NeurIPS 2019 accepted papers on Vision-language and multimodal
20 of the 1,429 papers accepted at NeurIPS 2019 (1.4%) are on Vision-language and multimodal, compared with 1.6% at NeurIPS 2018. They fall into 4 topics.
See NeurIPS 2019 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 · 11 papers
- Visualizing and Measuring the Geometry of BERT (179 citations)
- Are Disentangled Representations Helpful for Abstract Visual Reasoning? (116 citations)
- Adaptively Aligned Image Captioning via Adaptive Attention Time (39 citations)
- Aligning Visual Regions and Textual Concepts for Semantic-Grounded Image Representations (33 citations)
- Visual Concept-Metaconcept Learning (31 citations)
- On The Classification-Distortion-Perception Tradeoff (22 citations)
- Connective Cognition Network for Directional Visual Commonsense Reasoning (18 citations)
- Heterogeneous Graph Learning for Visual Commonsense Reasoning (18 citations)
- Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries (13 citations)
- Predicting the Politics of an Image Using Webly Supervised Data (8 citations)
- Visual Sequence Learning in Hierarchical Prediction Networks and Primate Visual Cortex (3 citations)
Cross-modal learning · 4 papers
- Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Models (87 citations)
- DM2C: Deep Mixed-Modal Clustering (23 citations)
- A coupled autoencoder approach for multi-modal analysis of cell types (17 citations)
- Adaptive Cross-Modal Few-shot Learning (5 citations)
Visual question answering · 4 papers
- ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks (1,665 citations)
- Self-Critical Reasoning for Robust Visual Question Answering (123 citations)
- RUBi: Reducing Unimodal Biases for Visual Question Answering (66 citations)
- TAB-VCR: Tags and Attributes based VCR Baselines (6 citations)
