CVPR Language & Vision Workshop list of accepted 2019 papers

Individual emails coming by Monday.
Some submissions will be invited to present longer talks.
All submissions are invited to present spotlights.
A schedule, instructions, and details are coming in the next week.

Thanks!


1. A Coherence Approach to Data-Driven Inference in Visual Communication
2. Answer Them All! Toward Universal Visual Question Answering Models
3. Answering Questions about Data Visualizations using Efficient Bimodal Fusion
4. Baby steps towards few-shot learning with multiple semantics
5. ClearGAN: Photo-Realistic High-Resolution Text-to-Image Synthesis via Joint Inter-modal and Intra-modal Attention Modeling
6. Counterfactually Resilient Visual Grounding with a Modular Design
7. Curvature: A signature for Action Recognition in Video Sequences
8. Deep Sentiment Features of Context, Faces and Text for Affective Video Analysis
9. Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioning
10. Generating Diverse and Informative Natural Language Fashion Feedback
11. Image Captioning with Integrated Bottom-Up and Multi-level Residual Top-Down Attention for Game Scene Understanding
12. Image captioning with weakly-supervised attention penalty
13. Indian Language Optical Character Recognition Through Bharati Script based Deep Convolutional Neural Networks
14. Integration of Text-maps in Convolutional Neural Networks for Region Detection among Different Textual Categories
15. Joint Visual-Textual Embedding for Multimodal Style Search
16. Let's Transfer Text Transformations to Images
17. Leveraging Unpaired Data for Image Captioning upon Scarce Supervised Data
18. Neural Sign Language Translation based on Human Keypoint Estimation
19. Language Guided Life-long Visual Learning
20. Referring Expression Object Segmentation with Caption-Aware Consistency
21. Scene Perspective Framing with Visual Question Answering Dialog
22. Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions
23. Sometimes you just need to ask: Situation recognition via VQA
24. SuperChat: Dialogue Generation by Transfer Learning from Vision to Language using Two-dimensional Word Embedding and Pretrained ImageNet
25. Tripping through time: Efficient Temporal Localization of Activities in Videos
26. Understanding Art through Multi-Modal Retrieval in Paintings
27. Using Language to Evaluate Image Enhancement Tasks
28. Video Object Segmentation with Language Referring Expressions
29. Visual Discourse Parsing
30. Visual Natural Language Query Auto-Completion for Estimating Instance Probabilities
31. VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People
32. Which generates better jokes, hand-crafted features or deep features
33. Multitask Text-to-Visual Embedding with Titles and Clickthrough Data