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.
Timeception for Complex Action Recognition
Graph-Based Global Reasoning Networks
Evolving Space-Time Neural Architectures for Videos
TSM: Temporal Shift Module for Efficient Video Understanding
A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos
Informed Democracy: Voting-based Novelty Detection for Action Recognition
$A^2$-Nets: Double Attention Networks
Representation Flow for Action Recognition
A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling
Predicting Action Tubes
Interaction-aware Spatio-temporal Pyramid Attention Networks for Action Classification
A Short Note about Kinetics-600
Multi-Fiber Networks for Video Recognition
Actor-Centric Relation Network
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
Modality Distillation with Multiple Stream Networks for Action Recognition
Spatio-Temporal Channel Correlation Networks for Action Classification
Videos as Space-Time Region Graphs
VideoCapsuleNet: A Simplified Network for Action Detection
ECO: Efficient Convolutional Network for Online Video Understanding
Rethinking the Faster R-CNN Architecture for Temporal Action Localization
Motion Fused Frames: Data Level Fusion Strategy for Hand Gesture Recognition
M-PACT: An Open Source Platform for Repeatable Activity Classification Research
SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos
Disjoint Multi-task Learning between Heterogeneous Human-centric Tasks
End-to-End Fine-Grained Action Segmentation and Recognition Using Conditional Random Field Models and Discriminative Sparse Coding
Actionable Email Intent Modeling with Reparametrized RNNs
HACS: Human Action Clips and Segments Dataset for Recognition and Temporal Localization
Weakly Supervised Action Localization by Sparse Temporal Pooling Network
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
Compressed Video Action Recognition
A Closer Look at Spatiotemporal Convolutions for Action Recognition
Graph Distillation for Action Detection with Privileged Modalities
Highly Efficient Human Action Recognition with Quantum Genetic Algorithm Optimized Support Vector Machine
Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.