Data to 7 Oct 2026

P-CNN: Pose-based CNN Features for Action Recognition

arXiv 1506.03607 ↗First posted 11 Jun 2015cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

This work targets human action recognition in video. While recent methods typically represent actions by statistics of local video features, here we argue for the importance of a representation derived from human pose. To this end we propose a new Pose-based Convolutional Neural Network descriptor (P-CNN) for action recognition. The descriptor aggregates motion and appearance information along tracks of human body parts. We investigate different schemes of temporal aggregation and experiment with P-CNN features obtained both for automatically estimated and manually annotated human poses. We evaluate our method on the recent and challenging JHMDB and MPII Cooking datasets. For both datasets our method shows consistent improvement over the state of the art.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 10; 2023: 12; 2024: 13; 2025: 5; 2026: 2.

58 papers.

Sort:

By area:

2023AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimationcited by 64
2021Online Knowledge Distillation for Efficient Pose Estimationcited by 55
2021Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspectivecited by 49
2022Signature Methods in Machine Learningcited by 33
2021Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approachescited by 30
2021IIP-Transformer: Intra-Inter-Part Transformer for Skeleton-Based Action Recognitioncited by 17
2023Graph Contrastive Learning for Skeleton-based Action Recognitioncited by 17
2024On the Utility of 3D Hand Poses for Action Recognitioncited by 17
2021VA-RED2: Video Adaptive Redundancy Reductioncited by 15
2021Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networkscited by 15
2025Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoningcited by 13
2021A Multi-viewpoint Outdoor Dataset for Human Action Recognitioncited by 11

38 more

2024Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connectionscited by 11
2021Low-resolution Human Pose Estimationcited by 10
2021Logsig-RNN: a novel network for robust and efficient skeleton-based action recognitioncited by 10
2022FAR: Fourier Aerial Video Recognitioncited by 10
2024VIEW: Visual Imitation Learning with Waypointscited by 10
2022Review on Action Recognition for Accident Detection in Smart City Transportation Systemscited by 8
2023AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoningcited by 8
2023Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimationcited by 7
2023A Hierarchical Graph-based Approach for Recognition and Description Generation of Bimanual Actions in Videoscited by 7
2022Video-based Human Action Recognition using Deep Learning: A Reviewcited by 6
2023Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Surveycited by 6
2023FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillationcited by 5
2024MK-SGN: A Spiking Graph Convolutional Network with Multimodal Fusion and Knowledge Distillation for Skeleton-based Action Recognitioncited by 5
2024RNNs, CNNs and Transformers in Human Action Recognition: A Survey and a Hybrid Modelcited by 5
2021Learning Group Activities from Skeletons without Individual Action Labelscited by 4
2023MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognitioncited by 4
2021What can human minimal videos tell us about dynamic recognition models?cited by 3
2021Shift-BNN: Highly-Efficient Probabilistic Bayesian Neural Network Training via Memory-Friendly Pattern Retrievingcited by 3
2021Rethinking the Data Annotation Process for Multi-view 3D Pose Estimation with Active Learning and Self-Trainingcited by 3
20233DYoga90: A Hierarchical Video Dataset for Yoga Pose Understandingcited by 3
2024Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detectioncited by 3
2024SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognitioncited by 3
2022Explore Spatio-temporal Aggregation for Insubstantial Object Detection: Benchmark Dataset and Baselinecited by 2
2024GCN-DevLSTM: Path Development for Skeleton-Based Action Recognitioncited by 2
2024A Survey on Backbones for Deep Video Action Recognitioncited by 2
2024UAV (Unmanned Aerial Vehicles): Diverse Applications of UAV Datasets in Segmentation, Classification, Detection, and Trackingcited by 2
2021FasterPose: A Faster Simple Baseline for Human Pose Estimationcited by 1
2021Temporal Action Localization Using Gated Recurrent Unitscited by 1
2022No-audio speaking status detection in crowded settings via visual pose-based filtering and wearable accelerationcited by 1
2025Gaseous Object Detectioncited by 1
2021A Global to Local Double Embedding Method for Multi-person Pose Estimationcited by 0
2022ActAR: Actor-Driven Pose Embeddings for Video Action Recognitioncited by 0
2022RADNet: A Deep Neural Network Model for Robust Perception in Moving Autonomous Systemscited by 0
2022Action-based Early Autism Diagnosis Using Contrastive Feature Learningcited by 0
2022SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognitioncited by 0
2023SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognitioncited by 0
2023High-Performance Inference Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 0
2023LocaliseBot: Multi-view 3D object localisation with differentiable rendering for robot graspingcited by 0

50 most cited of 58 All 58 (JSON)