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.
Multidimensional Human Activity Recognition With Large Language Model: A Conceptual Framework
Integrating Audio Narrations to Strengthen Domain Generalization in Multimodal First-Person Action Recognition
A Comprehensive Methodological Survey of Human Activity Recognition Across Divers Data Modalities
ChildPlay-Hand: A Dataset of Hand Manipulations in the Wild
KAN-HyperpointNet for Point Cloud Sequence-Based 3D Human Action Recognition
Using The Concept Hierarchy for Household Action Recognition
Language-centered Human Activity Recognition
Benchmarking 2D Egocentric Hand Pose Datasets
2D bidirectional gated recurrent unit convolutional Neural networks for end-to-end violence detection In videos
A Wearable Multi-Modal Edge-Computing System for Real-Time Kitchen Activity Recognition
Data Collection-free Masked Video Modeling
Real-Time Human Action Recognition on Embedded Platforms
ReL-SAR: Representation Learning for Skeleton Action Recognition with Convolutional Transformers and BYOL
CKnowEdit: A New Chinese Knowledge Editing Dataset for Linguistics, Facts, and Logic Error Correction in LLMs
OneEdit: A Neural-Symbolic Collaboratively Knowledge Editing System
Property Neurons in Self-Supervised Speech Transformers
ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching
Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment
Few-Shot Continual Learning for Activity Recognition in Classroom Surveillance Images
Unfolding Videos Dynamics via Taylor Expansion
Unified Framework with Consistency across Modalities for Human Activity Recognition
TASAR: Transfer-based Attack on Skeletal Action Recognition
SITAR: Semi-supervised Image Transformer for Action Recognition
ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognition
Decoding finger velocity from cortical spike trains with recurrent spiking neural networks
Action-Based ADHD Diagnosis in Video
ADHD diagnosis based on action characteristics recorded in videos using machine learning
TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model
Affordance-based Robot Manipulation with Flow Matching
FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition
Does Knowledge Localization Hold True? Surprising Differences Between Entity and Relation Perspectives in Language Models
A Critical Analysis on Machine Learning Techniques for Video-based Human Activity Recognition of Surveillance Systems: A Review
Fisher Information guided Purification against Backdoor Attacks
Robotic Vision and Multi-View Synergy: Action and activity recognition in assisted living scenarios
Text-Enhanced Zero-Shot Action Recognition: A training-free approach
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.