AAAI 2017 accepted papers on Vision-language and multimodal
21 of the 639 papers accepted at AAAI 2017 (3.3%) are on Vision-language and multimodal, compared with 3.3% at AAAI 2016. They fall into 4 topics.
See AAAI 2017 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
- Attention Correctness in Neural Image Captioning (208 citations)
- Visual Sentiment Analysis by Attending on Local Image Regions (165 citations)
- Text-Guided Attention Model for Image Captioning (94 citations)
- Condensed Memory Networks for Clinical Diagnostic Inferencing (86 citations)
- Imagined Visual Representations as Multimodal Embeddings (84 citations)
- Reference Based LSTM for Image Captioning (63 citations)
- Let Your Photos Talk: Generating Narrative Paragraph for Photo Stream via Bidirectional Attention Recurrent Neural Networks (58 citations)
- Towards Better Understanding the Clothing Fashion Styles: A Multimodal Deep Learning Approach (56 citations)
- Sherlock: Scalable Fact Learning in Images (24 citations)
- Web-Based Semantic Fragment Discovery for On-Line Lingual-Visual Similarity (2 citations)
Visual question answering · 6 papers
- Leveraging Video Descriptions to Learn Video Question Answering (164 citations)
- Question Difficulty Prediction for READING Problems in Standard Tests (125 citations)
- Attentive Interactive Neural Networks for Answer Selection in Community Question Answering (92 citations)
- Improving Event Causality Recognition with Multiple Background Knowledge Sources Using Multi-Column Convolutional Neural Networks (70 citations)
- Community-Based Question Answering via Asymmetric Multi-Faceted Ranking Network Learning (56 citations)
- Word Embedding Based Correlation Model for Question/Answer Matching (49 citations)
Cross-modal learning · 4 papers
- Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval (344 citations)
- Collective Deep Quantization for Efficient Cross-Modal Retrieval (101 citations)
- Exploring Commonality and Individuality for Multi-Modal Curriculum Learning (33 citations)
- Transitive Hashing Network for Heterogeneous Multimedia Retrieval (30 citations)
