Papers with Code 아카이브
Activity Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 11
- 평가표
- 4
- 보존된 평가 기록
- 10
Human Activity Recognition is the problem of identifying events performed by humans given a video input. It is formulated as a binary (or multiclass) classification problem of outputting activity class labels. Activity Recognition is an important problem with many societal applications including smart surveillance, video search/retrieval, intelligent robots, and other monitoring systems.
Source: Learning Latent Sub-events in Activity Videos Using Temporal Attention Filters
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
When Spatial meets Temporal in Action Recognition
Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction
DATTA: Domain-Adversarial Test-Time Adaptation for Cross-Domain WiFi-Based Human Activity Recognition
Extending Video Masked Autoencoders to 128 frames
Bi-LSTM neural network for EEG-based error detection in musicians' performance
Rethinking Top Probability from Multi-view for Distracted Driver Behaviour Localization
Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition
Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models
Efficient Transfer Learning for Video-language Foundation Models
Neuron: Learning Context-Aware Evolving Representations for Zero-Shot Skeleton Action Recognition
Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognition
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition
Towards Next-Generation Medical Agent: How o1 is Reshaping Decision-Making in Medical Scenarios
FedAli: Personalized Federated Learning with Aligned Prototypes through Optimal Transport
FedSub: Introducing class-aware Subnetworks Fusion to Enhance Personalized Federated Learning in Ubiquitous Systems
Process-aware Human Activity Recognition
Model Editing for LLMs4Code: How Far are We?
Grounding Video Models to Actions through Goal Conditioned Exploration
Past, Present, and Future of Sensor-Based Human Activity Recognition Using Wearables: A Surveying Tutorial on a Still Challenging Task
Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)
Federated Split Learning for Human Activity Recognition with Differential Privacy
Video RWKV:Video Action Recognition Based RWKV
Autoregressive Adaptive Hypergraph Transformer for Skeleton-based Activity Recognition
Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures
WiFlexFormer: Efficient WiFi-Based Person-Centric Sensing
ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition
Learning Where to Edit Vision Transformers
AM Flow: Adapters for Temporal Processing in Action Recognition
Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-based Human Activity Recognition
Benchmarking Vision, Language, & Action Models on Robotic Learning Tasks
HiMemFormer: Hierarchical Memory-Aware Transformer for Multi-Agent Action Anticipation
STAA: Spatio-Temporal Attention Attribution for Real-Time Interpreting Transformer-based Video Models
Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
Human Action Recognition (HAR) Using Skeleton-based Spatial Temporal Relative Transformer Network: ST-RTR
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.