AAAI 2019 accepted papers on Vision-language and multimodal
51 of the 1,147 papers accepted at AAAI 2019 (4.4%) are on Vision-language and multimodal, compared with 6.1% at AAAI 2018. They fall into 5 topics.
See AAAI 2019 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
Visual question answering · 25 papers
- Beyond RNNs: Positional Self-Attention with Co-Attention for Video Question Answering (269 citations)
- BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection (235 citations)
- KVQA: Knowledge-Aware Visual Question Answering (185 citations)
- VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis (155 citations)
- TallyQA: Answering Complex Counting Questions (102 citations)
- Personalized Question Routing via Heterogeneous Network Embedding (57 citations)
- Differential Networks for Visual Question Answering (40 citations)
- Dynamic Capsule Attention for Visual Question Answering (40 citations)
- A Novel Framework for Robustness Analysis of Visual QA Models (32 citations)
- Exploiting Sentence Embedding for Medical Question Answering (24 citations)
- Adversarial Training for Community Question Answer Selection Based on Multi-Scale Matching (23 citations)
- Answer Identification from Product Reviews for User Questions by Multi-Task Attentive Networks (22 citations)
and 13 more in the interactive map.
Human and embodied modeling · 16 papers
- Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition (455 citations)
- Multi-Interactive Memory Network for Aspect Based Multimodal Sentiment Analysis (275 citations)
- Scene Text Recognition from Two-Dimensional Perspective (259 citations)
- Hierarchical Attention Network for Image Captioning (141 citations)
- Deliberate Attention Networks for Image Captioning (52 citations)
- Hashtag Recommendation for Photo Sharing Services (47 citations)
- Hierarchical Photo-Scene Encoder for Album Storytelling (30 citations)
- Incorporating Semantic Similarity with Geographic Correlation for Query-POI Relevance Learning (29 citations)
- Cognitive Deficit of Deep Learning in Numerosity (15 citations)
- Connecting Language to Images: A Progressive Attention-Guided Network for Simultaneous Image Captioning and Language Grounding (14 citations)
- DeepTileBars: Visualizing Term Distribution for Neural Information Retrieval (13 citations)
- Abstractive Text Summarization by Incorporating Reader Comments
and 4 more in the interactive map.
Cross-modal learning · 8 papers
- Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval (121 citations)
- An Efficient Approach to Informative Feature Extraction from Multimodal Data (81 citations)
- Ranking-Based Deep Cross-Modal Hashing (78 citations)
- Joint Representation Learning for Multi-Modal Transportation Recommendation (77 citations)
- Y2Seq2Seq: Cross-Modal Representation Learning for 3D Shape and Text by Joint Reconstruction and Prediction of View and Word Sequences (56 citations)
- ACM: Adaptive Cross-Modal Graph Convolutional Neural Networks for RGB-D Scene Recognition (39 citations)
- Deep Robust Unsupervised Multi-Modal Network (7 citations)
- Found in Translation: Learning Robust Joint Representations by Cyclic Translations between Modalities
