Papers with Code 아카이브

Action Detection

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 8
평가표: 11
보존된 평가 기록: 81

Action Detection aims to find both where and when an action occurs within a video clip and classify what the action is taking place. Typically results are given in the form of action tublets, which are action bounding boxes linked across time in the video. This is related to temporal localization, which seeks to identify the start and end frame of an action, and action recognition, which seeks only to classify which action is taking place and typically assumes a trimmed video.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/kaai520/PGFA

공식 코드

Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment

https://github.com/kaist-dmlab/monaq

공식 코드

MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices

https://github.com/kalpitthakkar/pb-gcn

공식 코드

Part-based Graph Convolutional Network for Action Recognition

https://github.com/kathpra/lshr_lsht

공식 코드

Local Spherical Harmonics Improve Skeleton-Based Hand Action Recognition

https://github.com/kennymckormick/pyskl

공식 코드

PYSKL: Towards Good Practices for Skeleton Action Recognition

https://github.com/kenziyuliu/ms-g3d

공식 코드

Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition

https://github.com/kikihub/consense

공식 코드

ConSense: Continually Sensing Human Activity with WiFi via Growing and Picking

https://github.com/kkahatapitiya/Coarse-Fine-Networks

공식 코드

Coarse-Fine Networks for Temporal Activity Detection in Videos

https://github.com/kkahatapitiya/SSDet

공식 코드

Weakly-guided Self-supervised Pretraining for Temporal Activity Detection

https://github.com/knmac/LCDC_release

공식 코드

Learning Motion in Feature Space: Locally-Consistent Deformable Convolution Networks for Fine-Grained Action Detection

https://github.com/kpeng9510/musclemap

공식 코드

Towards Activated Muscle Group Estimation in the Wild

https://github.com/kpeng9510/os-sar

공식 코드

Navigating Open Set Scenarios for Skeleton-based Action Recognition

https://github.com/kpeng9510/proformer

공식 코드

Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions

https://github.com/kpeng9510/trans4soar

공식 코드

Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions

https://github.com/kpeng9510/transdarc

공식 코드

TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration

https://github.com/kuangenzhang/edh

공식 코드

Ensemble diverse hypotheses and knowledge distillation for unsupervised cross-subject adaptation

https://github.com/kylemin/SPELL

공식 코드

Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection

https://github.com/kyutai-labs/moshi

공식 코드

Moshi: a speech-text foundation model for real-time dialogue

https://github.com/lab-emi/airhar

공식 코드

RadMamba: Efficient Human Activity Recognition through Radar-based Micro-Doppler-Oriented Mamba State-Space Model

https://github.com/lalasray/txp

공식 코드

TxP: Reciprocal Generation of Ground Pressure Dynamics and Activity Descriptions for Improving Human Activity Recognition

https://github.com/leiwangr/video-ar

공식 코드

Taylor Videos for Action Recognition

https://github.com/levigty/acl

공식 코드

Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition

https://github.com/levigty/aimclr

공식 코드

Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition

https://github.com/limaosen0/AS-GCN

공식 코드

Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition

https://github.com/liujf69/MMCL-Action

공식 코드

Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition

https://github.com/liujf69/icmew2024-track10

공식 코드

HDBN: A Novel Hybrid Dual-branch Network for Robust Skeleton-based Action Recognition

https://github.com/lizaowo/hpi-gcn

공식 코드

High-Performance Inference Graph Convolutional Networks for Skeleton-Based Action Recognition

https://github.com/lizhi1104/haan

공식 코드

Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions

https://github.com/lou1sm/online_hard_clustering

공식 코드

Hard Regularization to Prevent Deep Online Clustering Collapse without Data Augmentation

https://github.com/lshiwjx/2s-AGCN

공식 코드

Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks

https://github.com/lshiwjx/DSTA-Net

공식 코드

Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition

https://github.com/lukashedegaard/continual-skeletons

공식 코드

Continual Spatio-Temporal Graph Convolutional Networks

https://github.com/lukashedegaard/continual-transformers

공식 코드

Continual Transformers: Redundancy-Free Attention for Online Inference

https://github.com/luyg45/hardnoboxattack

공식 코드

Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient

https://github.com/maclong01/STEP-CATFormer

공식 코드

STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition

https://github.com/makecent/apn

공식 코드

Progression-Guided Temporal Action Detection in Videos

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.