MA2.L6: Training and Supervision Strategies for Image & Video Data - I
Mon, 28 Oct, 10:30 - 12:00 Gulf Standard Time (UTC +4)
Location: Capital Suite - 18
Session Type: Lecture
Session Co-Chairs: Sérgio Manuel de Faria, Instituto Politécnico de Leiria and Ricardo Queiroz, Universidade de Brasilia
Track: Visual Artificial Intelligence
Click the to view the manuscript on IEEE Xplore Open Preview
Mon, 28 Oct, 10:30 - 10:48 Gulf Standard Time (UTC +4)
 

MA2.L6.1: INSTANCE-AWARE UNCERTAINTY FOR ACTIVE LEARNING IN OBJECT DETECTION
Zhipeng Zhang, Wenting Ma, China Mobile Research Institute, China; Xiaohang Yuan, Yuan Hao, China Mobile GBA (Greater Bay Area) Innovation Institute, China; Meng Guo, China Mobile Research Institute, China; Hongyi Tang, China Mobile GBA (Greater Bay Area) Innovation Institute, China; Zhiheng Zhou, South China University of Technology, China; Zhenjie Yao, Chinese Academy of Sciences, China
Mon, 28 Oct, 10:48 - 11:06 Gulf Standard Time (UTC +4)
 Best Paper Candidate

MA2.L6.2: SPATIALITY-AWARE PROMPT TUNING FOR FEW-SHOT SMALL OBJECT DETECTION
Takumi Karasawa, Nakamasa Inoue, Rei Kawakami, Institute of Science Tokyo, Japan
Mon, 28 Oct, 11:06 - 11:24 Gulf Standard Time (UTC +4)
 

MA2.L6.3: DISENTANGLED KNOWLEDGE DISTILLATION FOR UNIFIED MULTI-CLASS ANOMALY DETECTION
Jiyong Jang, Hayeon Lee, Younkwan Lee, Samsung Electronics, Korea, Republic of
Mon, 28 Oct, 11:24 - 11:42 Gulf Standard Time (UTC +4)
 

MA2.L6.4: MMAQ: A Multi-modal Self-supervised Approach For Estimating Air Quality From Remote Sensing Data
Georgios Fotios Angelis, Alexandros Emvoliadis, Anastasios Drosou, Dimitrios Tzovaras, Information and Technologies Institute, Greece
Mon, 28 Oct, 11:42 - 12:00 Gulf Standard Time (UTC +4)
 

MA2.L6.5: CROWDASSIGN: A LABEL ASSIGNMENT SCHEME FOR PEDESTRIAN DETECTION IN CROWDED SCENES
Zihao LI, Shanghai Jiao Tong University, China; Ning LUO, Ningbo Seago Electric Co., Ltd, China; Xiwen ZHANG, Ziliang GUO, Xingqi FANG, Yu QIAO, Shanghai Jiao Tong University, China