-
-
-
LaGoVAD-PreVAD Public
[ICLR 26] This repository contains the code and dataset for our paper: Language-guided Open-world Video Anomaly Detection under Weak Supervision (https://arxiv.org/abs/2503.13160)
-
stagehand-python Public
Forked from browserbase/stagehand-pythonThe AI Browser Automation Framework
Python UpdatedNov 3, 2025 -
RethinkingVAD Public
This repository contains the codes and datasets for the ArXiv paper: Rethinking Metrics and Benchmarks of Video Anomaly Detection (https://arxiv.org/abs/2505.19022)
-
Adaptive-BLIP2-MM24 Public
This is official implementation of our MM'24 paper: Adaptively Building a Video-Language Model For Video Captioning and Retrieval without Massive Video Pretraining
-
-
PEL4VAD Public
Forked from yujiangpu20/PEL4VADOfficial code for "Learning Prompt-Enhanced Context features for Weakly-Supervised Video Anomlay Detection"
Jupyter Notebook MIT License UpdatedJul 5, 2023 -
cifar-pytorch-learning Public
Forked from blindwang/cifar-pytorch-learningLeNet5、AlexNet、VGG、GoogleNet、ResNet不同网络结构的尝试
Python UpdatedMay 7, 2023 -
LAVIS-MMVCT Public
Forked from salesforce/LAVISLAVIS - A One-stop Library for Language-Vision Intelligence
Python BSD 3-Clause "New" or "Revised" License UpdatedFeb 25, 2023 -
video_features Public
Forked from v-iashin/video_featuresExtract video features from raw videos using multiple GPUs. We support RAFT and PWC flow frames as well as I3D, R(2+1)D, VGGish, ResNet, CLIP features.
-
watermark-tracer Public
一个基于可视水印检测识别的数字媒体溯源应用系统,是我的大作业项目,包含这个系统以及一个开源的大规模常见水印图像数据集(Large-scale Common Watermark Dataset, LCWD)。 输入一个带有可视水印的图片或视频,系统会检测定位到水印所在的区域,然后将其提取出来,然后借助百度AI开放平台的OCR和logo识别以及Bing搜索引擎,溯源到这个图片或视频的源头。
-
vatex-downloader Public
A simple vatex dataset downloader. 一个简单的VATEX数据集(或其他YouTube视频数据集)的下载器,特别为国内网络环境优化(其实就是断点下载和加上代理的参数)。
-
pycocoevalcap Public
Forked from salaniz/pycocoevalcapPython 3 support for the MS COCO caption evaluation tools
Python Other UpdatedJul 22, 2022 -
mmselfsup Public
Forked from open-mmlab/mmselfsupOpenMMLab Self-Supervised Learning Toolbox and Benchmark
Python Apache License 2.0 UpdatedJun 22, 2022 -
wx-challenge Public
Forked from WeChat-Big-Data-Challenge-2022/challenge微信大赛baseline
Python UpdatedMay 25, 2022 -
-
learn_cryptography Public
The Python3 implementation of MD5, SHA1 algorithms. Used for learning cryptography.
Python UpdatedApr 21, 2022 -
Video-Captioning-Transformer Public
这是一个基于Pytorch平台、Transformer框架实现的视频描述生成 (Video Captioning) 深度学习模型。 视频描述生成任务指的是:输入一个视频,输出一句描述整个视频内容的文字(前提是视频较短且可以用一句话来描述)。本repo主要目的是帮助视力障碍者欣赏网络视频、感知周围环境,促进“无障碍视频”的发展。
-
-
torchvggish Public
Forked from harritaylor/torchvggishPytorch port of Google Research's VGGish model used for extracting audio features.
Python Apache License 2.0 UpdatedNov 3, 2021 -
S2VT-video-caption Public
An implementation of paper "Sequence to Sequence – Video to Text". This implementation uses the S2VT model to do video captioning(or video description) task.
-
torch_videovision Public
Forked from hassony2/torch_videovisionTransforms for video datasets in pytorch
Python GNU General Public License v3.0 UpdatedJun 7, 2021 -
mmt Public
Forked from gabeur/mmtMulti-Modal Transformer for Video Retrieval
Python Apache License 2.0 UpdatedMay 10, 2021 -
CBIR Public
Forked from pochih/CBIR🏞 A content-based image retrieval (CBIR) system
Python UpdatedMay 10, 2021 -
-
pytorch-book Public
Forked from chenyuntc/pytorch-bookPyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch:入门与实战》)
Jupyter Notebook MIT License UpdatedDec 22, 2020 -
CreationEngine Public
Forked from BuleStorm/CreationEngineC++ OpenGL 模仿我的世界,内容相对完善,随机地图,支持双人联机,代码注释多
C++ GNU General Public License v3.0 UpdatedOct 20, 2020 -
-
a-PyTorch-Tutorial-to-Image-Captioning Public
Forked from sgrvinod/a-PyTorch-Tutorial-to-Image-CaptioningShow, Attend, and Tell | a PyTorch Tutorial to Image Captioning
Python MIT License UpdatedAug 3, 2020