Submit at https://cmt3.research.microsoft.com/ROSE2022
- Workshop paper submission deadline:
March 10, 2022March 28, 2022
- Notification to authors:
April 01, 2022April 12, 2022
- Camera ready deadline:
April 08, 2022April 18, 2022
The goal of this workshop is to explore the following fundamental problems:
- Characterizing distribution shifts in sequential data
- Developing robust models for sequential data
- Evaluation and benchmarking robustness in sequential data
- Real-world applications of robust learning.
This workshop will focus on the following non-exhaustive list of topics addressing the above mentioned fundamental problems:
- Sequential visual data: This will include problems focusing on video data such as action recognition, action detection, temporal action detection, video segmentation, video object detection, and video retrieval.
- Continual learning domain: Humans have capabilities to continually learn new skills and adapt to new environments without forgetting previous skills. Here, the focus will be to develop robust models under continually evolving data such as in the self-driving car domain.
- Vision-language domain: In this multi-modal theme we will focus on problems such as visual reasoning (visual question answering, visual commonsense, composition visual question answering, video question answering, etc.), visual grounded text generation (image captioning, video captioning, etc.), and cross-modal retrieval (video-text retrieval).
- Applications: In many real-world applications, data is mostly sequential and we will focus on real-world applications from robustness point of view. This includes tasks in robotics (for example, vision-language navigation), autonomous driving, medicine, and surveillance.
- Fairness and social impact: The existing models are prone to the bias present in the training data and this topic will focus on developing robust models for sequential data with fairness as the main objective.
- The manuscript should follow CVPR 2022 paper template. The paper can have maximum of 8 pages (excluding references) on above mentioned topics. We encourage the authors to submit 4 page papers. Please refer to CVPR 2022 author kit for detailed formatting instructions.
- Submitted manuscript should follow the double-blind policy following CVPR 2022.
- Dual submission to CVPR 2022 and ROSE 2022 is allowed, however the manuscript must contain substantial original contents that is not submitted to any other workshop, conference or journal.
- Submissions will be desk-rejected without review if they:
- violate the double-blind or dual-submission policy
- have more than 8 pages (excluding references)
- Submitted manuscripts will be peer reviewed under the double-blind policy of CVPR 2022. Submission should be done online through the CMT submission system.
- Accepted papers will be available at the workshop webpage. They will also be made available in the main conference proceedings if the authors agree (only for full-length papers not published at CVPR 2022).
Join our mailing list for updates.
For any questions, please contact Yogesh Rawat [email@example.com] and
Vibhav Vineet [Vibhav.Vineet@microsoft.com].