面向遥感的语义分割
multimodal-fusion 开源项目推荐(143 个)
multimodal-fusion 话题在 GitHub 上没有填写简介,这里按 Star 数汇总最相关的热门仓库。
热门项目 前 20
按 Star 数排序展示前 20 个 · GitHub 共 143 个仓库SuperYOLO is accepted by TGRS
机器人视觉 SDK
Multimodal Co-Attention Transformer for Survival Prediction in Gigapixel Whole Slide Images - ICCV 2021
Source code for "Bi-modal Transformer for Dense Video Captioning" (BMVC 2020)
This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.
[NeurIPS 2025] PhysioWave 与 PhysioWave-T:面向 EEG、ECG 和 sEMG 的令牌高效小波基础模型,具备可靠性感知的多模态融合。
MIntRec: A New Dataset for Multimodal Intent Recognition (ACM MM 2022)
E2E-MFD-OOD
[AAAI-2026] Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning
基于多模态输入选择动作的代码。此处的输入为语音和文本。
Multimodal object tracking and scene analytics for highly actionable, real-world contextualized data
Creating multimodal multitask models
Multimodal sentiment analysis using hierarchical fusion with context modeling
[CVAMD 2021] "End-to-End Learning of Fused Image and Non-Image Feature for Improved Breast Cancer Classification from MRI"
Few-Shot malware classification using fused features of static analysis and dynamic analysis (基于静态+动态分析的混合特征的小样本恶意代码分类框架)
[TPAMI 2026 | NeurIPS 2025 Spotlight] Official implementation of "InfMasking, a unified framework for supervised and unsupervised synergistic multimodal learning."
[2025] ModalFormer: Multimodal Transformer for Low-Light Image Enhancement
Official implementation of "Multi-scale Bottleneck Transformer for Weakly Supervised Multimodal Violence Detection"
Multimodal sentiment analysis
关于这个话题
- 清单取自 GitHub 话题页并按 Star 数排序,每次展示前 20 个项目;原始页面见 https://github.com/topics/multimodal-fusion。
- 该话题在 GitHub 上共有 143 个仓库, 本站收录的是其中最热门的 20 个,不是全量列表。
- Star / Fork 每日自动刷新一次,实时数据以 GitHub 为准。
- 当前 20 个项目累计 3353 Star,覆盖 2 种主要语言,数据更新于 2026-11-07。
- 中文介绍来自 GitHub 官方话题说明(github/explore)的机器翻译,可点「查看原文」对照;译文缺失时会先展示原文。