Awesome Visual Commonsense

This is a curated list of resources about learning visual commonsense. Some datasets in pure texts are included as they might help expand commonsense knowledge.

Testbed

Vision

• Visual Choice of Plausible Alternatives: An Evaluation of Image-based Commonsense Causal Reasoning (LREC 2018)

• From Recognition to Cognition: Visual Commonsense Reasoning (CVPR 2019)

• What is More Likely to Happen Next? Video-and-Language Future Event Prediction (EMNLP 2020)

• Vis-Causal: Learning Contextual Causality from Time-consecutive Images

Language

• SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (EMNLP 2018)
• HellaSwag: Can a Machine Really Finish Your Sentence? (ACL 2019)

Knowledge Graph

Vision

• VisualCOMET: Reasoning about the Dynamic Context of a Still Image (ECCV 2020)

Language

• ConceptNet (AAAI 2017)
• ATOMIC (AAAI 2019)
• TransOMCS (IJCAI 2020)
• ATOMIC 2020 (AAAI 2021) : The comparison with the above datasets can be found in the paper.

Tutorials and Talks

• ACL 2020 Commonsense Tutorial
• Intuitive reasoning as (un)supervised language generation - Yejin Choi
• Learning representations of semantic concepts and their causal relationships: Inspiration from conscious processing - Yoshua Bengio

Implicit Knowledge Resources