Papers with Code 아카이브

Temporal Action Localization

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

하위 태스크: 8
평가표: 14
보존된 평가 기록: 125

Temporal Action Localization aims to detect activities in the video stream and output beginning and end timestamps. It is closely related to Temporal Action Proposal Generation.

코드

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

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

공식 코드

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

https://github.com/lsy0882/RDFA-S6

공식 코드

Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism

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

공식 코드

Continual Spatio-Temporal Graph Convolutional Networks

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/m-hasan-n/roundabout

공식 코드

Maneuver-based Anchor Trajectory Hypotheses at Roundabouts

https://github.com/machelreid/editpro

공식 코드

Learning to Model Editing Processes

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/madrylab/modelcomponents

공식 코드

Decomposing and Editing Predictions by Modeling Model Computation

https://github.com/magnux/MotionGAN

공식 코드

Human Motion Prediction via Spatio-Temporal Inpainting

https://github.com/mail-research/cad-attribution4diffusion

공식 코드

Unveiling Concept Attribution in Diffusion Models

https://github.com/maoyunyao/cmd

공식 코드

CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation

https://github.com/maoyunyao/mamp

공식 코드

Masked Motion Predictors are Strong 3D Action Representation Learners

https://github.com/map-learning/tl2la

공식 코드

Semantic Map Learning of Traffic Light to Lane Assignment based on Motion Data

https://github.com/mariusbock/context_har

공식 코드

DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition

https://github.com/mariusbock/tal_for_har

공식 코드

Temporal Action Localization for Inertial-based Human Activity Recognition

https://github.com/mariusbock/wear

공식 코드

WEAR: An Outdoor Sports Dataset for Wearable and Egocentric Activity Recognition

https://github.com/martinxm/gap

공식 코드

Generative Action Description Prompts for Skeleton-based Action Recognition

https://github.com/martinxm/lst

공식 코드

Generative Action Description Prompts for Skeleton-based Action Recognition

https://github.com/mcg-nju/basictad

공식 코드

BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection

https://github.com/mcg-nju/mgsampler

공식 코드

MGSampler: An Explainable Sampling Strategy for Video Action Recognition

https://github.com/mcg-nju/pointtad

공식 코드

PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points

https://github.com/mcgill-nlp/logicalknowedit

공식 코드

Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness

https://github.com/mdeff/cnn_graph

공식 코드

Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering

https://github.com/mduhme/fusion-gcn

공식 코드

Fusion-GCN: Multimodal Action Recognition using Graph Convolutional Networks

https://github.com/meaten/motionaug

공식 코드

MotionAug: Augmentation with Physical Correction for Human Motion Prediction

https://github.com/mediabrain-sjtu/auxformer

공식 코드

Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction

https://github.com/mediabrain-sjtu/eqmotion

공식 코드

EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning

https://github.com/mediabrain-sjtu/jrtransformer

공식 코드

Joint-Relation Transformer for Multi-Person Motion Prediction

https://github.com/mediabrain-sjtu/spgsn

공식 코드

Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction

https://github.com/mengyuanchen21/cvpr2022-ftcl

공식 코드

Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization

https://github.com/metrics-lab/st-fmri

공식 코드

Improving Phenotype Prediction using Long-Range Spatio-Temporal Dynamics of Functional Connectivity

https://github.com/mgiant/2p-gcn

공식 코드

Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition

https://github.com/mhnasseri/sort_oh

공식 코드

Simple online and real-time tracking with occlusion handling

https://github.com/michigan-traffic-lab/DECODE

공식 코드

DECODE: Domain-aware Continual Domain Expansion for Motion Prediction

https://github.com/michigannlp/vlog_action_localization

공식 코드

When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs

https://github.com/microsoft/SGN

공식 코드

Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition

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