Call for Paper: DeepView Workshop


About
In recent years, there has been great progress in demand for visual surveillance systems and intelligent cities capable of providing accurate traffic measurements and essential information for user-friendly monitoring and real-world applications. Those surveillance systems are generally based on large-scale camera systems consisting of object detection, tracking, re-identification, and human behavior analysis. However, in many emerging applications, there are still severe challenges due to variances of the real-world scenes taken by large-scale multi-view cameras, such as illumination changes, dynamic backgrounds, poor data quality, and the lack of high-quality models. In order to tackle such challenges, many researchers and engineers strive for robust algorithms that can be applied to large-scale surveillance systems. Based on our fundamental knowledge, we want to further boost the performance of the visual surveillance system and make breakthroughs in this area through cooperation with various researchers including you. In this workshop, we seek original contributions reporting the most recent progress on different computer vision methodologies for surveillance analysis of large-scale visual content and its wide applications that will help make smart systems.

The workshop embrace advanced deep learning systems based on real-time large-scale analysis, meanwhile being open to classical physically grounded models and feature engineering, as well as any well-motivated combination of the two streams. We will solicit papers from but not limited to the following topics:

• Robust recognition and detection in the surveillance videos
• Fast large-scale multi-camera multi-object application (detection, tracking, re-identification, and others)
• 2D/3D pose estimation in the surveillance videos
• One/few-shot learning in the unconstrained surveillance scenarios
• Anomaly detection in the surveillance videos
• Human behavior analysis and recognition in the surveillance videos
• Generation of visual data for surveillance analysis system
• Applications and systems for security and safe
• Deep learning techniques for visual surveillance
• Applications of visual surveillance in smart cities
• Safety in surveillance systems
• Data protection in visual surveillance systems
• Adversarial attacks in visual surveillance systems
• Deidentification and Privacy-preserving visual learning


Call for contribution:
We are soliciting high-quality papers covering the topics listed below. Papers should follow the standard AVSS formatting instructions. Paper length should be 4 to 8 pages according to the AVSS format. Details about formatting at https://sites.google.com/view/deepview2022/submission.

Important Dates:
• Submission Deadline: September 23, 2022
• Author Notification: October 14, 2022
• Camera Ready Due: October 21, 2022
• Submission via CMT: https://sites.google.com/view/deepview2022/call-for-papers
• Workshop day: November 29, 2022


Organizers:
• Prof. Moongu Jeon (GIST)
• Dr. Yuseok Bae (ETRI)
• Dr. Kin-Choong Yow (University of Regina)
• Dr. Jinyoung Moon (ETRI)
• Dr. Du Yong Kim (RMIT)
• Dr. Muhammad Aasim Rafique (GIST)
• Yongmin Ko (GIST)