TA1.L6: Training and Supervision Strategies for Image & Video Data - III
Tue, 29 Oct, 08:30 - 10:00 Gulf Standard Time (UTC +4)
Location: Capital Suite - 18
Session Type: Lecture
Session Chair: Jumana Abu-Khalaf, Edith Cowan University
Track: Visual Artificial Intelligence
Click the to view the manuscript on IEEE Xplore Open Preview
Tue, 29 Oct, 08:30 - 08:48 Gulf Standard Time (UTC +4)
 

TA1.L6.1: SEMANTIC ENHANCED FEW-SHOT OBJECT DETECTION
Zheng Wang, Yingjie Gao, Qingjie Liu, Yunhong Wang, State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing, China, China
Tue, 29 Oct, 08:48 - 09:06 Gulf Standard Time (UTC +4)
 

TA1.L6.2: Segment Any Object Model (SAOM): Real-to-Simulation Fine-Tuning Strategy for Multi-Class Multi-Instance Segmentation
Mariia Khan, Edith Cowan University, Australia; Yue Qiu, University of Tsukuba, Japan; Yuren Cong, Bodo Rosenhahn, Leibniz University of Hannover, Germany; Jumana Abu-Khalaf, David Suter, Edith Cowan University, Australia
Tue, 29 Oct, 09:06 - 09:24 Gulf Standard Time (UTC +4)
 

TA1.L6.3: ACCELERATING CASCADE CLASSIFIER TRAINING WITH GENETIC ALGORITHMS FOR EDGE ML APPLICATIONS
Abhishek Saini, Sajjad Moazeni, University of Washington, United States of America
Tue, 29 Oct, 09:24 - 09:42 Gulf Standard Time (UTC +4)
 

TA1.L6.4: SCENE GENERALIZED MULTI-VIEW PEDESTRIAN DETECTION WITH ROTATION-BASED AUGMENTATION AND REGULARIZATION
Satoshi Suzuki, Shotaro Tora, Ryo Masumura, NTT Corporation, Japan
Tue, 29 Oct, 09:42 - 10:00 Gulf Standard Time (UTC +4)
 

TA1.L6.5: LERCPOSE: LEARNED RANKING AND CONTRASTIVE LOSS FOR ROBUST HEAD POSE ESTIMATION
Aratrik Chattopadhyay, Harshita Soni, Mercedes-Benz Research and Development India Private Limited, India; Dr. Shuaib Ahmed, Mercedes-Benz Research and Development Private Limited, India