CVPR 2019 accepted papers on Vision-language and multimodal
68 of the 1,294 papers accepted at CVPR 2019 (5.3%) are on Vision-language and multimodal, compared with 5.3% at CVPR 2018. They fall into 5 topics.
See CVPR 2019 in the interactive map
Submitting to CVPR? 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 · 28 papers
- Attention Branch Network: Learning of Attention Mechanism for Visual Explanation (521 citations)
- Unsupervised Image Captioning (231 citations)
- Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions (215 citations)
- Improving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing (204 citations)
- Engaging Image Captioning via Personality (168 citations)
- Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations (166 citations)
- Look Back and Predict Forward in Image Captioning (155 citations)
- Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks (147 citations)
- Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech (145 citations)
- Good News, Everyone! Context Driven Entity-Aware Captioning for News Images (139 citations)
- Connecting Touch and Vision via Cross-Modal Prediction (133 citations)
- Cross-Modal Relationship Inference for Grounding Referring Expressions (126 citations)
and 16 more in the interactive map.
Visual question answering · 22 papers
- GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering (1,458 citations)
- Deep Modular Co-Attention Networks for Visual Question Answering (953 citations)
- From Recognition to Cognition: Visual Commonsense Reasoning (785 citations)
- Towards VQA Models That Can Read (702 citations)
- OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge (689 citations)
- Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering (401 citations)
- MUREL: Multimodal Relational Reasoning for Visual Question Answering (331 citations)
- Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering (281 citations)
- RAVEN: A Dataset for Relational and Analogical Visual REasoNing (180 citations)
- Cycle-Consistency for Robust Visual Question Answering (166 citations)
- Recursive Visual Attention in Visual Dialog (139 citations)
- Explicit Bias Discovery in Visual Question Answering Models (95 citations)
and 10 more in the interactive map.
Cross-modal learning · 11 papers
- Cross-Modal Self-Attention Network for Referring Image Segmentation (534 citations)
- Deep Supervised Cross-Modal Retrieval (469 citations)
- Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval (271 citations)
- ContextDesc: Local Descriptor Augmentation With Cross-Modality Context (233 citations)
- Deep Multimodal Clustering for Unsupervised Audiovisual Learning (210 citations)
- Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition With Multimodal Training (191 citations)
- Selective Sensor Fusion for Neural Visual-Inertial Odometry (167 citations)
- Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food Images (142 citations)
- A Simple Baseline for Audio-Visual Scene-Aware Dialog (69 citations)
- Cross-Modality Personalization for Retrieval (12 citations)
- A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing
Robot action and navigation · 5 papers
- Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation (548 citations)
- TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments (373 citations)
- The Regretful Agent: Heuristic-Aided Navigation Through Progress Estimation (174 citations)
- Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigation (154 citations)
- Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Intervention (107 citations)
CLIP and zero-shot · 2 papers
- Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval (169 citations)
- Hybrid-Attention Based Decoupled Metric Learning for Zero-Shot Image Retrieval (71 citations)
