CVPR 2018 accepted papers on Vision-language and multimodal
52 of the 979 papers accepted at CVPR 2018 (5.3%) are on Vision-language and multimodal, compared with 6.8% at CVPR 2017. They fall into 5 topics.
See CVPR 2018 in the interactive map
Submitting to CVPR? 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 · 23 papers
- MAttNet: Modular Attention Network for Referring Expression Comprehension (869 citations)
- Convolutional Image Captioning (432 citations)
- Learning Semantic Concepts and Order for Image and Sentence Matching (361 citations)
- AON: Towards Arbitrarily-Oriented Text Recognition (329 citations)
- Grounding Referring Expressions in Images by Variational Context (273 citations)
- Visual Grounding via Accumulated Attention (215 citations)
- Discriminability Objective for Training Descriptive Captions (196 citations)
- Parallel Attention: A Unified Framework for Visual Object Discovery Through Dialogs and Queries (154 citations)
- Learning to Evaluate Image Captioning (139 citations)
- SemStyle: Learning to Generate Stylised Image Captions Using Unaligned Text (131 citations)
- Knowledge Aided Consistency for Weakly Supervised Phrase Grounding (111 citations)
- Regularizing RNNs for Caption Generation by Reconstructing the Past With the Present (96 citations)
and 11 more in the interactive map.
Visual question answering · 23 papers
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering (5,159 citations)
- VizWiz Grand Challenge: Answering Visual Questions From Blind People (612 citations)
- Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering (602 citations)
- Tips and Tricks for Visual Question Answering: Learnings From the 2017 Challenge (430 citations)
- Multimodal Explanations: Justifying Decisions and Pointing to the Evidence (420 citations)
- IQA: Visual Question Answering in Interactive Environments (376 citations)
- Improved Fusion of Visual and Language Representations by Dense Symmetric Co-Attention for Visual Question Answering (373 citations)
- Embodied Question Answering (352 citations)
- DVQA: Understanding Data Visualizations via Question Answering (252 citations)
- Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning (206 citations)
- Visual Question Generation as Dual Task of Visual Question Answering (177 citations)
- Visual Question Answering With Memory-Augmented Networks (112 citations)
and 11 more in the interactive map.
