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.
Leveraging Next-Active Objects for Context-Aware Anticipation in Egocentric Videos
Action Class Relation Detection and Classification Across Multiple Video Datasets
Ske2Grid: Skeleton-to-Grid Representation Learning for Action Recognition
Masked Motion Predictors are Strong 3D Action Representation Learners
On the Importance of Spatial Relations for Few-shot Action Recognition
EasyEdit: An Easy-to-use Knowledge Editing Framework for Large Language Models
Semantics2Hands: Transferring Hand Motion Semantics between Avatars
Versatile Face Animator: Driving Arbitrary 3D Facial Avatar in RGBD Space
TrainFors: A Large Benchmark Training Dataset for Image Manipulation Detection and Localization
Ensemble Modeling for Multimodal Visual Action Recognition
Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient
Temporally-Adaptive Models for Efficient Video Understanding
Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning
JEDI: Joint Expert Distillation in a Semi-Supervised Multi-Dataset Student-Teacher Scenario for Video Action Recognition
ViLP: Knowledge Exploration using Vision, Language, and Pose Embeddings for Video Action Recognition
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
M$^3$Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognition
MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition
TS-RGBD Dataset: a Novel Dataset for Theatre Scenes Description for People with Visual Impairments
SkateboardAI: The Coolest Video Action Recognition for Skateboarding
MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment
Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration
Event-based Vision for Early Prediction of Manipulation Actions
Human-centric Scene Understanding for 3D Large-scale Scenarios
EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge: Mixed Sequences Prediction
Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion
Multiscale Video Pretraining for Long-Term Activity Forecasting
Evaluating the Ripple Effects of Knowledge Editing in Language Models
Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition
AI on the Road: A Comprehensive Analysis of Traffic Accidents and Accident Detection System in Smart Cities
An X3D Neural Network Analysis for Runner's Performance Assessment in a Wild Sporting Environment
Actor-agnostic Multi-label Action Recognition with Multi-modal Query
Language-based Action Concept Spaces Improve Video Self-Supervised Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.