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.
MLP-AIR: An Efficient MLP-Based Method for Actor Interaction Relation Learning in Group Activity Recognition
GoferBot: A Visual Guided Human-Robot Collaborative Assembly System
Contactless Human Activity Recognition using Deep Learning with Flexible and Scalable Software Define Radio
Human activity recognition using deep learning approaches and single frame cnn and convolutional lstm
Applications of Deep Learning for Top-View Omnidirectional Imaging: A Survey
ATTACH Dataset: Annotated Two-Handed Assembly Actions for Human Action Understanding
Robust Cross-Modal Knowledge Distillation for Unconstrained Videos
PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition
Explaining, Analyzing, and Probing Representations of Self-Supervised Learning Models for Sensor-based Human Activity Recognition
NEV-NCD: Negative Learning, Entropy, and Variance regularization based novel action categories discovery
Peer-to-Peer Federated Continual Learning for Naturalistic Driving Action Recognition
Skeleton-based action analysis for ADHD diagnosis
Continuous Human Activity Recognition using a MIMO Radar for Transitional Motion Analysis
WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition
Attack-Augmentation Mixing-Contrastive Skeletal Representation Learning
Domain Adaptation for Inertial Measurement Unit-based Human Activity Recognition: A Survey
Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting
Therbligs in Action: Video Understanding through Motion Primitives
VicTR: Video-conditioned Text Representations for Activity Recognition
Off-Policy Action Anticipation in Multi-Agent Reinforcement Learning
A real-time algorithm for human action recognition in RGB and thermal video
Multi-Channel Time-Series Person and Soft-Biometric Identification
DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation
Focalized Contrastive View-invariant Learning for Self-supervised Skeleton-based Action Recognition
MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition
AutoLabel: CLIP-based framework for Open-set Video Domain Adaptation
On the Benefits of 3D Pose and Tracking for Human Action Recognition
DOAD: Decoupled One Stage Action Detection Network
HaLP: Hallucinating Latent Positives for Skeleton-based Self-Supervised Learning of Actions
WSense: A Robust Feature Learning Module for Lightweight Human Activity Recognition
STMT: A Spatial-Temporal Mesh Transformer for MoCap-Based Action Recognition
HARFLOW3D: A Latency-Oriented 3D-CNN Accelerator Toolflow for HAR on FPGA Devices
Streaming Video Model
Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation
Sensing with OFDM Waveform at mmWave Band based on Micro-Doppler Analysis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.