Papers with Code 아카이브
Action Recognition In Videos
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 17
- 보존된 평가 기록
- 45
Action Recognition in Videos is a task in computer vision and pattern recognition where the goal is to identify and categorize human actions performed in a video sequence. The task involves analyzing the spatiotemporal dynamics of the actions and mapping them to a predefined set of action classes, such as running, jumping, or swimming.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Space-time Mixing Attention for Video Transformer
Technical Report: Temporal Aggregate Representations
Anticipative Video Transformer
Anticipating human actions by correlating past with the future with Jaccard similarity measures
Learning Implicit Temporal Alignment for Few-shot Video Classification
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
Higher Order Recurrent Space-Time Transformer for Video Action Prediction
Busy-Quiet Video Disentangling for Video Classification
NAS-TC: Neural Architecture Search on Temporal Convolutions for Complex Action Recognition
Forecasting Action through Contact Representations from First Person Video
Video Transformer Network
Learning to Anticipate Egocentric Actions by Imagination
Tensor Representations for Action Recognition
TDN: Temporal Difference Networks for Efficient Action Recognition
Towards Improving Spatiotemporal Action Recognition in Videos
Developing Motion Code Embedding for Action Recognition in Videos
Multi-Temporal Convolutions for Human Action Recognition in Videos
Pose And Joint-Aware Action Recognition
Toward Accurate Person-level Action Recognition in Videos of Crowded Scenes
Deep Sequence Learning for Video Anticipation: From Discrete and Deterministic to Continuous and Stochastic
Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
Region-based Non-local Operation for Video Classification
IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos
Self-Supervised MultiModal Versatile Networks
Video Representation Learning with Visual Tempo Consistency
Dynamic Sampling Networks for Efficient Action Recognition in Videos
Unsupervised Learning of Video Representations via Dense Trajectory Clustering
Rescaling Egocentric Vision
Learn to cycle: Time-consistent feature discovery for action recognition
Egocentric Object Manipulation Graphs
Temporal Aggregate Representations for Long-Range Video Understanding
Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs
Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video
Knowledge Distillation for Action Anticipation via Label Smoothing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.