MIR第5期专题"Multimodal Learning, Temporal Modeling, and Foundation Models for Video Understanding"已于10月正式出版，9篇特约好文，欢迎阅读！

专题客座编委：

刘云, 南开大学, 中国

孙国磊, 南开大学, 中国

Radu Timofte, University of Würzburg, Germany

Ender Konukoglu, ETH Zürich, Switzerland

Luc Van Gool, Sofia University “St. Kliment Ohridski”, Bulgaria

专题 · Editorial

Editorial for Special Issue on Multimodal Learning, Temporal Modeling, and Foundation Models for Video Understanding

Yun Liu, Guolei Sun, Radu Timofte, Ender Konukoglu & Luc Van Gool

https://link.springer.com/article/10.1007/s11633-026-1696-z

https://www.mi-research.net/article/doi/10.1007/s11633-026-1696-z

专题 · 综述

Video Understanding: From Geometry and Semantics to Unified Models

Zhaochong An, Zirui Li, Mingqiao Ye, Feng Qiao, Jiaang Li, Zongwei Wu, Vishal Thengane, Chengzu Li, Lei Li, Luc Van Gool, Guolei Sun & Serge Belongie

https://link.springer.com/article/10.1007/s11633-026-1656-7

https://www.mi-research.net/article/doi/10.1007/s11633-026-1656-7 

专题 · 研究论文

Self-supervised Video Depth Adaptation for Efficient Sparse-view NeRF

Jiatong Xia, Libo Sun, Ian Reid & Jia-Wang Bian

https://link.springer.com/article/10.1007/s11633-025-1592-y

https://www.mi-research.net/article/doi/10.1007/s11633-025-1592-y

专题 · 研究论文

GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-aware Paradigm

Yu-Huan Wu, Wei Liu, Zi-Xuan Zhu, Zizhou Wang, Yong Liu & Liangli Zhen

https://link.springer.com/article/10.1007/s11633-025-1593-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1593-x

专题 · 研究论文

Evaluating SAM2 for Video Semantic Segmentation

Syed Ariff Syed Hesham, Yun Liu, Guolei Sun, Jing Yang, Henghui Ding, Xue Geng & Xudong Jiang

https://link.springer.com/article/10.1007/s11633-026-1638-9

https://www.mi-research.net/article/doi/10.1007/s11633-026-1638-9

专题 · 研究论文

Training-free Dense Video Captioning with Large-scale Pretrained Models

Yue Feng, Ziyi Yan, Yizhen Jia, Ethan Q. Chen & Jie Qin

https://link.springer.com/article/10.1007/s11633-025-1585-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1585-x

专题 · 研究论文

Multimodal Skeleton-based Action Representation Learning via Decomposition and Composition

Hongsong Wang, Heng Fei, Bingxuan Dai & Jie Gui

https://link.springer.com/article/10.1007/s11633-025-1583-z

https://www.mi-research.net/article/doi/10.1007/s11633-025-1583-z

专题 · 研究论文

Object-centric Video Prediction with Mask-guided Spatiotemporal Diffusion

Chenchen Han, Jiayi Fan, Na Wu, Jinpeng Dai, Hanbin Bao & Xiankai Lu

https://link.springer.com/article/10.1007/s11633-025-1584-y

https://www.mi-research.net/article/doi/10.1007/s11633-025-1584-y

专题 · 研究论文

SAMDistill: SAM-based Spatial-temporal Distillation for Robust 3D Object Detection

Zhaozhong Wang, Dian Shao, Lei Zhang, Zuowei Zhang & Binglu Wang

https://link.springer.com/article/10.1007/s11633-025-1586-9

https://www.mi-research.net/article/doi/10.1007/s11633-025-1586-9

专题 · 研究论文

DynaMix-VLT: Dynamic Multi-head Attention and Semantic-guided Modal Mixing for Robust Vision-language Tracking

Huanlong Zhang, Linjie Zhou, Liao Zhu, Fengli Shen, Jingjing Wu & Jianwei Zhang

https://link.springer.com/article/10.1007/s11633-025-1605-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1605-x

第5期Regular Papers

综述

Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning

Qi Peng, Jiatong Li, Sirui Huang, Yiyang Jiang, Kaisong Gong, Ronger Ding, Shijie Ye, Changmeng Zheng, Yi Cai, Xiaobo Yang, Jin Huang, Xiao-Yong Wei & Qing Li

https://link.springer.com/article/10.1007/s11633-026-1659-4

https://www.mi-research.net/article/doi/10.1007/s11633-026-1659-4

研究论文

M2SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation

Xiaoqi Zhao, Hongpeng Jia, Youwei Pang, Long Lv, Feng Tian, Lihe Zhang, Weibing Sun & Huchuan Lu

https://link.springer.com/article/10.1007/s11633-026-1662-9

https://www.mi-research.net/article/doi/10.1007/s11633-026-1662-9

研究论文

Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

Haokun Lin, Haobo Xu, Yichen Wu, Ziyu Guo, Renrui Zhang, Zhichao Lu, Ying Wei, Qingfu Zhang & Zhenan Sun

https://link.springer.com/article/10.1007/s11633-025-1624-x

https://www.mi-research.net/article/doi/10.1007/s11633-025-1624-x

研究论文

Surviving Resource-constraint Compression: Capability Retention under Tensor-train Decomposition for Sub-billion Parameter Language Models

Mingxue Xu, Yao Lei Xu & Danilo P. Mandic

https://link.springer.com/article/10.1007/s11633-026-1653-x

https://www.mi-research.net/article/doi/10.1007/s11633-026-1653-x

研究论文

OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box Prompts

Zhen Zhou, Junfeng Fan, Yunkai Ma, Sihan Zhao, Fengshui Jing, Shuo Wang & Min Tan

https://link.springer.com/article/10.1007/s11633-025-1590-0

https://www.mi-research.net/article/doi/10.1007/s11633-025-1590-0

研究论文

A Reinforcement Learning-driven Transformer GAN for Molecular Generation

Chen Li, Huidong Tang, Ye Zhu & Yoshihiro Yamanishi

https://link.springer.com/article/10.1007/s11633-025-1589-6

https://www.mi-research.net/article/doi/10.1007/s11633-025-1589-6

研究论文

StyleVideo: One-shot Image-guided Video Style Transfer

Xinyang Song, Xi Yong, Qi Li, Jianxin Sun, Yunfan Liu & Zhenan Sun

https://link.springer.com/article/10.1007/s11633-025-1609-6

https://www.mi-research.net/article/doi/10.1007/s11633-025-1609-6

Machine Intelligence Research

MIR为所有读者提供免费寄送纸刊服务，如您对本篇文章感兴趣，请点击下方链接填写收件地址，编辑部将尽快为您免费寄送纸版全文！

说明：如遇特殊原因无法寄达的，将推迟邮寄时间，咨询电话010-82544737

收件信息登记：

https://lcn76mgd97vz.feishu.cn/share/base/form/shrcnsQ6cmRjqoxPF5WDowSBFVr

支持单位：