ECCV 2016 accepted papers on Vision-language and multimodal
18 of the 415 papers accepted at ECCV 2016 (4.3%) are on Vision-language and multimodal. They fall into 4 topics.
See ECCV 2016 in the interactive map
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 · 10 papers
- SPICE: Semantic Propositional Image Caption Evaluation (2,045 citations)
- Modeling Context in Referring Expressions (1,205 citations)
- Deep Learning the City: Quantifying Urban Perception at a Global Scale (623 citations)
- Generating Visual Explanations (558 citations)
- Grounding of Textual Phrases in Images by Reconstruction (463 citations)
- A Benchmark for Automatic Visual Classification of Clinical Skin Disease Images (208 citations)
- Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network (162 citations)
- The Curious Robot: Learning Visual Representations via Physical Interactions (162 citations)
- Matching Handwritten Document Images (56 citations)
- Automatic Attribute Discovery with Neural Activations (51 citations)
Visual question answering · 5 papers
- Ask, Attend and Answer: Exploring Question-Guided Spatial Attention for Visual Question Answering (765 citations)
- A Diagram is Worth a Dozen Images (373 citations)
- Revisiting Visual Question Answering Baselines (238 citations)
- Learning Models for Actions and Person-Object Interactions with Transfer to Question Answering (118 citations)
- Leveraging Visual Question Answering for Image-Caption Ranking (82 citations)
Cross-modal learning · 2 papers
Multimodal LLMs · 1 paper
- Visual Motif Discovery via First-Person Vision (15 citations)
