mlsanityData to 13 Oct 2026

Action Recognition Based on Joint Trajectory Maps Using Convolutional Neural Networks

arXiv 1611.02447 ↗First posted 8 Nov 2016cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Recently, Convolutional Neural Networks (ConvNets) have shown promising performances in many computer vision tasks, especially image-based recognition. How to effectively use ConvNets for video-based recognition is still an open problem. In this paper, we propose a compact, effective yet simple method to encode spatio-temporal information carried in 3D skeleton sequences into multiple 2D images, referred to as Joint Trajectory Maps (JTM), and ConvNets are adopted to exploit the discriminative features for real-time human action recognition. The proposed method has been evaluated on three public benchmarks, i.e., MSRC-12 Kinect gesture dataset (MSRC-12), G3D dataset and UTD multimodal human action dataset (UTD-MHAD) and achieved the state-of-the-art results.

Key facts. Cited by 32 papers in the map (data through 13 Oct 2026). First posted on arXiv 8 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 2; 2022: 5; 2023: 10; 2024: 7; 2025: 5; 2026: 3.

32 papers.

Sort:

By area:

  1. 2024SkateFormer: Skeletal-Temporal Transformer for Human Action Recognitioncited by 46
  2. 2022SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognitioncited by 29
  3. 2022Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognitioncited by 18
  4. 2023Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognitioncited by 11
  5. 2024Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learningcited by 11
  6. 2024Event Stream based Human Action Recognition: A High-Definition Benchmark Dataset and Algorithmscited by 11
  7. 2023Skeleton-based Action Recognition through Contrasting Two-Stream Spatial-Temporal Networkscited by 9
  8. 2024Skeleton-Based Human Action Recognition with Noisy Labelscited by 8
  9. 2023STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognitioncited by 7
  10. 2025Trokens: Semantic-Aware Relational Trajectory Tokens for Few-Shot Action Recognitioncited by 7
  11. 2021A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognitioncited by 6
  12. 2022Progressive Cross-modal Knowledge Distillation for Human Action Recognitioncited by 6
20 more
  1. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  2. 20253D Skeleton-Based Action Recognition: A Reviewcited by 6
  3. 2025Towards Robust and Realistic Human Pose Estimation via WiFi Signalscited by 5
  4. 20253D Plant Root Skeleton Detection and Extractioncited by 5
  5. 2023Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN)cited by 4
  6. 2024Deep video representation learning: a surveycited by 4
  7. 2022Transformers in Action Recognition: A Review on Temporal Modelingcited by 3
  8. 2026Universal Skeleton Understanding via Differentiable Rendering and MLLMscited by 3
  9. 2022Collective Intelligent Strategy for Improved Segmentation of COVID-19 from CTcited by 1
  10. 2024Analyzing Data Efficiency and Performance of Machine Learning Algorithms for Assessing Low Back Pain Physical Rehabilitation Exercisescited by 1
  11. 2025Trajectory-guided Motion Perception for Facial Expression Quality Assessment in Neurological Disorderscited by 1
  12. 2021Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognitioncited by 0
  13. 2023Budget-Aware Graph Convolutional Network Design using Probabilistic Magnitude Pruningcited by 0
  14. 2023Miniaturized Graph Convolutional Networks with Topologically Consistent Pruningcited by 0
  15. 2023SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition Systemcited by 0
  16. 2023Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Artcited by 0
  17. 2023One-Shot Multi-Rate Pruning of Graph Convolutional Networkscited by 0
  18. 2024Unsupervised Motion Retargeting for Human-Robot Imitationcited by 0
  19. 2026Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognitioncited by 0
  20. 2026DiMoP: Diffusion-Driven Motion Representation Learning With Frame-Level Pseudo-Classification for Skeleton-Based Action Recognitioncited by 0