Researcher — paper.dinq.me

2026 顶会论文

作者位次 #3/3NeurIPS 2026Poster

MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion

Gong Meiqi · Hao Zhang · Jiayi Ma

多模态检索与知识OpenReview

作者位次 #6/6NeurIPS 2026Poster

G2Fusion: Geometric-to-Generative Image Fusion via Registration-Restoration Evolution

Hao Zhang · Douyu Wu · Han Xu · Linfeng Tang · Qiwen Jin · Jiayi Ma

多模态OpenReview

作者位次 #6/6NeurIPS 2026Poster

V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion

Jiajun Chen · Han Xu · Yunfei Huang · Zhuoya Zhang · Guangcan Liu · Jiayi Ma

多模态OpenReview

作者位次 #6/6NeurIPS 2026Poster

PIU-CR: Physics-Informed Deep Unfolding Network with SAR-Optical Image Fusion for Cloud Removal

Gengque Fan · Han Xu · Junxi Li · Hao Zhang · Guangcan Liu · Jiayi Ma

多模态OpenReview

作者位次 #3/4NeurIPS 2026Poster

MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image Fusion

Han Xu · Yunfei Deng · Jiayi Ma · Guangcan Liu

多模态OpenReview

作者位次 #5/5CVPR 2026Poster· Computer Vision & Pattern Recognition

ReCoFuse: Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal Coupling

Hao Zhang · Shuhan Yang · Linfeng Tang · Xunpeng Yi · Jiayi Ma

多模态OpenReview 项目页

作者位次 #10/10CVPR 2026Poster· Computer Vision & Pattern Recognition

VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion

Linfeng Tang · Yeda Wang · Meiqi Gong · Zizhuo Li · Yuxin Deng · Xunpeng Yi · Chunyu Li · Han Xu · Hao Zhang · Jiayi Ma

多模态OpenReview 项目页

作者位次 #5/5CVPR 2026Poster· Computer Vision & Pattern Recognition

SAG-GNN: Semantic-Aware Guided GNN for Descriptor-Free 2D-3D Matching

Shihua Zhang · Tianhao Xu · Zizhuo Li · Qing Ma · Jiayi Ma

多模态OpenReview 项目页

作者位次 #5/5CVPR 2026Poster· Computer Vision & Pattern Recognition

MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement

Hao Zhang · Yanping Zha · Zizhuo Li · Meiqi Gong · Jiayi Ma

多模态强化学习与后训练OpenReview 项目页

作者位次 #5/5AAAI 2026Poster· Artificial Intelligence

SGPFeat: Semantic and Geometric Priors for Multi-modal Image Matching

Yuxin Deng · Botian Wang · Kaining Zhang · Hao Zhang · Jiayi Ma

多模态OpenReview

作者位次 #2/2AAAI 2026Poster· Artificial Intelligence

GeoMoE: Divide-and-Conquer Motion Field Modeling with Mixture-of-Experts for Two-View Geometry

Jiajun Le · Jiayi Ma

效率与系统OpenReview

作者位次 #5/5AAAI 2026Poster· Artificial Intelligence

Probabilistic Deformation Consistency for Unsupervised Shape Matching

Yifan Xia · Tianwei Ye · Jun Huang · Xiaoguang Mei · Jiayi Ma

OpenReview

作者位次 #7/7AAAI 2026Poster· Artificial Intelligence

Diff-NAT: Better Naturalistic and Aggressive Adversarial Attacks via Class-Optimized Diffusion for Object Detection

Qinglong Yan · Tong Zou · Xunpeng Yi · Xinyu Xiang · Xuying Wu · Hao Zhang · Jiayi Ma

安全OpenReview

作者位次 #5/5AAAI 2026Poster· Artificial Intelligence

Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions

Hao Zhang · Yanping Zha · Qingwei Zhuang · Zhenfeng Shao · Jiayi Ma

多模态OpenReview

Jiayi Ma

获取完整研究档案

联系方式

2026 顶会论文

MemoryFusion: Cross-Temporal Memory Learning for Multimodal Video Fusion

G2Fusion: Geometric-to-Generative Image Fusion via Registration-Restoration Evolution

V2VFusion: Text-Controlled Video-to-Video Diffusion for Degradation-Aware Video Fusion

PIU-CR: Physics-Informed Deep Unfolding Network with SAR-Optical Image Fusion for Cloud Removal

MODULE: A Mutual-Promoting Deep Unfolding Framework Towards Degradation-Robust Multi-modal Image Fusion

ReCoFuse: Ultra-Robust Image Fusion via Restorative Multi-Modal Diffusion Reciprocal Coupling

VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion

SAG-GNN: Semantic-Aware Guided GNN for Descriptor-Free 2D-3D Matching

MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement

SGPFeat: Semantic and Geometric Priors for Multi-modal Image Matching

GeoMoE: Divide-and-Conquer Motion Field Modeling with Mixture-of-Experts for Two-View Geometry

Probabilistic Deformation Consistency for Unsupervised Shape Matching

Diff-NAT: Better Naturalistic and Aggressive Adversarial Attacks via Class-Optimized Diffusion for Object Detection

Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions

常见合作者