ICCV 2017 accepted papers on Vision-language and multimodal
42 of the 621 papers accepted at ICCV 2017 (6.8%) are on Vision-language and multimodal. They fall into 5 topics.
See ICCV 2017 in the interactive map
Submitting to ICCV? 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 · 19 papers
- Boosting Image Captioning With Attributes (760 citations)
- Focusing Attention: Towards Accurate Text Recognition in Natural Images (542 citations)
- Improved Image Captioning via Policy Gradient Optimization of SPIDEr (465 citations)
- Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention (383 citations)
- Deep Spatial-Semantic Attention for Fine-Grained Sketch-Based Image Retrieval (268 citations)
- Automatic Spatially-Aware Fashion Concept Discovery (237 citations)
- Speaking the Same Language: Matching Machine to Human Captions by Adversarial Training (230 citations)
- Areas of Attention for Image Captioning (212 citations)
- Learning Visual Attention to Identify People With Autism Spectrum Disorder (180 citations)
- Fashion Forward: Forecasting Visual Style in Fashion (178 citations)
- Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding (169 citations)
- BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography (165 citations)
and 7 more in the interactive map.
Visual question answering · 11 papers
- Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization (25,969 citations)
- Multi-Modal Factorized Bilinear Pooling With Co-Attention Learning for Visual Question Answering (810 citations)
- MUTAN: Multimodal Tucker Fusion for Visual Question Answering (755 citations)
- Learning to Reason: End-To-End Module Networks for Visual Question Answering (538 citations)
- An Analysis of Visual Question Answering Algorithms (268 citations)
- VQS: Linking Segmentations to Questions and Answers for Supervised Attention in VQA and Question-Focused Semantic Segmentation (124 citations)
- Structured Attentions for Visual Question Answering (118 citations)
- A Read-Write Memory Network for Movie Story Understanding (100 citations)
- MarioQA: Answering Questions by Watching Gameplay Videos (95 citations)
- Learning to Disambiguate by Asking Discriminative Questions (23 citations)
- Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks (20 citations)
Cross-modal learning · 8 papers
- Look, Listen and Learn (865 citations)
- Identity-Aware Textual-Visual Matching With Latent Co-Attention (290 citations)
- Learning a Recurrent Residual Fusion Network for Multimodal Matching (163 citations)
- Cross-Modal Deep Variational Hashing (100 citations)
- Deep Binaries: Encoding Semantic-Rich Cues for Efficient Textual-Visual Cross Retrieval (53 citations)
- Misalignment-Robust Joint Filter for Cross-Modal Image Pairs (28 citations)
- A Multimodal Deep Regression Bayesian Network for Affective Video Content Analyses (25 citations)
- Multimodal Gaussian Process Latent Variable Models With Harmonization (9 citations)
Multimodal LLMs · 2 papers
CLIP and zero-shot · 2 papers
- Learning Robust Visual-Semantic Embeddings (170 citations)
- Learning Visual N-Grams From Web Data (94 citations)
