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.
Editing Common Sense in Transformers
High Speed Human Action Recognition using a Photonic Reservoir Computer
Editable Graph Neural Network for Node Classifications
Can We Edit Factual Knowledge by In-Context Learning?
Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition
Enhancing Next Active Object-based Egocentric Action Anticipation with Guided Attention
Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning
Editing Large Language Models: Problems, Methods, and Opportunities
Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition
SCP: Soft Conditional Prompt Learning for Aerial Video Action Recognition
Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness
Riemannian Multinomial Logistics Regression for SPD Neural Networks
Motion-Scenario Decoupling for Rat-Aware Video Position Prediction: Strategy and Benchmark
Learning Higher-order Object Interactions for Keypoint-based Video Understanding
Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
Is end-to-end learning enough for fitness activity recognition?
Lightweight Delivery Detection on Doorbell Cameras
M$^2$DAR: Multi-View Multi-Scale Driver Action Recognition with Vision Transformer
MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition
MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing
Few-shot Action Recognition via Intra- and Inter-Video Information Maximization
Learning Video-Conditioned Policies for Unseen Manipulation Tasks
Self-Supervised Video Representation Learning via Latent Time Navigation
Building Neural Networks on Matrix Manifolds: A Gyrovector Space Approach
Modelling Spatio-Temporal Interactions for Compositional Action Recognition
Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition
Cross-view Action Recognition via Contrastive View-invariant Representation
Part Aware Contrastive Learning for Self-Supervised Action Recognition
Physical Adversarial Attacks for Surveillance: A Survey
Improving Rating Prediction in Multi-Criteria Recommender Systems via a Collective Factor Model
Deep Graph Reprogramming
End-to-End Spatio-Temporal Action Localisation with Video Transformers
TSGCNeXt: Dynamic-Static Multi-Graph Convolution for Efficient Skeleton-Based Action Recognition with Long-term Learning Potential
Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis
Search-Map-Search: A Frame Selection Paradigm for Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.