Papers with Code 아카이브
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 and Multimodal Data for Daily Activity Understanding
Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections
A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
Functional Abstraction of Knowledge Recall in Large Language Models
REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models
Talk is Not Always Cheap: Promoting Wireless Sensing Models with Text Prompts
Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization
Are you SURE? Enhancing Multimodal Pretraining with Missing Modalities through Uncertainty Estimation
PCBEAR: Pose Concept Bottleneck for Explainable Action Recognition
SkeletonX: Data-Efficient Skeleton-based Action Recognition via Cross-sample Feature Aggregation
Action Anticipation from SoccerNet Football Video Broadcasts
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
AnimeDL-2M: Million-Scale AI-Generated Anime Image Detection and Localization in Diffusion Era
Can We Edit LLMs for Long-Tail Biomedical Knowledge?
H-MoRe: Learning Human-centric Motion Representation for Action Analysis
Knowledge Distillation for Multimodal Egocentric Action Recognition Robust to Missing Modalities
Towards Micro-Action Recognition with Limited Annotations: An Asynchronous Pseudo Labeling and Training Approach
Temporal Alignment-Free Video Matching for Few-shot Action Recognition
NAACL2025 Tutorial: Adaptation of Large Language Models
MultiTSF: Transformer-based Sensor Fusion for Human-Centric Multi-view and Multi-modal Action Recognition
MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion
Efficient Model Editing with Task-Localized Sparse Fine-tuning
Localized Definitions and Distributed Reasoning: A Proof-of-Concept Mechanistic Interpretability Study via Activation Patching
Is Temporal Prompting All We Need For Limited Labeled Action Recognition?
LSC-ADL: An Activity of Daily Living (ADL)-Annotated Lifelog Dataset Generated via Semi-Automatic Clustering
$μ$KE: Matryoshka Unstructured Knowledge Editing of Large Language Models
OwlSight: A Robust Illumination Adaptation Framework for Dark Video Human Action Recognition
CA^2ST: Cross-Attention in Audio, Space, and Time for Holistic Video Recognition
Identifying Multi-modal Knowledge Neurons in Pretrained Transformers via Two-stage Filtering
Action Recognition in Real-World Ambient Assisted Living Environment
Leaking LoRa: An Evaluation of Password Leaks and Knowledge Storage in Large Language Models
ForcePose: A Deep Learning Approach for Force Calculation Based on Action Recognition Using MediaPipe Pose Estimation Combined with Object Detection
DF-Net: The Digital Forensics Network for Image Forgery Detection
Context-Aware Weakly Supervised Image Manipulation Localization with SAM Refinement
Siformer: Feature-isolated Transformer for Efficient Skeleton-based Sign Language Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.