视觉大模型 / VLM - arXivDaily 专题

2104.06365 2021-04-14 cs.LG cs.CV 62%

Neuro-Symbolic VQA: A review from the perspective of AGI desiderata

Ian Berlot-Attwell

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

2104.03046 2021-04-08 cs.CV cs.LG 62%

Multimodal Continuous Visual Attention Mechanisms

António Farinhas, André F. T. Martins, Pedro M. Q. Aguiar

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

2104.02096 2021-04-07 cs.CV cs.AI 62%

Compressing Visual-linguistic Model via Knowledge Distillation

Zhiyuan Fang, Jianfeng Wang, Xiaowei Hu, Lijuan Wang, Yezhou Yang, Zicheng Liu

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

2104.01394 2021-04-06 cs.CV cs.CL cs.LG 62%

MMBERT: Multimodal BERT Pretraining for Improved Medical VQA

Yash Khare, Viraj Bagal, Minesh Mathew, Adithi Devi, U Deva Priyakumar, CV Jawahar

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

2103.11537 2021-03-23 cs.LG cs.CV 62%

How to Design Sample and Computationally Efficient VQA Models

Karan Samel, Zelin Zhao, Binghong Chen, Kuan Wang, Robin Luo, Le Song

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

Comments 20 pages, 5 figures

2103.05900 2021-03-11 cs.CV cs.AI 62%

RL-CSDia: Representation Learning of Computer Science Diagrams

Shaowei Wang, LingLing Zhang, Xuan Luo, Yi Yang, Xin Hu, Jun Liu

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

2102.06793 2021-02-16 cs.CV cs.AI cs.CL 62%

Unanswerable Questions about Images and Texts

Ernest Davis

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

Comments 15 pages, 4 figures

Journal ref Frontiers in Artificial Intelligence: Language and Computation. July 2020

2102.00424 2021-02-02 cs.CL cs.CV cs.LG 62%

An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games

Alessandro Suglia, Yonatan Bisk, Ioannis Konstas, Antonio Vergari, Emanuele Bastianelli, Andrea Vanzo, Oliver Lemon

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

Comments Accepted paper for the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2021)

2012.14891 2021-01-01 cs.CV cs.LG 62%

Detecting Hate Speech in Multi-modal Memes

Abhishek Das, Japsimar Singh Wahi, Siyao Li

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

2006.07214 2020-10-30 cs.LG cs.CL cs.CV stat.ML 62%

Sparse and Continuous Attention Mechanisms

André F. T. Martins, António Farinhas, Marcos Treviso, Vlad Niculae, Pedro M. Q. Aguiar, Mário A. T. Figueiredo

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

Comments Accepted for spotlight presentation at NeurIPS 2020

2010.10802 2020-10-22 cs.CV cs.LG 62%

Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies

Itai Gat, Idan Schwartz, Alexander Schwing, Tamir Hazan

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

Comments NeurIPS 2020

1911.10354 2020-10-13 cs.CV cs.CL cs.LG 62%

Unsupervised Keyword Extraction for Full-sentence VQA

Kohei Uehara, Tatsuya Harada

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

Comments EMNLP 2020 workshop: NLP Beyond Text (NLPBT)

2010.00562 2020-10-02 cs.CL cs.AI cs.CV 62%

ISAAQ -- Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention

Jose Manuel Gomez-Perez, Raul Ortega

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

Comments Accepted for publication as a long paper in EMNLP2020

1912.00124 2020-08-31 cs.CV cs.CL cs.HC cs.LG 62%

A Free Lunch in Generating Datasets: Building a VQG and VQA System with Attention and Humans in the Loop

Jihyeon Lee, Sho Arora

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

Comments 9 pages, 12 figures

2001.07194 2020-08-05 cs.CL cs.CV cs.IR cs.LG cs.MM 62%

Recommending Themes for Ad Creative Design via Visual-Linguistic Representations

Yichao Zhou, Shaunak Mishra, Manisha Verma, Narayan Bhamidipati, Wei Wang

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

Comments 7 pages, 8 figures, 2 tables, accepted by The Web Conference 2020

1909.11740 2020-07-21 cs.CV cs.CL cs.LG 62%

UNITER: UNiversal Image-TExt Representation Learning

Yen-Chun Chen, Linjie Li, Licheng Yu, Ahmed El Kholy, Faisal Ahmed, Zhe Gan, Yu Cheng, Jingjing Liu

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

Comments ECCV 2020

2007.05608 2020-07-14 cs.CV cs.CL cs.LG 62%

Image Captioning with Compositional Neural Module Networks

Junjiao Tian, Jean Oh

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

Comments International Joint Conference on Artificial Intelligence (IJCAI-19)

