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.
Active Generation Network of Human Skeleton for Action Recognition
MV2MAE: Multi-View Video Masked Autoencoders
Computer Vision for Primate Behavior Analysis in the Wild
Multi-model learning by sequential reading of untrimmed videos for action recognition
Multi-modality action recognition based on dual feature shift in vehicle cabin monitoring
Unsupervised Spatial-Temporal Feature Enrichment and Fidelity Preservation Network for Skeleton based Action Recognition
GTAutoAct: An Automatic Datasets Generation Framework Based on Game Engine Redevelopment for Action Recognition
Training-Free Action Recognition and Goal Inference with Dynamic Frame Selection
From Understanding to Utilization: A Survey on Explainability for Large Language Models
On the Efficacy of Text-Based Input Modalities for Action Anticipation
M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition
ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts
Exploring Missing Modality in Multimodal Egocentric Datasets
DeepEdit: Knowledge Editing as Decoding with Constraints
Cross-lingual Editing in Multilingual Language Models
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models
Understanding Video Transformers via Universal Concept Discovery
GPT4Ego: Unleashing the Potential of Pre-trained Models for Zero-Shot Egocentric Action Recognition
Unsupervised Motion Retargeting for Human-Robot Imitation
Robustness Evaluation of Machine Learning Models for Robot Arm Action Recognition in Noisy Environments
Multi-view Distillation based on Multi-modal Fusion for Few-shot Action Recognition(CLIP-$\mathrm{M^2}$DF)
TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding
Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models
Model Editing at Scale leads to Gradual and Catastrophic Forgetting
Editing Arbitrary Propositions in LLMs without Subject Labels
See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
Collaboratively Self-supervised Video Representation Learning for Action Recognition
HaltingVT: Adaptive Token Halting Transformer for Efficient Video Recognition
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
Two-stream joint matching method based on contrastive learning for few-shot action recognition
Efficient Selective Audio Masked Multimodal Bottleneck Transformer for Audio-Video Classification
Big Data and Deep Learning in Smart Cities: A Comprehensive Dataset for AI-Driven Traffic Accident Detection and Computer Vision Systems
MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing
Explore Human Parsing Modality for Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.