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.
Talk is Not Always Cheap: Promoting Wireless Sensing Models with Text Prompts
InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners
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
Exploring Video-Based Driver Activity Recognition under Noisy Labels
Action Anticipation from SoccerNet Football Video Broadcasts
RadMamba: Efficient Human Activity Recognition through Radar-based Micro-Doppler-Oriented Mamba State-Space Model
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
Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models
Differentially Private 2D Human Pose Estimation
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
Semantically Encoding Activity Labels for Context-Aware Human Activity Recognition
MultiCore+TPU Accelerated Multi-Modal TinyML for Livestock Behaviour Recognition
Human Activity Recognition using RGB-Event based Sensors: A Multi-modal Heat Conduction Model and A Benchmark Dataset
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
Multi-Head Adaptive Graph Convolution Network for Sparse Point Cloud-Based Human Activity Recognition
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
Exploring the Capabilities of LLMs for IMU-based Fine-grained Human Activity Understanding
$μ$KE: Matryoshka Unstructured Knowledge Editing of Large Language Models
Order Matters: On Parameter-Efficient Image-to-Video Probing for Recognizing Nearly Symmetric Actions
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
Redundant feature screening method for human activity recognition based on attention purification mechanism
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.