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/wywywang/coachai-projects

공식 코드

ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis

https://github.com/wzmsltw/BSN-boundary-sensitive-network.pytorch

공식 코드

BSN: Boundary Sensitive Network for Temporal Action Proposal Generation

https://github.com/xh20/HAGCN

공식 코드

Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network

https://github.com/xinghaochen/squeezetime

공식 코드

No Time to Waste: Squeeze Time into Channel for Mobile Video Understanding

https://github.com/xlliu7/E2E-TAD

공식 코드

An Empirical Study of End-to-End Temporal Action Detection

https://github.com/xlliu7/TadTR

공식 코드

End-to-end Temporal Action Detection with Transformer

https://github.com/xtotodilex/deep-learning-model-optimization

공식 코드

Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation

https://github.com/xumingze0308/TRN.pytorch

공식 코드

Temporal Recurrent Networks for Online Action Detection

https://github.com/xuyankun/stvig-for-reads-v

공식 코드

VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG

https://github.com/xuyankun/vsvig

공식 코드

VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG

https://github.com/xuyizdby/noiseerasar

공식 코드

Skeleton-Based Human Action Recognition with Noisy Labels

https://github.com/xyanchen/wifi-csi-sensing-benchmark

공식 코드

SenseFi: A Library and Benchmark on Deep-Learning-Empowered WiFi Human Sensing

https://github.com/yairl/ivrit.ai

공식 코드

ivrit.ai: A Comprehensive Dataset of Hebrew Speech for AI Research and Development

https://github.com/yangle15/DyFADet-pytorch

공식 코드

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection

https://github.com/ycwfs/fmi-tal

공식 코드

FMI-TAL: Few-shot Multiple Instances Temporal Action Localization by Probability Distribution Learning and Interval Cluster Refinement

https://github.com/yellowtownhz/STIGCN

공식 코드

Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition

https://github.com/yfsong0709/EfficientGCNv1

공식 코드

Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition

https://github.com/yfsong0709/RA-GCNv2

공식 코드

Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition

https://github.com/yijieyang23/skelet-gcn

공식 코드

Expressive Keypoints for Skeleton-based Action Recognition via Skeleton Transformation

https://github.com/yilliajing/action-ood

공식 코드

Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detection

https://github.com/yilliajing/skeleton-ood

공식 코드

Skeleton-OOD: An End-to-End Skeleton-Based Model for Robust Out-of-Distribution Human Action Detection

https://github.com/yingsen1/unimd

공식 코드

UniMD: Towards Unifying Moment Retrieval and Temporal Action Detection

https://github.com/yjh0410/YOWOv2

공식 코드

YOWOv2: A Stronger yet Efficient Multi-level Detection Framework for Real-time Spatio-temporal Action Detection

https://github.com/yjh0410/pytorch_yowo

공식 코드

YOWO-Plus: An Incremental Improvement

https://github.com/yjxiong/action-detection

공식 코드

A Pursuit of Temporal Accuracy in General Activity Detection

https://github.com/yujieouo/pstl

공식 코드

Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences

https://github.com/yujieouo/smie

공식 코드

Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization

https://github.com/yunfengdiao/Skeleton-Robustness-Benchmark

공식 코드

TASAR: Transfer-based Attack on Skeletal Action Recognition

https://github.com/yuxiaochen1103/DG-STA

공식 코드

Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention

https://github.com/yuxiaochen1103/Hi-TRS

공식 코드

Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

https://github.com/yysijie/st-gcn

공식 코드

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

https://github.com/zachstarkk/asm2tv

공식 코드

ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework for Human Activity Recognition

https://github.com/zahrag/gg3dhar

공식 코드

Hierarchical growing grid networks for skeleton based action recognition

https://github.com/zechenli03/sensorllm

공식 코드

SensorLLM: Human-Intuitive Alignment of Multivariate Sensor Data with LLMs for Activity Recognition

https://github.com/zhaoyue-zephyrus/testra

공식 코드

Real-time Online Video Detection with Temporal Smoothing Transformers

https://github.com/zhaxidele/har-with-snn

공식 코드

Evaluating Spiking Neural Network On Neuromorphic Platform For Human Activity Recognition

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