视觉大模型 / VLM - arXivDaily 专题

2208.08104 2022-09-23 cs.CV cs.CL 57%

Understanding Attention for Vision-and-Language Tasks

Feiqi Cao, Soyeon Caren Han, Siqu Long, Changwei Xu, Josiah Poon

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments Accepted in COLING 2022

2105.11333 2022-09-22 cs.CV 57%

Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training

Jong Hak Moon, Hyungyung Lee, Woncheol Shin, Young-Hak Kim, Edward Choi

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments Accepted by IEEE Journal of Biomedical and Health Informatics

Journal ref IEEE Journal of Biomedical and Health Informatics 2022

2209.06730 2022-09-15 cs.CV 57%

MUST-VQA: MUltilingual Scene-text VQA

Emanuele Vivoli, Ali Furkan Biten, Andres Mafla, Dimosthenis Karatzas, Lluis Gomez

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments To be appeared in Text In Everything Workshop in ECCV 2022

2109.05014 2022-09-15 cs.CV 57%

An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA

Zhengyuan Yang, Zhe Gan, Jianfeng Wang, Xiaowei Hu, Yumao Lu, Zicheng Liu, Lijuan Wang

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments AAAI 2022 (Oral Presentation)

2209.04372 2022-09-12 cs.CV 57%

Pre-training image-language transformers for open-vocabulary tasks

AJ Piergiovanni, Weicheng Kuo, Anelia Angelova

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

2209.03609 2022-09-09 cs.CV cs.MM 57%

Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering

Jiong Wang, Zhou Zhao, Weike Jin

专题命中视觉问答：grounding(abstract)；分类 cs.CV

2004.05595 2022-09-05 cs.CV 57%

An Entropy Clustering Approach for Assessing Visual Question Difficulty

Kento Terao, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, Shun'ichi Satoh

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Journal ref IEEE Access, Vol.8, pp. 180633-180645, Sep 2020

2208.12037 2022-08-31 cs.CV 57%

Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

Stan Weixian Lei, Difei Gao, Jay Zhangjie Wu, Yuxuan Wang, Wei Liu, Mengmi Zhang, Mike Zheng Shou

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments 18 pages, 13 figures

2208.10760 2022-08-26 cs.CV 57%

How good are deep models in understanding the generated images?

Ali Borji

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

2205.04713 2022-08-05 cs.LG cs.DB cs.DC 57%

Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures

Yongji Wu, Matthew Lentz, Danyang Zhuo, Yao Lu

专题命中视觉问答：visual question answering(abstract)；分类 cs.LG

2207.11850 2022-07-26 cs.CV 57%

Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem

Yudong Han, Liqiang Nie, Jianhua Yin, Jianlong Wu, Yan Yan

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments 13 pages, 10 figures, submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence

2201.11732 2022-07-19 cs.CL cs.CV 57%

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages

Emanuele Bugliarello, Fangyu Liu, Jonas Pfeiffer, Siva Reddy, Desmond Elliott, Edoardo Maria Ponti, Ivan Vulić

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments ICML 2022

2206.14989 2022-07-01 cs.CV 57%

A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA

Yangyang Guo, Liqiang Nie, Yongkang Wong, Yibing Liu, Zhiyong Cheng, Mohan Kankanhalli

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

2110.09599 2022-06-20 cs.LG cs.CL 57%

Label-Descriptive Patterns and Their Application to Characterizing Classification Errors

Michael Hedderich, Jonas Fischer, Dietrich Klakow, Jilles Vreeken

专题命中视觉问答：visual question answering(abstract)；分类 cs.LG

Comments Accepted at ICML 2022

2206.01017 2022-06-03 cs.CV 57%

Structured Two-stream Attention Network for Video Question Answering

Lianli Gao, Pengpeng Zeng, Jingkuan Song, Yuan-Fang Li, Wu Liu, Tao Mei, Heng Tao Shen

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

2205.14895 2022-05-31 cs.CV cs.CL cs.MM 57%

From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering

Jiangtong Li, Li Niu, Liqing Zhang

专题命中视觉问答：grounding(abstract)；分类 cs.CV

Comments To appear in CVPR 2022

2203.05115 2022-05-24 cs.CL cs.LG 57%

Internet-augmented language models through few-shot prompting for open-domain question answering

Angeliki Lazaridou, Elena Gribovskaya, Wojciech Stokowiec, Nikolai Grigorev

专题命中视觉问答：grounding(abstract)；分类 cs.LG

2205.01883 2022-05-05 cs.CV cs.CL 57%

All You May Need for VQA are Image Captions

Soravit Changpinyo, Doron Kukliansky, Idan Szpektor, Xi Chen, Nan Ding, Radu Soricut

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments 2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2022)

