognitioncited by 0