Program

24th October 2022 - 10:15-18:00 (IDT - UTC+3) (with lunch and coffee breaks)

Time (IDT) Event Speaker/Presentation
10:15-10:30 Welcome
10:30-11:00 Session I Deep Multi-modal Representation Schemes for Federated 3D Human Action Recognition - Athanasios Psaltis*; Charalampos Z Patrikakis; Petros Daras
Spatio-Temporal Attention for Cloth-Changing ReID in Videos - Vaibhav Bansal*; Christian Micheloni; Gian Luca Foresti; Niki Martinel
CounTr: A Novel End-to-End Transformer Approach for Crowd Counting and Density Estimation - Haoyue Bai*; Hao He; Zhuoxuan Peng; Tianyuan Dai; S.-H. Gary Chan
11:00-11:30 Session II On the Design of Privacy-Aware Cameras: A Study on Deep Neural Networks - Marcela Carvalho*; Oussama Ennafii; Sylvain Chateau; Samy Ait Bachir
RelMobNet: End-to-end relative camera pose estimation using a robust two-stage training - Praveen Kumar Rajendran*; Sumit Mishra; Luiz Felipe Vecchietti; Dongsoo Har
Cross-Camera View-Overlap Recognition - Alessio Xompero*; Andrea Cavallaro
11:30-12:30 Invited Talk 1
12:30-14:00 Lunch Break
14:00-14:40 Session III Activity Monitoring Made Easier by Smart 360-Degree Cameras - Liliana Lo Presti*; Giuseppe Mazzola; Marco La Cascia
Seeing Objects in Dark with Continual Contrastive Learning - Ujjal Kr Dutta*
Towards Energy-Efficient Hyperspectral Image Processing inside Camera Pixels - Gourav Datta*; Zihan Yin; Ajey Jacob; Akhilesh Jaiswal; Peter A. Beerel
Identifying Auxiliary or Adversarial Tasks Using Necessary Condition Analysis for Adversarial Multi-task Video Understanding - Stephen Su*; Samuel Kwong; Qingyu Zhao; De-An Huang; Juan Carlos Niebles; Ehsan Adeli
14.40-15.00 Coffee Break
15.00-16.00 Invited Talk 2 Haojin Yang from Hasso-Plattner-Institut-Applied Edge AI: Towards Efficient Deep Model Design and Multi-Edge Inference
16.00-16.15 Coffee Break
16.15-17.15 Invited Talk 3 Dima Damen from University of Bristol-Opportunities in Wearable (Egocentric) Computer Vision
17.15-18.00 Demo Session from Companies Patrik Schmuck from Magic Leap