Papers with Code 아카이브
Action Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 28
- 보존된 평가 기록
- 444
Image source: The Kinetics Human Action Video Dataset
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Temporal Relational Reasoning in Videos
Non-local Neural Networks
Attend and Interact: Higher-Order Object Interactions for Video Understanding
Learning Gating ConvNet for Two-Stream based Methods in Action Recognition
Action Classification and Highlighting in Videos
ConvNet Architecture Search for Spatiotemporal Feature Learning
Revisiting the Effectiveness of Off-the-shelf Temporal Modeling Approaches for Large-scale Video Classification
Unsupervised Video Understanding by Reconciliation of Posture Similarities
Action recognition by learning pose representations
Temporal Convolution Based Action Proposal: Submission to ActivityNet 2017
Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition
Generic Tubelet Proposals for Action Localization
Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset
The Kinetics Human Action Video Dataset
Single Image Action Recognition by Predicting Space-Time Saliency
A Feature Embedding Strategy for High-level CNN representations from Multiple ConvNets
Temporal Segment Networks for Action Recognition in Videos
Skeleton-based Action Recognition with Convolutional Neural Networks
ActionVLAD: Learning spatio-temporal aggregation for action classification
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection
TS-LSTM and Temporal-Inception: Exploiting Spatiotemporal Dynamics for Activity Recognition
UntrimmedNets for Weakly Supervised Action Recognition and Detection
Deep representation learning for human motion prediction and classification
Asynchronous Temporal Fields for Action Recognition
Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild
Self-Supervised Video Representation Learning With Odd-One-Out Networks
From Traditional to Modern : Domain Adaptation for Action Classification in Short Social Video Clips
Learning Action Concept Trees and Semantic Alignment Networks from Image-Description Data
Generating Videos with Scene Dynamics
Efficient Two-Stream Motion and Appearance 3D CNNs for Video Classification
What makes ImageNet good for transfer learning?
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
Spatio-temporal Co-Occurrence Characterizations for Human Action Classification
VideoLSTM Convolves, Attends and Flows for Action Recognition
Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.