TA2.L6: Training and Supervision Strategies for Image & Video Data - IV
Tue, 29 Oct, 10:30 - 12:00 Gulf Standard Time (UTC +4)
Location: Lecture Room 6
Session Type: Lecture
Track: Visual Artificial Intelligence
Click the to view the manuscript on IEEE Xplore Open Preview
Tue, 29 Oct, 10:30 - 10:48 Gulf Standard Time (UTC +4)

TA2.L6.1: SET-NAS: Sample-Efficient Training for Neural Architecture Search with Strong Predictor and Stratified Sampling
Yu-Ming Zhang, National Central University, Taiwan; Jun-Wei Hsieh, National Yang Ming Chiao Tung University, Taiwan; Yu-Hsiu Chang, National Central University, Taiwan; Xin Li, Ming-Ching Chang, University at Albany, China; Chun-Chieh Lee, Kuo-Chin Fan, National Central University, Taiwan
Tue, 29 Oct, 10:48 - 11:06 Gulf Standard Time (UTC +4)

TA2.L6.2: CONTEXTUALITY HELPS REPRESENTATION LEARNING FOR GENERALIZED CATEGORY DISCOVERY
Tingzhang Luo, Mingxuan Du, Jiatao Shi, Xinxiang Chen, China University of Geosciences, China; Bingchen Zhao, University of Edinburgh, China; Shaoguang Huang, China University of Geosciences, China
Tue, 29 Oct, 11:06 - 11:24 Gulf Standard Time (UTC +4)

TA2.L6.3: UIMT: A framework for improving unimodal inference via multimodal training
Kateryna Chumachenko, Tampere University, Finland; Alexandros Iosifidis, Aarhus University, Finland; Moncef Gabbouj, Tampere University, Finland
Tue, 29 Oct, 11:24 - 11:42 Gulf Standard Time (UTC +4)

TA2.L6.4: BOX-LEVEL CLASS-BALANCED SAMPLING FOR ACTIVE OBJECT DETECTION
Jingyi Liao, Xun Xu, Chuan Sheng Foo, Lile Cai, Institute for Infocomm Research (I2R), A*STAR, Singapore
Tue, 29 Oct, 11:42 - 12:00 Gulf Standard Time (UTC +4)

TA2.L6.5: RSUD20K: A Dataset for Road Scene Understanding In Autonomous Driving
Hasib Zunair, Shakib Khan, Abdessamad Ben Hamza, Concordia University, Canada