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.
Hierarchical Temporal Convolution Network:Towards Privacy-Centric Activity Recognition
Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition
Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition
Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration
WiFi CSI Based Temporal Activity Detection via Dual Pyramid Network
MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition
Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
Do Language Models Understand Time?
Learning from Massive Human Videos for Universal Humanoid Pose Control
ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
Future Aspects in Human Action Recognition: Exploring Emerging Techniques and Ethical Influences
CompactFlowNet: Efficient Real-time Optical Flow Estimation on Mobile Devices
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
ConceptEdit: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning
Building a Multi-modal Spatiotemporal Expert for Zero-shot Action Recognition with CLIP
USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
Manta: Enhancing Mamba for Few-Shot Action Recognition of Long Sub-Sequence
SAT: Dynamic Spatial Aptitude Training for Multimodal Language Models
Mobile-TeleVision: Predictive Motion Priors for Humanoid Whole-Body Control
Action Recognition based Industrial Safety Violation Detection
KNN-MMD: Cross Domain Wireless Sensing via Local Distribution Alignment
CCS: Continuous Learning for Customized Incremental Wireless Sensing Services
D-LORD for Motion Stylization
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Unveiling Concept Attribution in Diffusion Models
Proximal Control of UAVs with Federated Learning for Human-Robot Collaborative Domains
EdgeOAR: Real-time Online Action Recognition On Edge Devices
ForgerySleuth: Empowering Multimodal Large Language Models for Image Manipulation Detection
SkelMamba: A State Space Model for Efficient Skeleton Action Recognition of Neurological Disorders
Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition
TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognition
An End-to-End Two-Stream Network Based on RGB Flow and Representation Flow for Human Action Recognition
EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond
LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.