Action Recognition
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 15
- 평가표
- 56
- 보존된 평가 기록
- 650
Action Recognition is a computer vision task that involves recognizing human actions in videos or images. The goal is to classify and categorize the actions being performed in the video or image into a predefined set of action classes.
In the video domain, it is an open question whether training an action classification network on a sufficiently large dataset, will give a similar boost in performance when applied to a different temporal task or dataset. The challenges of building video datasets has meant that most popular benchmarks for action recognition are small, having on the order of 10k videos.
Please note some benchmarks may be located in the Action Classification or Video Classification tasks, e.g. Kinetics-400.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
Optimizing Human Pose Estimation Through Focused Human and Joint Regions
MV-GMN: State Space Model for Multi-View Action Recognition
Can masking background and object reduce static bias for zero-shot action recognition?
SMART-Vision: Survey of Modern Action Recognition Techniques in Vision
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling
InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models
BlanketGen2-Fit3D: Synthetic Blanket Augmentation Towards Improving Real-World In-Bed Blanket Occluded Human Pose Estimation
HFGCN:Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition
Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
Computerized Assessment of Motor Imitation for Distinguishing Autism in Video (CAMI-2DNet)
Visual WetlandBirds Dataset: Bird Species Identification and Behavior Recognition in Videos
IoT-Based Real-Time Medical-Related Human Activity Recognition Using Skeletons and Multi-Stage Deep Learning for Healthcare
Collaborative Learning for 3D Hand-Object Reconstruction and Compositional Action Recognition from Egocentric RGB Videos Using Superquadrics
Improving Skeleton-based Action Recognition with Interactive Object Information
Video Summarisation with Incident and Context Information using Generative AI
Large Language Models for Video Surveillance Applications
Evolving Skeletons: Motion Dynamics in Action Recognition
Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras
SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization
Multimodal Large Models Are Effective Action Anticipators
Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble
Frequency-aware Event Cloud Network
A Large-Scale Study on Video Action Dataset Condensation
FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments
Temporal Context Consistency Above All: Enhancing Long-Term Anticipation by Learning and Enforcing Temporal Constraints
Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion
HumanVBench: Exploring Human-Centric Video Understanding Capabilities of MLLMs with Synthetic Benchmark Data
Knowledge Editing through Chain-of-Thought
Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking
Video Domain Incremental Learning for Human Action Recognition in Home Environments
Joint Knowledge Editing for Information Enrichment and Probability Promotion
Data-Driven Fairness Generalization for Deepfake Detection
FACTS: Fine-Grained Action Classification for Tactical Sports
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.