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.
Revisiting 3D ResNets for Video Recognition
roadscene2vec: A Tool for Extracting and Embedding Road Scene-Graphs
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
Pose is all you need: The pose only group activity recognition system (POGARS)
Video Contrastive Learning with Global Context
Enriching Local and Global Contexts for Temporal Action Localization
UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
Let's Play for Action: Recognizing Activities of Daily Living by Learning from Life Simulation Video Games
Attention Bottlenecks for Multimodal Fusion
Video Swin Transformer
TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification
VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?
Proposal Relation Network for Temporal Action Detection
BABEL: Bodies, Action and Behavior with English Labels
Space-time Mixing Attention for Video Transformer
Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
CT-Net: Channel Tensorization Network for Video Classification
Continual 3D Convolutional Neural Networks for Real-time Processing of Videos
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
Representation Learning via Global Temporal Alignment and Cycle-Consistency
Unsupervised Visual Representation Learning by Tracking Patches in Video
VidTr: Video Transformer Without Convolutions
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
Multiscale Vision Transformers
Temporal Query Networks for Fine-grained Video Understanding
Adaptive Intermediate Representations for Video Understanding
Object Priors for Classifying and Localizing Unseen Actions
Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning
TubeR: Tubelet Transformer for Video Action Detection
Recognizing Actions in Videos from Unseen Viewpoints
Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification
Busy-Quiet Video Disentangling for Video Classification
ViViT: A Video Vision Transformer
Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.