Skip to content

Latest commit

 

History

History
145 lines (115 loc) · 13.6 KB

README.md

File metadata and controls

145 lines (115 loc) · 13.6 KB

Visual Reasoning Papers

A curated list of visual reasoning papers.

  • Last update time: 2022-11-09.
  • Maintainer: Xin Hong

Visual Reasoning Papers on arXiv

In addition to the papers listed below, we also provide an automatically generated arXiv paper list, which is updated monthly. Click on the trend chart above to check.

"★" means the paper introduces a new task or dataset.

Survey Papers

  • Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices, Małkiński & Mańdziuk, arXiv 2022. Paper
  • A Review of Emerging Research Directions in Abstract Visual Reasoning, Małkiński & Mańdziuk, arXiv 2022. Paper
  • Reasoning about Actions over Visual and Linguistic Modalities: A Survey, Sampat et al., arXiv 2022. Paper

Related Paper Lists & Tutorials

  • Deep-Reasoning-Papers: Recent Papers including Neural Symbolic Reasoning, Logical Reasoning, Visual Reasoning, planning and any other topics connecting deep learning and reasoning.
  • Awesome deep logic: A collection of papers of neural-symbolic AI (mainly focus on NLP applications).
  • Neural Machine Reasoning: This tutorial reviews recent advances on dynamic neural networks that aim to reach a deliberative reasoning capability. This goes beyond the current associative pattern matching excelled by deep learning.

2022

  • ★ WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language Models, Bitton et al., NeurIPS 2022. Paper
  • ★ REX: Reasoning-aware and Grounded Explanation, Chen & Zhao, CVPR 2022. Paper
  • ★ The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning, Hessel et al., arXiv 2022. Paper
  • ★ Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions, Jiang et al., CVPR 2022. Paper
  • ★ Maintaining Reasoning Consistency in Compositional Visual Question Answering, Jing et al., CVPR 2022. Paper
  • ★ Visual Abductive Reasoning, Liang et al., CVPR 2022. Paper
  • ★ QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning, Li & Søgaard, ACL 2022. Paper
  • ★ From Representation to Reasoning: Towards Both Evidence and Commonsense Reasoning for Video Question-Answering, Li et al., CVPR 2022. Paper
  • ★ Visual Spatial Reasoning, Liu et al., arXiv 2022. Paper
  • Grammar-Based Grounded Lexicon Learning, Mao et al., NeurIPS 2022. Paper
  • RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning, Ma et al., ICLR 2022. Paper
  • ★ IntPhys 2019: A Benchmark for Visual Intuitive Physics Understanding, Riochet et al., TPAMI 2022.
  • ★ Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality, Thrush et al., CVPR 2022. Paper
  • ★ Self-Supervised Spatial Reasoning on Multi-View Line Drawings, Xiang et al., CVPR 2022. Paper
  • Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning, Zhang et al., ECCV 2022. Paper
  • ★ VideoABC: A Real-World Video Dataset for Abductive Visual Reasoning, Zhao et al., TIP 2022. Paper

2021

  • ★ Scale-Localized Abstract Reasoning, Benny et al., CVPR 2021. Paper
  • Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning, Chen et al., ICLR 2021. Paper
  • Meta Module Network for Compositional Visual Reasoning, Chen et al., WACV 2021. Paper
  • Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language, Ding et al., NeurIPS 2021. Paper
  • ★ Transformation Driven Visual Reasoning, Hong et al., CVPR 2021. Paper
  • ★ Stratified Rule-Aware Network for Abstract Visual Reasoning, Hu et al., AAAI 2021. Paper
  • Interpretable Visual Reasoning via Induced Symbolic Space, Wang et al., ICCV 2021. Paper

2020

  • Neuro-Symbolic Visual Reasoning: Disentangling "Visual" from "Reasoning", Amizadeh et al., ICML 2020. Paper
  • ★ CoPhy: Counterfactual Learning of Physical Dynamics, Baradel et al., ICLR 2020. Paper
  • Differentiable Adaptive Computation Time for Visual Reasoning, Eyzaguirre & Soto, CVPR 2020. Paper
  • ★ CATER: A diagnostic dataset for Compositional Actions & TEmporal Reasoning, Girdhar & Ramanan, ICLR 2020. Paper
  • Forward Prediction for Physical Reasoning, Girdhar et al., arXiv 2020. Paper
  • Dynamic Language Binding in Relational Visual Reasoning, Le et al., IJCAI 2020. Paper
  • ★ Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning, Nie et al., NeurIPS 2020. Paper
  • ★ VisualCOMET: Reasoning About the Dynamic Context of a Still Image, Park et al., ECCV 2020. Paper
  • ★ V-PROM: A Benchmark for Visual Reasoning Using Visual Progressive Matrices, Teney et al., AAAI 2020. Paper
  • What Can Neural Networks Reason About?, Xu et al., ICLR 2020. Paper
  • ★ CLEVRER: Collision Events for Video Representation and Reasoning, Yi et al., ICLR 2020. Paper

2019

  • ★ PHYRE: A New Benchmark for Physical Reasoning, Bakhtin et al., NeurIPS 2019. Paper
  • ★ GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering, Hudson & Manning, CVPR 2019. Paper
  • Learning by Abstraction: The Neural State Machine, Hudson & Manning, NeurIPS 2019. Paper
  • Visual Reasoning by Progressive Module Networks, Kim et al., ICLR 2019. Paper
  • ★ CLEVR-Ref+: Diagnosing Visual Reasoning With Referring Expressions, Liu et al., CVPR 2019. Paper
  • The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision, Mao et al., ICLR 2019. Paper
  • ★ Robust Change Captioning, Park et al., ICCV 2019. Paper
  • Explainable and Explicit Visual Reasoning Over Scene Graphs, Shi et al., CVPR 2019. Paper
  • ★ A Corpus for Reasoning about Natural Language Grounded in Photographs, Suhr et al., ACL 2019. Paper
  • ★ Visual Entailment: A Novel Task for Fine-Grained Image Understanding, Xie et al., arXiv 2019. Paper
  • ★ From Recognition to Cognition: Visual Commonsense Reasoning, Zellers et al., CVPR 2019. Paper
  • Learning Perceptual Inference by Contrasting, Zhang et al., NeurIPS 2019. Paper
  • ★ RAVEN: A Dataset for Relational and Analogical Visual REasoNing, Zhang et al., CVPR 2019. Paper

2018

  • ★ Measuring abstract reasoning in neural networks, Santoro et al., ICML 2018. Paper
  • Compositional Attention Networks for Machine Reasoning, Hudson & Manning, ICLR 2018. Paper
  • FiLM: Visual Reasoning with a General Conditioning Layer, Perez et al., AAAI 2018. Paper
  • Chain of Reasoning for Visual Question Answering, Wu et al., NeurIPS 2018. Paper
  • Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding, Yi et al., NeurIPS 2018. Paper

2017

  • Learning to Reason: End-to-End Module Networks for Visual Question Answering, Hu et al., ICCV 2017. Paper
  • ★ CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning, Johnson et al., CVPR 2017. Paper
  • Inferring and Executing Programs for Visual Reasoning, Johnson et al., ICCV 2017. Paper
  • A simple neural network module for relational reasoning, Santoro et al., NeurIPS 2017. Paper
  • ★ A Corpus of Natural Language for Visual Reasoning, Suhr et al., ACL 2017. Paper

2016

  • Neural Module Networks, Andreas et al., CVPR 2016. Paper
  • ★ Visual Storytelling, Huang et al., ACL 2016. Paper