CVPR 2020 accepted papers on Vision-language and multimodal
64 of the 1,467 papers accepted at CVPR 2020 (4.4%) are on Vision-language and multimodal, compared with 5.3% at CVPR 2019. They fall into 4 topics.
See CVPR 2020 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 · 27 papers
- X-Linear Attention Networks for Image Captioning (699 citations)
- Towards Accurate Scene Text Recognition With Semantic Reasoning Networks (382 citations)
- SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition (320 citations)
- Multi-Task Collaborative Network for Joint Referring Expression Comprehension and Segmentation (314 citations)
- Referring Image Segmentation via Cross-Modal Progressive Comprehension (236 citations)
- Image Search With Text Feedback by Visiolinguistic Attention Learning (193 citations)
- PaStaNet: Toward Human Activity Knowledge Engine (145 citations)
- More Grounded Image Captioning by Distilling Image-Text Matching Model (139 citations)
- Sketch Less for More: On-the-Fly Fine-Grained Sketch-Based Image Retrieval (133 citations)
- Multimodal Categorization of Crisis Events in Social Media (119 citations)
- Graph-Structured Referring Expression Reasoning in the Wild (102 citations)
- Transform and Tell: Entity-Aware News Image Captioning (88 citations)
and 15 more in the interactive map.
Cross-modal learning · 16 papers
- What Makes Training Multi-Modal Classification Networks Hard? (532 citations)
- Multi-Modality Cross Attention Network for Image and Sentence Matching (453 citations)
- IMRAM: Iterative Matching With Recurrent Attention Memory for Cross-Modal Image-Text Retrieval (434 citations)
- Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning (332 citations)
- Context-Aware Attention Network for Image-Text Retrieval (292 citations)
- MMTM: Multimodal Transfer Module for CNN Fusion (265 citations)
- Iterative Answer Prediction With Pointer-Augmented Multimodal Transformers for TextVQA (222 citations)
- Bi-Directional Relationship Inferring Network for Referring Image Segmentation (209 citations)
- Music Gesture for Visual Sound Separation (202 citations)
- Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation (175 citations)
- Creating Something From Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing (138 citations)
- Universal Weighting Metric Learning for Cross-Modal Matching (109 citations)
and 4 more in the interactive map.
Visual question answering · 13 papers
- 12-in-1: Multi-Task Vision and Language Representation Learning (415 citations)
- In Defense of Grid Features for Visual Question Answering (364 citations)
- Counterfactual Samples Synthesizing for Robust Visual Question Answering (358 citations)
- Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing (154 citations)
- Counterfactual Vision and Language Learning (130 citations)
- Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text (123 citations)
- Modality Shifting Attention Network for Multi-Modal Video Question Answering (81 citations)
- On the General Value of Evidence, and Bilingual Scene-Text Visual Question Answering (76 citations)
- Assessing Image Quality Issues for Real-World Problems (62 citations)
- SQuINTing at VQA Models: Introspecting VQA Models With Sub-Questions (47 citations)
- Attention-Based Context Aware Reasoning for Situation Recognition (28 citations)
- VQA With No Questions-Answers Training (16 citations)
and 1 more in the interactive map.
Robot action and navigation · 8 papers
- ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks (533 citations)
- REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments (317 citations)
- Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-Training (251 citations)
- Neural Topological SLAM for Visual Navigation (223 citations)
- Vision-Language Navigation With Self-Supervised Auxiliary Reasoning Tasks (215 citations)
- RoboTHOR: An Open Simulation-to-Real Embodied AI Platform (214 citations)
- Vision-Dialog Navigation by Exploring Cross-Modal Memory (54 citations)
- Gold Seeker: Information Gain From Policy Distributions for Goal-Oriented Vision-and-Langauge Reasoning (3 citations)
