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.
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
Transformers in Action Recognition: A Review on Temporal Modeling
TempCLR: Temporal Alignment Representation with Contrastive Learning
Adaptive frame selection in two dimensional convolutional neural network action recognition
SMAM: Self and Mutual Adaptive Matching for Skeleton-Based Few-Shot Action Recognition
From Single-Visit to Multi-Visit Image-Based Models: Single-Visit Models are Enough to Predict Obstructive Hydronephrosis
Understanding Ethics, Privacy, and Regulations in Smart Video Surveillance for Public Safety
MoQuad: Motion-focused Quadruple Construction for Video Contrastive Learning
TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization
Deep set conditioned latent representations for action recognition
Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning
Video Segmentation Learning Using Cascade Residual Convolutional Neural Network
Full-Body Articulated Human-Object Interaction
A Survey on Human Action Recognition
2D Pose Estimation based Child Action Recognition
Inductive Attention for Video Action Anticipation
iCub! Do you recognize what I am doing?: multimodal human action recognition on multisensory-enabled iCub robot
Cross-Modal Learning with 3D Deformable Attention for Action Recognition
Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognition
Contextual Explainable Video Representation: Human Perception-based Understanding
FLAG3D: A 3D Fitness Activity Dataset with Language Instruction
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
Multimodal Prototype-Enhanced Network for Few-Shot Action Recognition
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning
Learning Video Representations from Large Language Models
Deep Architectures for Content Moderation and Movie Content Rating
Towards Holistic Surgical Scene Understanding
PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning
Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning
ResFormer: Scaling ViTs with Multi-Resolution Training
Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition
From Actions to Events: A Transfer Learning Approach Using Improved Deep Belief Networks
Towards Good Practices for Missing Modality Robust Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.