Papers with Code 아카이브
Action Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 28
- 보존된 평가 기록
- 444
Image source: The Kinetics Human Action Video Dataset
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
MARLIN: Masked Autoencoder for facial video Representation LearnINg
Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks
Egocentric Audio-Visual Noise Suppression
Adversarial Domain Adaptation for Action Recognition Around the Clock
Turbo Training with Token Dropout
Application-Driven AI Paradigm for Human Action Recognition
RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical Flow
Global Semantic Descriptors for Zero-Shot Action Recognition
Self-supervised Learning for Unintentional Action Prediction
OmniVL:One Foundation Model for Image-Language and Video-Language Tasks
Shifting Perspective to See Difference: A Novel Multi-View Method for Skeleton based Action Recognition
ViA: View-invariant Skeleton Action Representation Learning via Motion Retargeting
Actor-identified Spatiotemporal Action Detection --- Detecting Who Is Doing What in Videos
Temporal Action Localization with Multi-temporal Scales
Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition
Frozen CLIP Models are Efficient Video Learners
Expanding Language-Image Pretrained Models for General Video Recognition
Class-Difficulty Based Methods for Long-Tailed Visual Recognition
Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition
MAR: Masked Autoencoders for Efficient Action Recognition
Is an Object-Centric Video Representation Beneficial for Transfer?
ReAct: Temporal Action Detection with Relational Queries
Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning
SLIC: Self-Supervised Learning with Iterative Clustering for Human Action Videos
Context-aware Proposal Network for Temporal Action Detection
Stand-Alone Inter-Frame Attention in Video Models
MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing
Spatial-temporal Concept based Explanation of 3D ConvNets
A Simple and Efficient Pipeline to Build an End-to-End Spatial-Temporal Action Detector
Do we really need temporal convolutions in action segmentation?
MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
Handcrafted localized phase features for human action recognition
CoCa: Contrastive Captioners are Image-Text Foundation Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.