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.
MoViNets: Mobile Video Networks for Efficient Video Recognition
Revisiting ResNets: Improved Training and Scaling Strategies
Domain and View-point Agnostic Hand Action Recognition
Is Space-Time Attention All You Need for Video Understanding?
Video Transformer Network
TCLR: Temporal Contrastive Learning for Video Representation
Human Action Recognition Based on Multi-scale Feature Maps from Depth Video Sequences
TDN: Temporal Difference Networks for Efficient Action Recognition
Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN
MVFNet: Multi-View Fusion Network for Efficient Video Recognition
Depth-Aware Action Recognition: Pose-Motion Encoding through Temporal Heatmaps
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks
Boundary-sensitive Pre-training for Temporal Localization in Videos
3D attention mechanism for fine-grained classification of table tennis strokes using a Twin Spatio-Temporal Convolutional Neural Networks
Improved Soccer Action Spotting using both Audio and Video Streams
Mutual Modality Learning for Video Action Classification
Do not trust the neighbors! Adversarial Metric Learning for Self-Supervised Scene Flow Estimation
Pose And Joint-Aware Action Recognition
Back to the Future: Cycle Encoding Prediction for Self-supervised Contrastive Video Representation Learning
Dissected 3D CNNs: Temporal Skip Connections for Efficient Online Video Processing
Knowledge Fusion Transformers for Video Action Recognition
PERF-Net: Pose Empowered RGB-Flow Net
HAA500: Human-Centric Atomic Action Dataset with Curated Videos
A novel action recognition system for smart monitoring of elderly people using Action Pattern Image and Series CNN with transfer learning
Action similarity judgment based on kinematic primitives
Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations
AssembleNet++: Assembling Modality Representations via Attention Connections
Memory-augmented Dense Predictive Coding for Video Representation Learning
Hierarchical Action Classification with Network Pruning
BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues
MotionSqueeze: Neural Motion Feature Learning for Video Understanding
Region-based Non-local Operation for Video Classification
Alleviating Over-segmentation Errors by Detecting Action Boundaries
AViD Dataset: Anonymized Videos from Diverse Countries
VPN: Learning Video-Pose Embedding for Activities of Daily Living
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.