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.
Language-free Compositional Action Generation via Decoupling Refinement
Fine-grained Action Analysis: A Multi-modality and Multi-task Dataset of Figure Skating
A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition
Self-supervised Optimization of Hand Pose Estimation using Anatomical Features and Iterative Learning
VideoGLUE: Video General Understanding Evaluation of Foundation Models
Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognition
Make A Long Image Short: Adaptive Token Length for Vision Transformers
Technical Report for Ego4D Long Term Action Anticipation Challenge 2023
Exploring Transformers for On-Line Handwritten Signature Verification
Physics-based Motion Retargeting from Sparse Inputs
Augmenting Deep Learning Adaptation for Wearable Sensor Data through Combined Temporal-Frequency Image Encoding
Don't freeze: Finetune encoders for better Self-Supervised HAR
SpATr: MoCap 3D Human Action Recognition based on Spiral Auto-encoder and Transformer Network
Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning
Streaming egocentric action anticipation: An evaluation scheme and approach
M3Act: Learning from Synthetic Human Group Activities
Post-train Black-box Defense via Bayesian Boundary Correction
milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing
Modified Parametric Multichannel Wiener Filter \\for Low-latency Enhancement of Speech Mixtures with Unknown Number of Speakers
GeXSe (Generative Explanatory Sensor System): An Interpretable Deep Generative Model for Human Activity Recognition in Smart Spaces
MyDigitalFootprint: an extensive context dataset for pervasive computing applications at the edge
Theater Aid System for the Visually Impaired Through Transfer Learning of Spatio-Temporal Graph Convolution Networks
Palm: Predicting Actions through Language Models @ Ego4D Long-Term Action Anticipation Challenge 2023
Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition
Differentially Private Video Activity Recognition
A Novel Two Stream Decision Level Fusion of Vision and Inertial Sensors Data for Automatic Multimodal Human Activity Recognition System
Action Anticipation with Goal Consistency
Attention-Refined Unrolling for Sparse Sequential micro-Doppler Reconstruction
Learning Scene Flow With Skeleton Guidance For 3D Action Recognition
Human Activity Behavioural Pattern Recognition in Smarthome with Long-hour Data Collection
Combining Public Human Activity Recognition Datasets to Mitigate Labeled Data Scarcity
Spiking Two-Stream Methods with Unsupervised STDP-based Learning for Action Recognition
RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection
"Filling the Blanks'': Identifying Micro-activities that Compose Complex Human Activities of Daily Living
Dynamic Perceiver for Efficient Visual Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.