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.
Contextual Explainable Video Representation: Human Perception-based Understanding
Deep Learning for Inertial Sensor Alignment
OpenPack: A Large-scale Dataset for Recognizing Packaging Works in IoT-enabled Logistic Environments
FLAG3D: A 3D Fitness Activity Dataset with Language Instruction
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition
Towards Stroke Patients' Upper-limb Automatic Motor Assessment Using Smartwatches
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
Learning Video Representations from Large Language Models
Deep Architectures for Content Moderation and Movie Content Rating
Towards Holistic Surgical Scene Understanding
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data
Automated Level Crossing System: A Computer Vision Based Approach with Raspberry Pi Microcontroller
DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition
Self-Supervised PPG Representation Learning Shows High Inter-Subject Variability
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylight
Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning
Learning Physically Realizable Skills for Online Packing of General 3D Shapes
Applications of human activity recognition in industrial processes -- Synergy of human and technology
Machine Learning 5G Attack Detection in Programmable Logic
Recognition and Prediction of Surgical Gestures and Trajectories Using Transformer Models in Robot-Assisted Surgery
Video-based Pose-Estimation Data as Source for Transfer Learning in Human Activity Recognition
Gated Recurrent Neural Networks with Weighted Time-Delay Feedback
ResFormer: Scaling ViTs with Multi-Resolution Training
Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition
From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks
Action-GPT: Leveraging Large-scale Language Models for Improved and Generalized Action Generation
Distribution estimation and change-point estimation for time series via DNN-based GANs
Towards Good Practices for Missing Modality Robust Action Recognition
XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning
Interaction Region Visual Transformer for Egocentric Action Anticipation
SWL-Adapt: An Unsupervised Domain Adaptation Model with Sample Weight Learning for Cross-User Wearable Human Activity Recognition
Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.