NeurIPS 2018 accepted papers on Vision-language and multimodal
16 of the 1,008 papers accepted at NeurIPS 2018 (1.6%) are on Vision-language and multimodal, compared with 1.6% at NeurIPS 2017. They fall into 5 topics.
See NeurIPS 2018 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
Visual question answering · 9 papers
- Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding (349 citations)
- Learning Conditioned Graph Structures for Interpretable Visual Question Answering (148 citations)
- Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base (86 citations)
- Bilinear Attention Networks (76 citations)
- Out of the Box: Reasoning with Graph Convolution Nets for Factual Visual Question Answering (63 citations)
- Chain of Reasoning for Visual Question Answering (39 citations)
- Learning to Specialize with Knowledge Distillation for Visual Question Answering (31 citations)
- Answerer in Questioner's Mind: Information Theoretic Approach to Goal-Oriented Visual Dialog (27 citations)
- Overcoming Language Priors in Visual Question Answering with Adversarial Regularization (17 citations)
Human and embodied modeling · 3 papers
- Toddler-Inspired Visual Object Learning (45 citations)
- A Neural Compositional Paradigm for Image Captioning (34 citations)
- GLoMo: Unsupervised Learning of Transferable Relational Graphs (21 citations)
Cross-modal learning · 2 papers
Robot action and navigation · 1 paper
- Speaker-Follower Models for Vision-and-Language Navigation (242 citations)
