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.
Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition
Discover and Mitigate Unknown Biases with Debiasing Alternate Networks
GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning
Time Is MattEr: Temporal Self-supervision for Video Transformers
Multi-manifold Attention for Vision Transformers
Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition
LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training
Is Appearance Free Action Recognition Possible?
Efficient Human Vision Inspired Action Recognition using Adaptive Spatiotemporal Sampling
Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network
Compound Prototype Matching for Few-shot Action Recognition
Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations
1st Place Solution to the EPIC-Kitchens Action Anticipation Challenge 2022
VidConv: A modernized 2D ConvNet for Efficient Video Recognition
Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition
EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 2022: Team HNU-FPV Technical Report
Unsupervised Learning for Human Sensing Using Radio Signals
Federated Self-supervised Learning for Video Understanding
Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
Large-scale Robustness Analysis of Video Action Recognition Models
Disentangled Action Recognition with Knowledge Bases
Noise and Edge Based Dual Branch Image Manipulation Detection
Dissecting Self-Supervised Learning Methods for Surgical Computer Vision
Video + CLIP Baseline for Ego4D Long-term Action Anticipation
Spatial Transformer Network with Transfer Learning for Small-scale Fine-grained Skeleton-based Tai Chi Action Recognition
Skeleton-based Action Recognition via Adaptive Cross-Form Learning
Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values
A New Adjacency Matrix Configuration in GCN-based Models for Skeleton-based Action Recognition
Pedestrian 3D Bounding Box Prediction
Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos
Defending Multimodal Fusion Models against Single-Source Adversaries
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space
NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.