OpenTAD is an open-source temporal action detection (TAD) toolbox based on PyTorch.

[CVPR 2024] Adapting Short-Term Transformers for Action Detection in Untrimmed Videos

[ECCV 2024] Official PyTorch implementation of "Classification Matters: Improving Video Action Detection with Class-Specific Attention"

🔥🔥DatalinkX异构数据源之间的数据同步系统，支持海量数据的增量或全量同步，同时支持HTTP、Oracle、MySQL、ES等数据源之间的数据流转，支持中间transform算子如SQL算子、大模型算子，底层依赖Flink、Seatunnel引擎，提供流转任务管理、任务级联配置、任务日志采集等功能🔥🔥

[停止维护 请使用note286/xduts]西安电子科技大学研究生学位论文XeLaTeX模板

The repo host the code and model of MAViL.

[WACV 2025] Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

Listen to Look: Action Recognition by Previewing Audio (CVPR 2020)

Code for the 2021 paper "Audio-Based Fine-Grained Classroom Activity Detection with Neural Networks"

[Tiny VAD] SG-VAD: Stochastic Gates Based Speech Activity Detection

[NeurIPS 2022 Spotlight] VideoMAE for Action Detection

[ICASSP 2024] Official code for Slowfast Network for Continuous Sign Language Recognition

[NeurIPS 2023] Official implementation of the paper "CAST: Cross-Attention in Space and Time for Video Action Recognition"

Temporal Action Localization with Cross Layer Task Decoupling and Refinement

Official Implementation of our WACV2023 paper: “Holistic Interaction Transformer Network for Action Detection”

Improving Mamaba performance on Video Understanding task

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

[ECCV2024] Official implementation of Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes

Student Classroom Behavior dataset

[ICCV 2023] Efficient Video Action Detection with Token Dropout and Context Refinement

[CVPR 2021] Actor-Context-Actor Relation Network for Spatio-temporal Action Localization

Spatio-Temporal Action Localization System

Hiera: A fast, powerful, and simple hierarchical vision transformer.

Code repository for the paper "On the Benefits of 3D Pose and Tracking for Human Action Recognition", (CVPR 2023)

We have implemented Track # 1 for ICME 2024: Spatial Action Localization on Chaotic World dataset. Our mAP on the validation set reaches 26.62%, and if we directly use officially provided chaos_tes…

Context-based Dialogue Act Recognition using Recurrent Neural Networks

Switchboard Dialog Act Corpus with Penn Treebank links