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.
Scalable Model Editing via Customized Expert Networks
Deep Image Composition Meets Image Forgery
Leveraging YOLO-World and GPT-4V LMMs for Zero-Shot Person Detection and Action Recognition in Drone Imagery
Language Model Guided Interpretable Video Action Reasoning
Disentangled Pre-training for Human-Object Interaction Detection
PREGO: online mistake detection in PRocedural EGOcentric videos
LLMs are Good Action Recognizers
Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
Dialectical Alignment: Resolving the Tension of 3H and Security Threats of LLMs
Multi-hop Question Answering under Temporal Knowledge Editing
A Unified Framework for Human-centric Point Cloud Video Understanding
Hypergraph-based Multi-View Action Recognition using Event Cameras
Retrieval-enhanced Knowledge Editing in Language Models for Multi-Hop Question Answering
Robust and Scalable Model Editing for Large Language Models
OmniVid: A Generative Framework for Universal Video Understanding
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
Understanding Long Videos with Multimodal Language Models
DeGCN: Deformable Graph Convolutional Networks for Skeleton-Based Action Recognition
Enhancing Video Transformers for Action Understanding with VLM-aided Training
EgoExoLearn: A Dataset for Bridging Asynchronous Ego- and Exo-centric View of Procedural Activities in Real World
Emotion Recognition from the perspective of Activity Recognition
General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing
GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition
InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
A Unified Framework for Model Editing
Editing Knowledge Representation of Language Model via Rephrased Prefix Prompts
Locating and Mitigating Gender Bias in Large Language Models
Detoxifying Large Language Models via Knowledge Editing
vid-TLDR: Training Free Token merging for Light-weight Video Transformer
BadEdit: Backdooring large language models by model editing
Hierarchical NeuroSymbolic Approach for Comprehensive and Explainable Action Quality Assessment
Editing Massive Concepts in Text-to-Image Diffusion Models
Benchmarking Badminton Action Recognition with a New Fine-Grained Dataset
Intention Action Anticipation Model with Guide-Feedback Loop Mechanism
ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.