NeurIPS 2020 accepted papers on Vision-language and multimodal
26 of the 1,901 papers accepted at NeurIPS 2020 (1.4%) are on Vision-language and multimodal, compared with 1.4% at NeurIPS 2019. They fall into 4 topics.
See NeurIPS 2020 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Human and embodied modeling · 16 papers
- The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes (145 citations)
- Counterfactual Contrastive Learning for Weakly-Supervised Vision-Language Grounding (99 citations)
- A Benchmark for Systematic Generalization in Grounded Language Understanding (72 citations)
- Compositional Explanations of Neurons (64 citations)
- Diverse Image Captioning with Context-Object Split Latent Spaces (26 citations)
- Prophet Attention: Predicting Attention with Future Attention (25 citations)
- Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning (21 citations)
- Texture Interpolation for Probing Visual Perception (13 citations)
- Self-Supervised Relationship Probing (8 citations)
- Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data (7 citations)
- High-contrast “gaudy” images improve the training of deep neural network models of visual cortex (4 citations)
- Multi-Stage Influence Function (3 citations)
and 4 more in the interactive map.
Cross-modal learning · 4 papers
- Self-Supervised MultiModal Versatile Networks (193 citations)
- Deep Multimodal Fusion by Channel Exchanging (116 citations)
- CoMIR: Contrastive Multimodal Image Representation for Registration (59 citations)
- See, Hear, Explore: Curiosity via Audio-Visual Association (24 citations)
Robot action and navigation · 3 papers
Visual question answering · 3 papers
- Large-Scale Adversarial Training for Vision-and-Language Representation Learning (277 citations)
- Multimodal Graph Networks for Compositional Generalization in Visual Question Answering (27 citations)
- Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies (21 citations)
