Researcher — paper.dinq.me

2026 顶会论文

作者位次 #7/9ECCV 2026Poster

Maximum Spanning Tree Guided Confidence and Sparse Graph for Robust Noisy Label Learning

Gengfeng Chen · Xu Liu · Boyi Peng · Liangqiu Xiao · Weicheng Xie · Siyang Song · Zitong Yu · Laizhong Cui · Linlin Shen

Open-World Recognition, Segmentation & TransferOpenReview

作者位次 #3/10ECCV 2026Poster

Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing

Yingjie Ma · Xun Lin · Zitong Yu · Haonan Wang · Ruixin Zhang · Shouhong Ding · Xin Liu · Xiaochen Yuan · Weicheng Xie · Linlin Shen

多模态理论与学习动力学Open-World Recognition, Segmentation & TransferOpenReview

作者位次 #9/9ECCV 2026Poster

RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning

Yelin Wang · Zijia Song · Shuo Ye · Chuanguang Yang · Miaoyu Wang · Yong Xu · Zhulin An · Yongjun Xu · Zitong Yu

多模态Vision-Language Models & Foundation ModelsOpenReview

作者位次 #5/6ECCV 2026Poster

FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography

Wei Qian · Dan Guo · Jinxing Zhou · Bochao Zou · Zitong Yu · Meng Wang

推理多模态社会与人本Computational Imaging, Medical & Scientific VisionOpenReview

作者位次 #3/7ECCV 2026Poster

DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning

JIAJIAN HUANG · Dongliang Zhu · Zitong Yu · Hui Ma · Jiayu Zhang · Chunmei Zhu · Xiaochun Cao

多模态数据与预训练社会与人本Open-World Recognition, Segmentation & TransferOpenReview

作者位次 #3/8ECCV 2026Poster

MoMCE: Mixture of Modality and Cue Experts for Multimodal Deception Detection

Dongliang Zhu · Ruimin Hu · Zitong Yu · Xiaobao Guo · Mei Wang · Shuo Ye · Fei Ma · Xiaochun Cao

多模态Open-World Recognition, Segmentation & TransferOpenReview

作者位次 #4/6ECCV 2026Poster

VC-VAE: Leveraging Video Codecs for Training-Efficient and High-Fidelity Video VAE

Xinxu Ge · Shang Chai · Litong Gong · Zitong Yu · Xin Liu · Tiezheng Ge

多模态效率与系统Video Understanding, Generation and Multimodal LearningOpenReview

作者位次 #6/6ACL 2026Poster· Natural Language Processing

Retrieving to Recover: Towards Incomplete Audio-Visual Question Answering via Semantic-consistent Purification

Jiayu Zhang · Shuo Ye · Qilang Ye · Zihan Song · JIAJIAN HUANG · Zitong Yu

摘要

Recent Audio-Visual Question Answering (AVQA) methods have advanced significantly. However, most AVQA methods lack effective mechanisms for handling missing modalities, suffering from severe performance degradation in real-world scenarios with data interruptions. Furthermore, prevailing methods f...

检索与知识多模态推理OpenReview 项目页

Zitong Yu

获取完整研究档案

联系方式