tianruochen / MultimodalVideoTag
多模态视频分类模型
☆12Updated last year
Related projects: ⓘ
- 中文CLIP:自定义数据集,可根据文图提取向量,实现文图匹配。☆21Updated 2 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%)☆56Updated last year
- 多模态融合情感分析☆108Updated 4 years ago
- 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…☆78Updated 2 years ago
- This is the code for the Paper "Guilherme L. Toledo, Ricardo M. Marcacini: Transfer Learning with Joint Fine-Tuning for Multimodal Sentim…☆14Updated 2 years ago
- 本项目采用多模态特征融合和引入外部知识的方式来检测短视频谣言,创新性地引入了对比学习的方式实现了谣言的区分☆17Updated 11 months ago
- Frames Extraction With OpenCV and Python☆15Updated 4 years ago
- 计算机视觉课程设计-基于Chinese-CLIP的图文检索系统☆37Updated last year
- 500,000 multimodal short video data and baseline models. 50万条多模态短视频数据集和基线模型(TensorFlow2.0)。☆127Updated 5 years ago
- 人工智能实验五:多模态情感分类☆14Updated 2 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 2 years ago
- 多模态情感分析——基于BERT+ResNet的多种融合方法☆214Updated last year
- 商品图像检索、多模态、深度学习☆26Updated 2 years ago
- 多模态融合情感分析☆26Updated 3 years ago
- 该项目旨在通过输入文本描述来检索与之相匹配的图片。☆23Updated last year
- Papers, codes collection of video summarization / video highlight detection / video key frame selection☆34Updated 3 years ago
- 该仓库存放了多模态情感分析实验的配套代码。☆37Updated 2 years ago
- (TIP'2023) Concept-Aware Video Captioning: Describing Videos with Effective Prior Information☆20Updated last month
- UniSA: Unified Generative Framework for Sentiment Analysis☆44Updated 4 months ago
- A demo for multi-modal emotion recognition.(多模态情感识别demo)☆73Updated 5 months ago
- PyTorch implementation of HANet: Hierarchical Alignment Networks for Video-Text Retrieval (ACM MM 2021).☆46Updated 3 years ago
- 看图说话,基于keras,支持GPU。Image captioning code in keras, runs on GPU.☆23Updated 4 years ago
- Workshop on Foundation Model 1st foundation model challenge Track1 codebase (Open TransMind v1.0)☆18Updated last year
- The source code for the paper titled "Sentiment Knowledge Enhanced Attention Fusion Network (SKEAFN)".☆21Updated last year
- 一个近几年来各大视觉顶会关于视频文本检索的库,同步我的博客:https://blog.csdn.net/AAliuxiaolei/article/details/121433833☆14Updated 2 years ago
- ☆66Updated 2 years ago
- Multimodal Sentiment Analysis with Image-Text Interaction Network☆10Updated last year
- 补充了一些Visualglm缺少的文件,可以对Visualglm进行训练,实例中是对人脸做了面相的识别☆12Updated last year
- 动作识别(Action Recognition)常见模型的Pytorch实现☆25Updated 3 years ago
- Paper reading notes in the field of Image-Text Matching/Retrieval.☆14Updated 2 years ago