mlsanityData to 7 Oct 2026

Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection

arXiv 1704.00616 ↗First posted 3 Apr 2017cs.CV cs.AI cs.HCcited by 34

Not on the map. Why?

Abstract (arXiv)

General human action recognition requires understanding of various visual cues. In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images. For the integration, we introduce a Markov chain model which adds cues successively. The resulting approach is efficient and applicable to action classification as well as to spatial and temporal action localization. The two contributions clearly improve the performance over respective baselines. The overall approach achieves state-of-the-art action classification performance on HMDB51, J-HMDB and NTU RGB+D datasets. Moreover, it yields state-of-the-art spatio-temporal action localization results on UCF101 and J-HMDB.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 11; 2023: 5; 2024: 4; 2025: 3.

34 papers.

Sort:

  1. 2022Two-Stream Network for Sign Language Recognition and Translationcited by 122
  2. 2021Skeleton Aware Multi-modal Sign Language Recognitioncited by 101
  3. 2021Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detectioncited by 32
  4. 2021Sign Language Recognition via Skeleton-Aware Multi-Model Ensemblecited by 16
  5. 2021Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognitioncited by 13
  6. 2022A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognitioncited by 9
  7. 2022Skeleton Sequence and RGB Frame Based Multi-Modality Feature Fusion Network for Action Recognitioncited by 6
  8. 2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
  9. 2023A Survey on Deep Learning-based Spatio-temporal Action Detectioncited by 5
  10. 2021Hierarchical growing grid networks for skeleton based action recognitioncited by 4
  11. 2022Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognitioncited by 4
  12. 2024Learning Visual Abstract Reasoning through Dual-Stream Networkscited by 4
22 more
  1. 2021Adaptive Intermediate Representations for Video Understandingcited by 3
  2. 2021Unsupervised View-Invariant Human Posture Representationcited by 3
  3. 2021Video Action Recognition Using spatio-temporal optical flow video framescited by 2
  4. 2024EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognitioncited by 2
  5. 2024Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)cited by 2
  6. 2025Content-Distortion High-Order Interaction for Blind Image Quality Assessmentcited by 2
  7. 2023TransNet: A Transfer Learning-Based Network for Human Action Recognitioncited by 1
  8. 2024ReL-SAR: Representation Learning for Skeleton Action Recognition with Convolutional Transformers and BYOLcited by 1
  9. 2021SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysiscited by 0
  10. 2021VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Searchcited by 0
  11. 2021Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generationcited by 0
  12. 2022Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectorscited by 0
  13. 2022Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networkscited by 0
  14. 2022ActAR: Actor-Driven Pose Embeddings for Video Action Recognitioncited by 0
  15. 2022Explanation-Guided Fairness Testing through Genetic Algorithmcited by 0
  16. 2022Using Graph Neural Networks for Program Terminationcited by 0
  17. 2022Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videoscited by 0
  18. 2022Action-based Early Autism Diagnosis Using Contrastive Feature Learningcited by 0
  19. 2023Tribe or Not? Critical Inspection of Group Differences Using TribalGramcited by 0
  20. 2023Seeing the Pose in the Pixels: Learning Pose-Aware Representations in Vision Transformerscited by 0
  21. 2025Exploring Simple Siamese Network for High-Resolution Video Quality Assessmentcited by 0
  22. 2025Dual Guidance Semi-Supervised Action Detectioncited by 0