tianruochen / MultimodalVideoTagLinks
多模态视频分类模型
☆23Updated 2 years ago
Alternatives and similar repositories for MultimodalVideoTag
Users that are interested in MultimodalVideoTag are comparing it to the libraries listed below
Sorting:
- Tiny Kinetics-400 for test☆94Updated last year
- 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…☆94Updated 3 years ago
- Papers, codes collection of video summarization / video highlight detection / video key frame selection☆36Updated 4 years ago
- Frames Extraction With OpenCV and Python☆15Updated 5 years ago
- 中文CLIP:自定义数据集,可根据文图提取向量,实现文图匹配。☆22Updated 3 years ago
- 人脸识别、人脸细粒度表情识别、异常行为检测和识别☆11Updated 3 years ago
- 使用pytorch完成的一个多模态分类任务,文本和图像部分分别使用了bert和resnet提取特征(在config里可以组合多种模型),在我的小规模数据集上取得了良好的性能(验证集acc96%)☆80Updated 2 years ago
- Efficient dual attention SlowFast networks for video action recognition☆23Updated 3 years ago
- ☆59Updated 3 years ago
- [CVPR 2023 Workshop] The code reproduce the results of our solutions on both tracks for Meta AI Video Similarity Challenge (CVPR 2023 Wor…☆53Updated 2 years ago
- 视频分类标注、视频时空标注☆42Updated 2 years ago
- Implementation of ViViT: A Video Vision Transformer - Zipping Coding Challenge☆32Updated 4 years ago
- Violence detection using CNN+LSTM model☆11Updated 2 years ago
- 疲劳检测☆11Updated 3 years ago
- In the consideration that the college student behavior dataset is scarce, we set up a novel college students’ action dataset in the class…☆19Updated 3 years ago
- 利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码☆31Updated 4 years ago
- (TIP'2023) Concept-Aware Video Captioning: Describing Videos with Effective Prior Information☆30Updated 8 months ago
- Code for the paper: "Efficient Two-Stream Network for Violence Detection Using Separable Convolutional LSTM"☆61Updated last year
- 多模态融合情感分析☆131Updated 5 years ago
- 动作识别(Action Recognition)常见模型的Pytorch实现☆33Updated 4 years ago
- Action_Recognition_Surveillance, for huamn fall down action recognition, helmet、smoke、cell-phone detection.☆17Updated 2 years ago
- 目标检测算法主要包括:两类two-stage和one-stage 一类是two-stage,two-stage检测算法将检测问题划分为两个阶段,首先产生候选区域(region proposals),然后对候选区域分类(一般还需要对位置精修),这一类的典型代表是R-CNN…☆14Updated 4 years ago
- 基于ClipCap的看图说话Image Caption模型☆313Updated 3 years ago
- Sports_Game_tracker是基于飞桨深度学习框架的实时行人分析工具PP-Human进行功能扩展的球赛识别追踪工具,目前的功能有:足球球员追踪、足球控球检测、足球检测。☆56Updated 2 years ago
- You Only Watch One Frame for Online Spatio-Temporal Action Detection☆34Updated 2 years ago
- 通过手动标注数据集,训练老人摔倒的模型☆19Updated 2 years ago
- 多模态情感分析——基于BERT+ResNet的多种融合方法☆317Updated 2 years ago
- The top conferences on video retrieval libraries in recent years, synchronized with my blog.☆14Updated 3 years ago
- ☆86Updated 4 years ago
- pytorch☆65Updated 4 years ago