BGN: Bilinear Graph Networks for Visual Question Answering (VQA Challenge Runner up)
Dalu Guo, Chang Xu, Dacheng Tao
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Visual-Linguistic Pre-training for Visual Question Answering (VQA Challenge Runner up)
Ming Yan, Chenliang Li, Wei Wang, Bin Bi, Zhongzhou Zhao, Songfang Huang
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Knowledge-Based Visual Question Answering in Videos
Noa Garcia, Mayu Otani, Chenhui Chu, Yuta Nakashima
[Video] [Slides]
Available for QA at Live QA-2

Which visual questions are difficult to answer? Analysis with Entropy of Answer Distributions
Kento Terao, Toru Tamaki, Bisser Raytchev, Kazufumi Kaneda, Shin'ichi Satoh
[Video] [Slides]
Available for QA at Live QA-2

Spatially Aware Multimodal Transformers for TextVQA
Yash Kant, Dhruv Batra, Peter Anderson, Alex Schwing, Devi Parikh, Jiasen Lu, Harsh Agrawal
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

TextCaps: a Dataset for Image Captioning with Reading Comprehension
Oleksii Sidorov, Ronghang Hu, Marcus Rohrbach, Amanpreet Singh
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Visual Question Answering with Prior Class Semantics
Violetta Shevchenko, Damien Teney, Anthony Dick, Anton van den Hengel
[Video] [Slides]
Available for QA at Live QA-2

Incorporating Background Knowledge Through Embedding-Space Constraints for Visual Question Answering
Damien Teney, Ehsan Abbasnejad, Anton van den Hengel
[Video] [Slides]
Available for QA at Live QA-2

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
[Video] [Slides]
Available for QA at Live QA-2

Zero-Shot Grounding of Objects from Natural Language Queries
Arka Sadhu, Kan Chen, Ram Nevatia
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Tricks for Training Visual dialogue Models
Guanlin Liang, Wenbin Li, Yang Liu, Sheng He, Ximin Zheng, You Wu, Xian Zhong
[Video] [Slides]
Available for QA at Live QA-2

Exploring Weaknesses of VQA Models through Attribution Driven Insights
Shaunak Halbe
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Neuro-Symbolic Visual Reasoning: Disentangling ‘Visual’ from ‘Reasoning’
Saeed Amizadeh, Oleksandr Polozov, Hamid Palangi, Yichen Huang, Kazuhito Koishida
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Automatic Reminiscence Therapy for Dementia
Mariona Carós, Xavier Giró-i-Nieto, Petia Radeva, Maite Garolera
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Weakly Supervised Categoric Visual Question Generation
Shagun Uppal*, Anish Madan*, Sarthak Bhagat*, Yi Yu, Rajiv Ratn Shah
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Ensemble MRR and NDCG models for Visual Dialog
Idan Schwartz, Alex Schwing, Tamir Hazan
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Controlling Length in Image Captioning
Ruotian Luo, Greg Shakhnarovich
[Video] [Slides]
Available for QA at Live QA-1 and Live QA-2

Visual Question Generation from Radiology Images based on Variational Autoencoders
Mourad Sarrouti, Asma Ben Abacha, Dina Demner-Fushman
[Video] [Slides]
Available for QA at Live QA-1

PathVQA: The First Step Towards an “AI Pathologist”
Xuehai He, Yichen Zhang, Luntian Moux, Eric P. Xing, Pengtao Xie
[Video] [Slides]
Available for QA at Live QA-1