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.
Mitigating the Language Mismatch and Repetition Issues in LLM-based Machine Translation via Model Editing
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
FAME: Towards Factual Multi-Task Model Editing
Neuron-Level Sequential Editing for Large Language Models
RIPPLECOT: Amplifying Ripple Effect of Knowledge Editing in Language Models via Chain-of-Thought In-Context Learning
Action Selection Learning for Multi-label Multi-view Action Recognition
VEDIT: Latent Prediction Architecture For Procedural Video Representation Learning
Shadow Augmentation for Handwashing Action Recognition: from Synthetic to Real Datasets
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization
LS-HAR: Language Supervised Human Action Recognition with Salient Fusion, Construction Sites as a Use-Case
Precision Knowledge Editing: Enhancing Safety in Large Language Models
UniAdapt: A Universal Adapter for Knowledge Calibration
Self-Updatable Large Language Models with Parameter Integration
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition
Identifying Knowledge Editing Types in Large Language Models
"Why" Has the Least Side Effect on Model Editing
EAGLE: Egocentric AGgregated Language-video Engine
Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion
Perturb, Attend, Detect and Localize (PADL): Robust Proactive Image Defense
Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition
SOAR: Self-supervision Optimized UAV Action Recognition with Efficient Object-Aware Pretraining
Path-adaptive Spatio-Temporal State Space Model for Event-based Recognition with Arbitrary Duration
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
Egocentric zone-aware action recognition across environments
Redefining Data Pairing for Motion Retargeting Leveraging a Human Body Prior
Interpretable Action Recognition on Hard to Classify Actions
StableMamba: Distillation-free Scaling of Large SSMs for Images and Videos
MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language
Mamba Fusion: Learning Actions Through Questioning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.