2204.07302 2022-04-18 cs.CV cs.CL 57%

Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning

Feilong Chen, Xiuyi Chen, Shuang Xu, Bo Xu

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments ICASSP 2022

2203.14072 2022-04-06 cs.CV 57%

Learning to Answer Questions in Dynamic Audio-Visual Scenarios

Guangyao Li, Yake Wei, Yapeng Tian, Chenliang Xu, Ji-Rong Wen, Di Hu

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments Accepted by CVPR2022 (Oral presentation)

2202.10401 2022-03-29 cs.CV 57%

Vision-Language Pre-Training with Triple Contrastive Learning

Jinyu Yang, Jiali Duan, Son Tran, Yi Xu, Sampath Chanda, Liqun Chen, Belinda Zeng, Trishul Chilimbi, Junzhou Huang

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments CVPR 2022; code: https://github.com/uta-smile/TCL

2203.07190 2022-03-15 cs.CV cs.CL 57%

CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment

Haoyu Song, Li Dong, Wei-Nan Zhang, Ting Liu, Furu Wei

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments ACL 2022 main conference

2203.05081 2022-03-11 cs.CV cs.CL 57%

NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks

Fawaz Sammani, Tanmoy Mukherjee, Nikos Deligiannis

专题命中视觉问答：vision-language model(abstract)；分类 cs.CV

Comments Accepted to CVPR 2022

2202.06858 2022-02-15 cs.CV 57%

An experimental study of the vision-bottleneck in VQA

Pierre Marza, Corentin Kervadec, Grigory Antipov, Moez Baccouche, Christian Wolf

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

2202.04015 2022-02-09 cs.CV cs.MM 57%

NEWSKVQA: Knowledge-Aware News Video Question Answering

Pranay Gupta, Manish Gupta

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

2112.12494 2021-12-28 cs.CV 57%

LaTr: Layout-Aware Transformer for Scene-Text VQA

Ali Furkan Biten, Ron Litman, Yusheng Xie, Srikar Appalaraju, R. Manmatha

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

1912.03879 2021-12-23 cs.CL cs.CV 57%

AI2D-RST: A multimodal corpus of 1000 primary school science diagrams

Tuomo Hiippala, Malihe Alikhani, Jonas Haverinen, Timo Kalliokoski, Evanfiya Logacheva, Serafina Orekhova, Aino Tuomainen, Matthew Stone, John A. Bateman

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments 24 pages; revised version submitted to Language Resources & Evaluation

Journal ref Language Resources and Evaluation 55(3), 2021, pp. 661-688

2010.16010 2021-12-15 cs.CV 57%

Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View

Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Qi Tian, Min Zhang

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

2103.12248 2021-12-15 cs.CV cs.CL 57%

Multi-Modal Answer Validation for Knowledge-Based VQA

Jialin Wu, Jiasen Lu, Ashish Sabharwal, Roozbeh Mottaghi

专题命中视觉问答：visual question answering(abstract)；分类 cs.CV

Comments AAAI 2022

2112.02839 2021-12-07 cs.MM cs.AI 57%

MoCA: Incorporating Multi-stage Domain Pretraining and Cross-guided Multimodal Attention for Textbook Question Answering

Fangzhi Xu, Qika Lin, Jun Liu, Lingling Zhang, Tianzhe Zhao, Qi Chai, Yudai Pan

专题命中视觉问答：visual question answering(abstract)；分类 cs.AI

Comments 9 pages, 6 figures

1. 视觉问答 3129 篇

Understanding Attention for Vision-and-Language Tasks

Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training

MUST-VQA: MUltilingual Scene-text VQA

An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA

Pre-training image-language transformers for open-vocabulary tasks

Frame-Subtitle Self-Supervision for Multi-Modal Video Question Answering

An Entropy Clustering Approach for Assessing Visual Question Difficulty

Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task

How good are deep models in understanding the generated images?

Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures

Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem

IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages

A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA

Label-Descriptive Patterns and Their Application to Characterizing Classification Errors

Structured Two-stream Attention Network for Video Question Answering

From Representation to Reasoning: Towards both Evidence and Commonsense Reasoning for Video Question-Answering

Internet-augmented language models through few-shot prompting for open-domain question answering

All You May Need for VQA are Image Captions

Improving Cross-Modal Understanding in Visual Dialog via Contrastive Learning

Learning to Answer Questions in Dynamic Audio-Visual Scenarios

Vision-Language Pre-Training with Triple Contrastive Learning

CLIP Models are Few-shot Learners: Empirical Studies on VQA and Visual Entailment

NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks

An experimental study of the vision-bottleneck in VQA

NEWSKVQA: Knowledge-Aware News Video Question Answering

LaTr: Layout-Aware Transformer for Scene-Text VQA

AI2D-RST: A multimodal corpus of 1000 primary school science diagrams

Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance View

Multi-Modal Answer Validation for Knowledge-Based VQA

MoCA: Incorporating Multi-stage Domain Pretraining and Cross-guided Multimodal Attention for Textbook Question Answering