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.
Discriminating sensor activation in activity recognition within multi-occupancy environments based on nearby interaction
Learning a Condensed Frame for Memory-Efficient Video Class-Incremental Learning
Deep Learning Computer Vision Algorithms for Real-time UAVs On-board Camera Image Processing
Fine-grained Human Activity Recognition Using Virtual On-body Acceleration Data
No-audio speaking status detection in crowded settings via visual pose-based filtering and wearable acceleration
Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition
Evaluation and comparison of federated learning algorithms for Human Activity Recognition on smartphones
Uncertainty-DTW for Time Series and Sequences
Text2Model: Text-based Model Induction for Zero-shot Image Classification
Learning Joint Representation of Human Motion and Language
Handwashing Action Detection System for an Autonomous Social Robot
IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text
The Contribution of Human Body Capacitance/Body-Area Electric Field To Individual and Collaborative Activity Recognition
Adversarial Domain Adaptation for Action Recognition Around the Clock
Clean Text and Full-Body Transformer: Microsoft's Submission to the WMT22 Shared Task on Sign Language Translation
GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction
Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation
Holistic Interaction Transformer Network for Action Detection
Baby Physical Safety Monitoring in Smart Home Using Action Recognition System
3D Human Pose Estimation in Multi-View Operating Room Videos Using Differentiable Camera Projections
Text Editing as Imitation Game
Transformer-based Action recognition in hand-object interacting scenarios
Rethinking Learning Approaches for Long-Term Action Anticipation
Performance of different machine learning methods on activity recognition and pose estimation datasets
A Symbolic Representation of Human Posture for Interpretable Learning and Reasoning
Towards Effective Image Manipulation Detection with Proposal Contrastive Learning
STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition
Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification
MMTSA: Multimodal Temporal Segment Attention Network for Efficient Human Activity Recognition
Real-time Action Recognition for Fine-Grained Actions and The Hand Wash Dataset
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition
Text-Derived Knowledge Helps Vision: A Simple Cross-modal Distillation for Video-based Action Anticipation
Masked Motion Encoding for Self-Supervised Video Representation Learning
MotionBERT: A Unified Perspective on Learning Human Motion Representations
An Action Is Worth Multiple Words: Handling Ambiguity in Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.