视觉大模型 / VLM - arXivDaily 专题

2104.00926 2021-07-21 cs.CV cs.HC 57%

VisQA: X-raying Vision and Language Reasoning in Transformers

Theo Jaunet, Corentin Kervadec, Romain Vuillemot, Grigory Antipov, Moez Baccouche, Christian Wolf

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

2002.05556 2021-07-09 cs.CL cs.CV 57%

Sparse and Structured Visual Attention

Pedro Henrique Martins, Vlad Niculae, Zita Marinho, André Martins

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

2106.09141 2021-06-18 cs.CL cs.CV 57%

Probing Image-Language Transformers for Verb Understanding

Lisa Anne Hendricks, Aida Nematzadeh

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

2106.05251 2021-06-10 cs.LG cs.CL stat.ML 57%

Bayesian Attention Belief Networks

Shujian Zhang, Xinjie Fan, Bo Chen, Mingyuan Zhou

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

Comments ICML 2021

2105.07141 2021-05-18 cs.CV 57%

Show Why the Answer is Correct! Towards Explainable AI using Compositional Temporal Attention

Nihar Bendre, Kevin Desai, Peyman Najafirad

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

Comments 7 pages, 4 figures, 3 tables

2105.01993 2021-05-06 cs.CV 57%

AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss

Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Feng Ji, Ji Zhang, Alberto Del Bimbo

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

2010.06087 2021-04-20 cs.CV 57%

Contrast and Classify: Training Robust VQA Models

Yash Kant, Abhinav Moudgil, Dhruv Batra, Devi Parikh, Harsh Agrawal

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

2104.08108 2021-04-19 cs.CV cs.CL 57%

Cross-Modal Retrieval Augmentation for Multi-Modal Classification

Shir Gur, Natalia Neverova, Chris Stauffer, Ser-Nam Lim, Douwe Kiela, Austin Reiter

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

2104.03762 2021-04-09 cs.CV cs.CL 57%

Video Question Answering with Phrases via Semantic Roles

Arka Sadhu, Kan Chen, Ram Nevatia

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

Comments NAACL21 Camera Ready including appendix

2104.03656 2021-04-09 cs.CV 57%

How Transferable are Reasoning Patterns in VQA?

Corentin Kervadec, Theo Jaunet, Grigory Antipov, Moez Baccouche, Romain Vuillemot, Christian Wolf

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

2006.05726 2021-04-09 cs.CV cs.CL 57%

Estimating semantic structure for the VQA answer space

Corentin Kervadec, Grigory Antipov, Moez Baccouche, Christian Wolf

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

Comments [WARNING] We want to notice the reader that additional experiments (not in the paper) have shown that using a `random' semantic space performs as much as the proposed semantic loss. This additional result question the effectiveness of our method

2006.05121 2021-04-08 cs.CV 57%

Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?

Corentin Kervadec, Grigory Antipov, Moez Baccouche, Christian Wolf

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

2104.00332 2021-04-02 cs.CV 57%

UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

Mingyang Zhou, Luowei Zhou, Shuohang Wang, Yu Cheng, Linjie Li, Zhou Yu, Jingjing Liu

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

2103.15974 2021-03-31 cs.CV 57%

Domain-robust VQA with diverse datasets and methods but no target labels

Mingda Zhang, Tristan Maidment, Ahmad Diab, Adriana Kovashka, Rebecca Hwa

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

Comments To appear in CVPR 2021

2102.08981 2021-03-31 cs.CV cs.CL 57%

Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

Soravit Changpinyo, Piyush Sharma, Nan Ding, Radu Soricut

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

Comments IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2021). Our dataset is available at https://github.com/google-research-datasets/conceptual-12m

2103.04181 2021-03-09 cs.LG 57%

Contextual Dropout: An Efficient Sample-Dependent Dropout Module

Xinjie Fan, Shujian Zhang, Korawat Tanwisuth, Xiaoning Qian, Mingyuan Zhou

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

Journal ref ICLR 2021

2101.06573 2021-01-19 cs.AI 57%

Understanding in Artificial Intelligence

Stefan Maetschke, David Martinez Iraola, Pieter Barnard, Elaheh ShafieiBavani, Peter Zhong, Ying Xu, Antonio Jimeno Yepes

