视觉大模型 / VLM

Multi-Image Visual Question Answering

Harsh Raj, Janhavi Dadhania, Akhilesh Bhardwaj, Prabuchandran KJ

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?

Sedigheh Eslami, Gerard de Melo, Christoph Meinel

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Single-Modal Entropy based Active Learning for Visual Question Answering

Dong-Jin Kim, Jae Won Cho, Jinsoo Choi, Yunjae Jung, In So Kweon

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Accepted to BMVC 2021

Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering

Siddharth Karamcheti, Ranjay Krishna, Li Fei-Fei, Christopher D. Manning

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Accepted at ACL-IJCNLP 2021. 17 pages, 16 Figures

Inverse Visual Question Answering with Multi-Level Attentions

Yaser Alwattar, Yuhong Guo

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

LRTA: A Transparent Neural-Symbolic Reasoning Framework with Modular Supervision for Visual Question Answering

Weixin Liang, Feiyang Niu, Aishwarya Reganti, Govind Thattai, Gokhan Tur

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments NeurIPS KR2ML 2020

Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering

Zihao Zhu, Jing Yu, Yujing Wang, Yajing Sun, Yue Hu, Qi Wu

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Augmenting Visual Question Answering with Semantic Frame Information in a Multitask Learning Approach

Mehrdad Alizadeh, Barbara Di Eugenio

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 14th IEEE International Conference on SEMANTIC COMPUTING, 8 Pages, February 2020, San Diego CA USA

Robust Explanations for Visual Question Answering

Badri N. Patro, Shivansh Pate, Vinay P. Namboodiri

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments WACV-2020 (Accepted)

Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering

Ramakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach, Dhruv Batra, Devi Parikh

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments ICML 2019 Camera Ready + Appendix

The meaning of "most" for visual question answering models

Alexander Kuhnle, Ann Copestake

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

MUREL: Multimodal Relational Reasoning for Visual Question Answering

Remi Cadene, Hedi Ben-younes, Matthieu Cord, Nicolas Thome

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments CVPR2019 accepted paper

Learning Visual Question Answering by Bootstrapping Hard Attention

Mateusz Malinowski, Carl Doersch, Adam Santoro, Peter Battaglia

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments ECCV 2018

R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering

Pan Lu, Lei Ji, Wei Zhang, Nan Duan, Ming Zhou, Jianyong Wang

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 10 pages, 5 figures, accepted as an oral paper in SIGKDD 2018

Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets

Wei-Lun Chao, Hexiang Hu, Fei Sha

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments Accepted for Oral Presentation at NAACL-HLT 2018

High-Order Attention Models for Visual Question Answering

Idan Schwartz, Alexander G. Schwing, Tamir Hazan

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 9 pages, 8 figures, NIPS 2017

Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering

Yash Goyal, Tejas Khot, Douglas Summers-Stay, Dhruv Batra, Devi Parikh

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

C-VQA: A Compositional Split of the Visual Question Answering (VQA) v1.0 Dataset

Aishwarya Agrawal, Aniruddha Kembhavi, Dhruv Batra, Devi Parikh

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Analyzing the Behavior of Visual Question Answering Models

Aishwarya Agrawal, Dhruv Batra, Devi Parikh

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments 13 pages, 20 figures; To appear in EMNLP 2016

Towards Transparent AI Systems: Interpreting Visual Question Answering Models

Yash Goyal, Akrit Mohapatra, Devi Parikh, Dhruv Batra

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Measuring Machine Intelligence Through Visual Question Answering

C. Lawrence Zitnick, Aishwarya Agrawal, Stanislaw Antol, Margaret Mitchell, Dhruv Batra, Devi Parikh

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI、cs.LG

Comments AI Magazine, 2016

Enhancing Visual Question Answering through Ranking-Based Hybrid Training and Multimodal Fusion

Peiyuan Chen, Zecheng Zhang, Yiping Dong, Li Zhou, Han Wang

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.LG

Comments Visual Question Answering, Rank VQA, Faster R-CNN, BERT, Multimodal Fusion, Ranking Learning, Hybrid Training Strategy

Learning Sparse Mixture of Experts for Visual Question Answering

Vardaan Pahuja, Jie Fu, Christopher J. Pal

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.LG

Comments Accepted in Visual Question Answering and Dialog Workshop, CVPR 2019

Attention on Attention: Architectures for Visual Question Answering (VQA)

Jasdeep Singh, Vincent Ying, Alex Nutkiewicz

专题命中 视觉问答 ：visual question answering(title,abstract)；分类 cs.CV、cs.AI

Comments Visual Question Answering Project

Ground, Cover, and Refine: Evidence-Centric Frame Selection for Long-Video Question Answering

