mlsanityData to 7 Oct 2026

Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognition

arXiv 2101.11530 ↗First posted 27 Jan 2021cs.CV cs.GR cs.MMcited by 24

Not on the map. Why?

Abstract (arXiv)

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 involved modalities (visual, language). The inter-modal constraints are defined between action sequence embedding and embeddings of Parts of Speech (PoS) tagged words in the corresponding action description. We deploy SynSE for the task of skeleton-based action sequence recognition. Our design choices enable SynSE to generalize compositionally, i.e., recognize sequences whose action descriptions contain words not encountered during training. We also extend our approach to the more challenging Generalized Zero-Shot Learning (GZSL) problem via a confidence-based gating mechanism. We are the first to present zero-shot skeleton action recognition results on the large-scale NTU-60 and NTU-120 skeleton action datasets with multiple splits. Our results demonstrate SynSE's state of the art performance in both ZSL and GZSL settings compared to strong baselines on the NTU-60 and NTU-120 datasets. The code and pretrained models are available at https://github.com/skelemoa/synse-zsl

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 22 of its 27 references that are in the map. First posted on arXiv 27 Jan 2021.

Builds on

22 of 27 references.

References · 22

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  6. 2016NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysiscited by 683
  7. 2019NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understandingcited by 530
  8. 2020Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognitioncited by 339
  9. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  10. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  11. 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
  12. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
10 more
  1. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  2. 2015Label-Embedding for Image Classificationcited by 164
  3. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  4. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  5. 2019Fine-Grained Action Retrieval Through Multiple Parts-of-Speech Embeddingscited by 101
  6. 2018View Adaptive Neural Networks for High Performance Skeleton-based Human Action Recognitioncited by 84
  7. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  8. 2017Learning Robust Visual-Semantic Embeddingscited by 56
  9. 2019Skeleton based Zero Shot Action Recognition in Joint Pose-Language Semantic Spacecited by 19
  10. 2017Deep Matching Autoencoderscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 0; 2023: 3; 2024: 7; 2025: 4; 2026: 8.

24 papers.

Sort:

By area:

  1. 2023Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximizationcited by 24
  2. 2024Part-aware Unified Representation of Language and Skeleton for Zero-shot Action Recognitioncited by 23
  3. 2024Fine-Grained Side Information Guided Dual-Prompts for Zero-Shot Skeleton Action Recognitioncited by 19
  4. 2024SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoderscited by 19
  5. 2024Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognitioncited by 13
  6. 2023Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognitioncited by 9
  7. 2024Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignmentcited by 9
  8. 2024Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognitioncited by 9
  9. 2024An Information Compensation Framework for Zero-Shot Skeleton-based Action Recognitioncited by 7
  10. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  11. 2025Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognitioncited by 6
  12. 2021ZS-SLR: Zero-Shot Sign Language Recognition from RGB-D Videoscited by 4
12 more
  1. 2025Zero-Shot Skeleton-Based Action Recognition With Prototype-Guided Feature Alignmentcited by 4
  2. 2021Multi-Modal Zero-Shot Sign Language Recognitioncited by 3
  3. 2025Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptationcited by 3
  4. 2026SkeletonContext: Skeleton-side Context Prompt Learning for Zero-Shot Skeleton-based Action Recognitioncited by 3
  5. 2026Universal Skeleton Understanding via Differentiable Rendering and MLLMscited by 2
  6. 2026Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognitioncited by 2
  7. 2025DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognitioncited by 1
  8. 2026SCALE: Semantic- and Confidence-Aware Conditional Variational Autoencoder for Zero-shot Skeleton-based Action Recognitioncited by 1
  9. 2026Toward Universal Skeleton-Based Action Recognition across Heterogeneous Skeletons and Open Vocabulariescited by 0
  10. 2026PoseBridge: Bridging the Skeletonization Gap for Zero-Shot Skeleton-Based Action Recognitioncited by 0
  11. 2026GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognitioncited by 0
  12. 2026Visual Anchoring in Diffusion: Multimodal Zero-Shot Skeleton Action Recognitioncited by 0