Action Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 56
- 보존된 평가 기록
- 650
Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.
In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.
Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Multi-dataset Training of Transformers for Robust Action Recognition
Global Semantic Descriptors for Zero-Shot Action Recognition
Weakly Supervised Two-Stage Training Scheme for Deep Video Fight Detection Model
View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning
Leveraging Self-Supervised Training for Unintentional Action Recognition
FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification
Adaptive Local-Component-aware Graph Convolutional Network for One-shot Skeleton-based Action Recognition
Exploring Modulated Detection Transformer as a Tool for Action Recognition in Videos
FT-HID: A Large Scale RGB-D Dataset for First and Third Person Human Interaction Analysis
Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks
Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos
MECCANO: A Multimodal Egocentric Dataset for Humans Behavior Understanding in the Industrial-like Domain
Real-time Online Video Detection with Temporal Smoothing Transformers
Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks
Differentiable Frequency-based Disentanglement for Aerial Video Action Recognition
Vision Transformers for Action Recognition: A Survey
Predicting the Next Action by Modeling the Abstract Goal
MAiVAR: Multimodal Audio-Image and Video Action Recognizer
PoliTO-IIT-CINI Submission to the EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition
Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition
A Novel Self-Knowledge Distillation Approach with Siamese Representation Learning for Action Recognition
Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition
Temporal Contrastive Learning with Curriculum
MAPLE: Masked Pseudo-Labeling autoEncoder for Semi-supervised Point Cloud Action Recognition
CASPER: Cognitive Architecture for Social Perception and Engagement in Robots
SkeletonMAE: Spatial-Temporal Masked Autoencoders for Self-supervised Skeleton Action Recognition
ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting
Ecsnet: Spatio-temporal feature learning for event camera
Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in Videos
CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation
Modality Mixer for Multi-modal Action Recognition
Lane Change Classification and Prediction with Action Recognition Networks
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
Efficient Attention-free Video Shift Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.