2004.13073 2020-07-14 cs.CV cs.CL cs.LG 62%

A Novel Attention-based Aggregation Function to Combine Vision and Language

Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

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

Comments ICPR 2020

1910.02509 2020-07-14 cs.LG cs.CV cs.NE 62%

REMIND Your Neural Network to Prevent Catastrophic Forgetting

Tyler L. Hayes, Kushal Kafle, Robik Shrestha, Manoj Acharya, Christopher Kanan

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

Comments To appear in the European Conference on Computer Vision (ECCV-2020)

2007.02833 2020-07-07 cs.CV cs.LG 62%

Eliminating Catastrophic Interference with Biased Competition

Amelia Elizabeth Pollard, Jonathan L. Shapiro

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

2007.00900 2020-07-03 cs.CV cs.AI cs.HC 62%

The Impact of Explanations on AI Competency Prediction in VQA

Kamran Alipour, Arijit Ray, Xiao Lin, Jurgen P. Schulze, Yi Yao, Giedrius T. Burachas

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

Comments Submitted to HCCAI 2020

2006.16917 2020-07-01 cs.AI cs.LG 62%

Ontology-guided Semantic Composition for Zero-Shot Learning

Jiaoyan Chen, Freddy Lecue, Yuxia Geng, Jeff Z. Pan, Huajun Chen

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

Comments Accepted by KR 2020 - 17th International Conference on Principles of Knowledge Representation and Reasoning

1912.07538 2020-06-01 cs.CV cs.CL cs.LG 62%

Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing

Vedika Agarwal, Rakshith Shetty, Mario Fritz

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

Comments 16 pages

2005.09241 2020-05-20 cs.CV cs.LG 62%

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

Damien Teney, Kushal Kafle, Robik Shrestha, Ehsan Abbasnejad, Christopher Kanan, Anton van den Hengel

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

2004.09034 2020-04-21 cs.CV cs.LG 62%

Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision

Damien Teney, Ehsan Abbasnedjad, Anton van den Hengel

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

1908.08530 2020-02-19 cs.CV cs.CL cs.LG 62%

VL-BERT: Pre-training of Generic Visual-Linguistic Representations

Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai

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

Comments Accepted by ICLR 2020

2001.03712 2020-01-14 cs.CV cs.CL cs.LG 62%

MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding

Geondo Park, Chihye Han, Wonjun Yoon, Daeshik Kim

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

Comments Accepted by the 2020 IEEE Winter Conference on Applications of Computer Vision (WACV 20), 9 pages, 5 figures

1910.04964 2020-01-07 cs.MM cs.CV cs.IR cs.LG 62%

Multi-modal Deep Analysis for Multimedia

Wenwu Zhu, Xin Wang, Hongzhi Li

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

Comments 25 pages, 39 figures, IEEE Transactions on Circuits and Systems for Video Technology

1912.03063 2019-12-09 cs.CV cs.CL cs.LG cs.NE 62%

Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks

Corentin Kervadec, Grigory Antipov, Moez Baccouche, Christian Wolf

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

1911.08618 2019-11-21 cs.CV cs.LG cs.MM eess.IV 62%

Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA

Badri N. Patro, Anupriy, Vinay P. Namboodiri

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

Comments AAAI-2020(Accepted)

1. 视觉问答 3129 篇

Neuro-Symbolic VQA: A review from the perspective of AGI desiderata

Multimodal Continuous Visual Attention Mechanisms

Compressing Visual-linguistic Model via Knowledge Distillation

MMBERT: Multimodal BERT Pretraining for Improved Medical VQA

How to Design Sample and Computationally Efficient VQA Models

RL-CSDia: Representation Learning of Computer Science Diagrams

Unanswerable Questions about Images and Texts

An Empirical Study on the Generalization Power of Neural Representations Learned via Visual Guessing Games

Detecting Hate Speech in Multi-modal Memes

Sparse and Continuous Attention Mechanisms

Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies

Unsupervised Keyword Extraction for Full-sentence VQA

ISAAQ -- Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention

A Free Lunch in Generating Datasets: Building a VQG and VQA System with Attention and Humans in the Loop

Recommending Themes for Ad Creative Design via Visual-Linguistic Representations

UNITER: UNiversal Image-TExt Representation Learning

Image Captioning with Compositional Neural Module Networks

A Novel Attention-based Aggregation Function to Combine Vision and Language

REMIND Your Neural Network to Prevent Catastrophic Forgetting

Eliminating Catastrophic Interference with Biased Competition

The Impact of Explanations on AI Competency Prediction in VQA

Ontology-guided Semantic Composition for Zero-Shot Learning

Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing

On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law

Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision

VL-BERT: Pre-training of Generic Visual-Linguistic Representations

MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding

Multi-modal Deep Analysis for Multimedia

Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks

Explanation vs Attention: A Two-Player Game to Obtain Attention for VQA