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

Comments 28 pages, 282 references

2012.05153 2020-12-10 cs.CV 57%

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps

Qi Zhu, Chenyu Gao, Peng Wang, Qi Wu

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

2012.02951 2020-12-08 cs.CV 57%

FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding

Maryam Rahnemoonfar, Tashnim Chowdhury, Argho Sarkar, Debvrat Varshney, Masoud Yari, Robin Murphy

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

Comments 11 pages

2004.04963 2020-12-02 cs.CV 57%

Rephrasing visual questions by specifying the entropy of the answer distribution

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

Comments 10 pages

2009.14759 2020-11-30 cs.AI 57%

Graph-based Heuristic Search for Module Selection Procedure in Neural Module Network

Yuxuan Wu, Hideki Nakayama

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

Comments in Neural Module Network[C]//Proceedings of the Asian Conference on Computer Vision. 2020

2011.11721 2020-11-25 cs.CV 57%

Siamese Tracking with Lingual Object Constraints

Maximilian Filtenborg, Efstratios Gavves, Deepak Gupta

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

2002.11894 2020-11-24 cs.CV 57%

Unshuffling Data for Improved Generalization

Damien Teney, Ehsan Abbasnejad, Anton van den Hengel

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

2011.04264 2020-11-10 cs.CL cs.CV 57%

CapWAP: Captioning with a Purpose

Adam Fisch, Kenton Lee, Ming-Wei Chang, Jonathan H. Clark, Regina Barzilay

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

Comments EMNLP 2020

2010.13128 2020-10-27 cs.AI cs.CL cs.IR 57%

ExplanationLP: Abductive Reasoning for Explainable Science Question Answering

Mokanarangan Thayaparan, Marco Valentino, André Freitas

专题命中视觉问答：grounding(abstract)；分类 cs.AI

2010.11701 2020-10-23 cs.CV cs.CL 57%

Spatial Attention as an Interface for Image Captioning Models

Philipp Sadler

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

Comments A thesis submitted in fulfillment of the requirements for the degree Master of Science in Cognitive Systems

2010.10604 2020-10-22 stat.ML cs.LG cs.NE 57%

Bayesian Attention Modules

Xinjie Fan, Shujian Zhang, Bo Chen, Mingyuan Zhou

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

2010.08189 2020-10-19 cs.CV 57%

New Ideas and Trends in Deep Multimodal Content Understanding: A Review

Wei Chen, Weiping Wang, Li Liu, Michael S. Lew

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

Comments Accepted by Neurocomputing

2010.06572 2020-10-14 cs.CL cs.CV 57%

Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think!

Jack Hessel, Lillian Lee

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

Journal ref Published in EMNLP 2020

2004.14451 2020-10-07 cs.CL cs.CV 57%

Pragmatic Issue-Sensitive Image Captioning

Allen Nie, Reuben Cohn-Gordon, Christopher Potts

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

Comments 15 pages, 7 figures. EMNLP 2020 Findings Accepted

1. 视觉问答 3153 篇

VisQA: X-raying Vision and Language Reasoning in Transformers

Sparse and Structured Visual Attention

Probing Image-Language Transformers for Verb Understanding

Bayesian Attention Belief Networks

Show Why the Answer is Correct! Towards Explainable AI using Compositional Temporal Attention

AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss

Contrast and Classify: Training Robust VQA Models

Cross-Modal Retrieval Augmentation for Multi-Modal Classification

Video Question Answering with Phrases via Semantic Roles

How Transferable are Reasoning Patterns in VQA?

Estimating semantic structure for the VQA answer space

Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To?

UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

Domain-robust VQA with diverse datasets and methods but no target labels

Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

Contextual Dropout: An Efficient Sample-Dependent Dropout Module

Understanding in Artificial Intelligence

Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps

FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding

Rephrasing visual questions by specifying the entropy of the answer distribution

Graph-based Heuristic Search for Module Selection Procedure in Neural Module Network

Siamese Tracking with Lingual Object Constraints

Unshuffling Data for Improved Generalization

CapWAP: Captioning with a Purpose

ExplanationLP: Abductive Reasoning for Explainable Science Question Answering

Spatial Attention as an Interface for Image Captioning Models

Bayesian Attention Modules

New Ideas and Trends in Deep Multimodal Content Understanding: A Review

Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think!

Pragmatic Issue-Sensitive Image Captioning