AAAI 2018 accepted papers on Vision-language and multimodal
57 of the 937 papers accepted at AAAI 2018 (6.1%) are on Vision-language and multimodal, compared with 3.3% at AAAI 2017. They fall into 6 topics.
See AAAI 2018 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 · 21 papers
- FiLM: Visual Reasoning with a General Conditioning Layer (3,024 citations)
- SciTaiL: A Textual Entailment Dataset from Science Question Answering (421 citations)
- R3: Reinforced Ranker-Reader for Open-Domain Question Answering (352 citations)
- S-Net: From Answer Extraction to Answer Synthesis for Machine Reading Comprehension (122 citations)
- Exploring Human-Like Attention Supervision in Visual Question Answering (107 citations)
- Co-Attending Free-Form Regions and Detections With Multi-Modal Multiplicative Feature Embedding for Visual Question Answering (89 citations)
- Fact Checking in Community Forums (74 citations)
- Question-Answering with Grammatically-Interpretable Representations (61 citations)
- Medical Exam Question Answering with Large-scale Reading Comprehension (55 citations)
- Explicit Reasoning over End-to-End Neural Architectures for Visual Question Answering (52 citations)
- Movie Question Answering: Remembering the Textual Cues for Layered Visual Contents (44 citations)
- A Question-Focused Multi-Factor Attention Network for Question Answering (33 citations)
and 9 more in the interactive map.
Cross-modal learning · 16 papers
- Multi-attention Recurrent Network for Human Communication Comprehension (546 citations)
- Unsupervised Generative Adversarial Cross-Modal Hashing (238 citations)
- Efficient Large-Scale Multi-Modal Classification (179 citations)
- CMCGAN: A Uniform Framework for Cross-Modal Visual-Audio Mutual Generation (83 citations)
- Robust Collaborative Discriminative Learning for RGB-Infrared Tracking (76 citations)
- DF2Net: Discriminative Feature Learning and Fusion Network for RGB-D Indoor Scene Classification (46 citations)
- Dual Deep Neural Networks Cross-Modal Hashing (46 citations)
- Integrating Both Visual and Audio Cues for Enhanced Video Caption (41 citations)
- Cross-Lingual Propagation for Deep Sentiment Analysis (39 citations)
- Learning Multimodal Word Representation via Dynamic Fusion Methods (36 citations)
- Learning Multi-Modal Word Representation Grounded in Visual Context (30 citations)
- Spatiotemporal Activity Modeling Under Data Scarcity: A Graph-Regularized Cross-Modal Embedding Approach (14 citations)
and 4 more in the interactive map.
Human and embodied modeling · 15 papers
- Adaptive Co-attention Network for Named Entity Recognition in Tweets (416 citations)
- Diverse Beam Search for Improved Description of Complex Scenes (239 citations)
- Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition (169 citations)
- Learning to Guide Decoding for Image Captioning (78 citations)
- Listening to the World Improves Speech Command Recognition (42 citations)
- Knowledge Enhanced Hybrid Neural Network for Text Matching (41 citations)
- How Images Inspire Poems: Generating Classical Chinese Poetry from Images with Memory Networks (38 citations)
- Acquiring Common Sense Spatial Knowledge Through Implicit Spatial Templates (37 citations)
- Discovering and Distinguishing Multiple Visual Senses for Polysemous Words (23 citations)
- Unsupervised Selection of Negative Examples for Grounded Language Learning (12 citations)
- VSE-ens: Visual-Semantic Embeddings with Efficient Negative Sampling (12 citations)
- Investigating Inner Properties of Multimodal Representation and Semantic Compositionality With Brain-Based Componential Semantics (10 citations)
and 3 more in the interactive map.
Robot action and navigation · 2 papers
CLIP and zero-shot · 2 papers
- Stack-Captioning: Coarse-to-Fine Learning for Image Captioning (202 citations)
- Neural Cross-Lingual Entity Linking (74 citations)
