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.
D$^2$ST-Adapter: Disentangled-and-Deformable Spatio-Temporal Adapter for Few-shot Action Recognition
Consistency Prototype Module and Motion Compensation for Few-Shot Action Recognition (CLIP-CP$\mathbf{M^2}$C)
A-Scan2BIM: Assistive Scan to Building Information Modeling
Action Recognition in Video Recordings from Gynecologic Laparoscopy
CAST: Cross-Attention in Space and Time for Video Action Recognition
Just Add $π$! Pose Induced Video Transformers for Understanding Activities of Daily Living
DEVIAS: Learning Disentangled Video Representations of Action and Scene
Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling
Object-based (yet Class-agnostic) Video Domain Adaptation
PALM: Predicting Actions through Language Models
Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes
GeoDeformer: Geometric Deformable Transformer for Action Recognition
LEAP: LLM-Generation of Egocentric Action Programs
Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition
F4D: Factorized 4D Convolutional Neural Network for Efficient Video-level Representation Learning
Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition
Side4Video: Spatial-Temporal Side Network for Memory-Efficient Image-to-Video Transfer Learning
DiffAnt: Diffusion Models for Action Anticipation
DUnE: Dataset for Unified Editing
REACT: Recognize Every Action Everywhere All At Once
Multi-modal Instance Refinement for Cross-domain Action Recognition
VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG
UniHPE: Towards Unified Human Pose Estimation via Contrastive Learning
A New Benchmark and Model for Challenging Image Manipulation Detection
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art
Modality Mixer Exploiting Complementary Information for Multi-modal Action Recognition
GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap
VLM-Eval: A General Evaluation on Video Large Language Models
Continual Learning: Applications and the Road Forward
Flexible Model Interpretability through Natural Language Model Editing
Assessing Knowledge Editing in Language Models via Relation Perspective
SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition System
MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation
Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.