锚定、覆盖与优化：面向长视频问答的以证据为中心的帧选择框架

Fan Wei, Siru Zhong, Runmin Dong, Miao Yang, Zhaoyang Luo, Haohuan Fu

专题命中 视觉问答 ：VLM(abstract,abstract_cn)；LLaVA(abstract,abstract_cn)；分类 cs.CV

AI总结 本文针对长视频问答中视觉预算有限及证据对齐弱的问题，提出无需训练的GCR框架，通过锚定、覆盖、优化三步选择帧，在LongVideoBench等基准上较基线取得显著性能提升。

XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs

XSPA：构建不可察觉的X形稀疏对抗扰动以对视觉语言模型的可迁移攻击

Chengyin Hu, Jiaju Han, Xuemeng Sun, Qike Zhang, Luwei Yang, Lehan Sun, Jiahuan Long, Yiwei Wei, Jiujiang Guo

专题命中 视觉问答 ：VLM(abstract,abstract_cn)；vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV

AI总结 本文提出XSPA攻击，通过限制扰动为两条相交对角线，测试VLMs在稀疏扰动下的鲁棒性，实验表明其能显著破坏跨任务语义。

LoMeVQA: A Comprehensive Benchmark for Longitudinal Medical VQA

LoMeVQA：纵向医学视觉问答综合基准

Zhilin Wu, Zhangkai Ni, Chengmei Yang, Longzhen Yang, Yihang Liu, Ying Wen, Lianghua He

机构 * Tongji University（同济大学） ； East China Normal University（华东师范大学） 纠错

专题命中 视觉问答 ：visual reasoning(abstract)；visual question answering(abstract)；grounding(abstract)；multimodal large language model(abstract)

AI总结 该研究提出纵向医学视觉问答基准LoMeVQA，发现现有多模态大语言模型在该任务上时间推理能力不足，推出MedLong-8B实现最优性能，并开展相关分析。

Comments 23 pages, 17 figures, 7 tables. Code and data: https://github.com/pepperbubble/LoMeVQA

How Do VLMs Fail? Vision-Operation Misalignment in Compositional VQA

视觉语言模型如何失败？组合式视觉问答中的视觉-操作不对齐

Navya Gupta, Bingjie Xu, Avinash Anand, Timothy Liu, Zhengchen Zhang

机构 * Singapore Institute of Technology（新加坡科技学院） ； NVIDIA（英伟达） 纠错

专题命中 视觉问答 ：vision-language model(abstract)；VLM(abstract)；visual question answering(abstract)；grounding(abstract)

AI总结 研究组合式视觉问答中视觉语言模型失败的机制，引入以操作为中心的框架分解失败模式，揭示四种失败模式及传播路径，表明不同失败类型需不同纠正策略，为提升模型可靠性提供基础。

Comments Accepted at ACM Multimedia 2026

SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity

SSMNBench: 通过单视图充分性与多视图必要性诊断基于图像的跨视角人-物理解

Tianchen Guo, Chen Liu, Ling Chen, Xin Yu

机构 * The University of Queensland（昆士兰大学） ； Australian Institute for Machine Learning, Adelaide University（阿德莱德大学澳大利亚机器学习研究所） ； University of Technology Sydney（悉尼科技大学） ； Follow Me AI Pty LTD（Follow Me AI有限公司） 纠错

专题命中 视觉问答 ：MLLM(summary_cn,abstract_cn)；multimodal large language model(abstract)；分类 cs.CV

AI总结 提出SSMNBench基准，通过单视图充分性(SVS)和多视图必要性(MVN)任务分类，诊断MLLM在跨视角人-物理解中的视觉干扰退化和跨视角融合失败问题。

Comments European Conference on Computer Vision (ECCV). 32 pages, 10 figures. The code is available at: $ \href{https://github.com/gtc-gh/SSMNBench}{\text{SSMNBench}} $

Ill-Posed by Design: Probing Evidence Use in VLMs

刻意设计的不适定问题：探究VLMs中的证据使用

Boaz Meivar, Shaked Perek, Shani Shvartzman, Eli Schwartz, Shai Avidan

机构 * Tel Aviv University（特拉维夫大学） ； IBM Research（IBM研究院） 纠错

专题命中 视觉问答 ：VLM(summary_cn,abstract_cn)；vision-language model(abstract)；分类 cs.CV

AI总结 提出单目物体尺寸估计作为不适定诊断任务，通过反事实分析分解六种视觉和语言证据通道，评估12个开源VLM，发现最大模型仍落后于纯文本LLM，且模型未有效利用场景几何信息。