Visual Question Answering

Visual Question Answering (VQA) aims to enable computers to answer questions about images, requiring sophisticated integration of visual and linguistic understanding. Current research emphasizes improving model robustness and reliability, focusing on addressing issues like inconsistencies in responses, hallucinations, and the handling of unanswerable questions, often using large multimodal language models (MLLMs) like BLIP-2 and LLaVA. This field is crucial for advancing AI's ability to interact with the world in a more human-like way, with applications ranging from assistive technologies for visually impaired individuals to medical image analysis and automated data visualization evaluation.

Papers

April 16, 2023

Chain of Thought Prompt Tuning in Vision Language Models
Jiaxin Ge, Hongyin Luo, Siyuan Qian, Yulu Gan, Jie Fu, Shanghang Zhang
Vision Language Model Vision Language Visual Question Answering Chain of Thought Side Chain Reasoning Process Thought Prompting

April 13, 2023

PDFVQA: A New Dataset for Real-World VQA on PDF Documents
Yihao Ding, Siwen Luo, Hyunsuk Chung, Soyeon Caren Han
Visual Question Answering Document Understanding PDF Document VQA Datasets Ok Vqa

April 6, 2023

Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions
Jia-Hong Huang, Modar Alfadly, Bernard Ghanem, Marcel Worring
Context Learning Visual Question Answering Side Chain QA Datasets Robustness Analysis Visual Question Answering Model

April 4, 2023

SC-ML: Self-supervised Counterfactual Metric Learning for Debiased Visual Question Answering
Xinyao Shu, Shiyang Yan, Xu Yang, Ziheng Wu, Zhongfeng Chen, Zhenyu Lu
Visual Question Answering Visual Question Corpus Bias Counterfactual Metric

April 2, 2023

Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space
Yuwei Sun, Hideya Ochiai, Jun Sakuma
Visual Question Answering Adversarial Learning Trojan Attack Activation Space

March 27, 2023

Curriculum Learning for Compositional Visual Reasoning
Wafa Aissa, Marin Ferecatu, Michel Crucianu
Visual Question Answering Curriculum Learning Modal Embeddings Neural Module Compositional Visual Reasoning

March 22, 2023

Integrating Image Features with Convolutional Sequence-to-sequence Network for Multilingual Visual Question Answering
Triet Minh Thai, Son T. Luu
Visual Question Answering

March 16, 2023

Logical Implications for Visual Question Answering Consistency
Sergio Tascon-Morales, Pablo Márquez-Neila, Raphael Sznitman
Visual Question Answering Consistency Loss

March 13, 2023

Polar-VQA: Visual Question Answering on Remote Sensed Ice sheet Imagery from Polar Region
Argho Sarkar, Maryam Rahnemoonfar
Visual Question Answering Visual Question POLAR Keywords

March 10, 2023

Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models
Tom van Sonsbeek, Mohammad Mahdi Derakhshani, Ivona Najdenkoska, Cees G. M. Snoek, Marcel Worring
Language Model Pre Trained Language Model Visual Question Answering Visual Question Medical Visual Question Answering Prefix Tuning Open Ended Visual Question Answering

March 9, 2023

VQA-based Robotic State Recognition Optimized with Genetic Algorithm
Kento Kawaharazuka, Yoshiki Obinata, Naoaki Kanazawa, Kei Okada, Masayuki Inaba
Vision Language Model Non Humanoid Robot Visual Question Answering Genetic Algorithm Robotic Arm Activity State Recognition

March 7, 2023

Graph Neural Networks in Vision-Language Image Understanding: A Survey
Henry Senior, Gregory Slabaugh, Shanxin Yuan, Luca Rossi
Graph Neural Network Timely Survey Visual Question Answering 2 Dimensional Image Captioning Scene Understanding

March 5, 2023

March 2, 2023

MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering
Jingjing Jiang, Nanning Zheng
Vision Language Model Visual Question Answering Parameter Efficient Tuning

February 28, 2023

VQA with Cascade of Self- and Co-Attention Blocks
Aakansha Mishra, Ashish Anand, Prithwijit Guha
Visual Question Answering Attention Module Self Information Self Attention Module Attention Block TF Cascade Cross Attention Block

February 25, 2023

Medical visual question answering using joint self-supervised learning
Yuan Zhou, Jing Mei, Yiqin Yu, Tanveer Syeda-Mahmood
Medical Image Visual Question Answering Visual Question Medical Visual Question Answering

February 23, 2023

EVJVQA Challenge: Multilingual Visual Question Answering
Ngan Luu-Thuy Nguyen, Nghia Hieu Nguyen, Duong T. D Vo, Khanh Quoc Tran, Kiet Van Nguyen
Visual Question Answering Open Domain Question

February 19, 2023

Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learning
Xinyue Hu, Lin Gu, Kazuma Kobayashi, Qiyuan An, Qingyu Chen, Zhiyong Lu, Chang Su, Tatsuya Harada, Yingying Zhu
Medical Image Visual Question Answering Medical Visual Question Answering Modal Temporal Relation Graph Learning

February 18, 2023

Bridge Damage Cause Estimation Using Multiple Images Based on Visual Question Answering
Tatsuro Yamane, Pang-jo Chun, Ji Dang, Takayuki Okatani
Visual Question Answering Damage Detection Multiple Image Building Damage Detection Bridge Inspection

Visual Question Answering

Papers

Chain of Thought Prompt Tuning in Vision Language Models

PDFVQA: A New Dataset for Real-World VQA on PDF Documents

Improving Visual Question Answering Models through Robustness Analysis and In-Context Learning with a Chain of Basic Questions

SC-ML: Self-supervised Counterfactual Metric Learning for Debiased Visual Question Answering

Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space

Curriculum Learning for Compositional Visual Reasoning

Integrating Image Features with Convolutional Sequence-to-sequence Network for Multilingual Visual Question Answering

Logical Implications for Visual Question Answering Consistency

Polar-VQA: Visual Question Answering on Remote Sensed Ice sheet Imagery from Polar Region

Open-Ended Medical Visual Question Answering Through Prefix Tuning of Language Models

VQA-based Robotic State Recognition Optimized with Genetic Algorithm

Graph Neural Networks in Vision-Language Image Understanding: A Survey

VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning

Knowledge-Based Counterfactual Queries for Visual Question Answering

MixPHM: Redundancy-Aware Parameter-Efficient Tuning for Low-Resource Visual Question Answering

VQA with Cascade of Self- and Co-Attention Blocks

Medical visual question answering using joint self-supervised learning

EVJVQA Challenge: Multilingual Visual Question Answering

Interpretable Medical Image Visual Question Answering via Multi-Modal Relationship Graph Learning

Bridge Damage Cause Estimation Using Multiple Images Based on Visual Question Answering