MLSP-P38: Pattern Recognition and Classification III
Fri, 19 Apr, 13:10 - 15:10 (UTC +9)
Location: Poster Zone 3C
Session Type: Poster
Session Chair: Jian Guan, Harbin Engineering University
Track: Machine Learning for Signal Processing
Click the to view the manuscript on IEEE Xplore Open Preview
 

MLSP-P38.1: CO-SALIENT OBJECT DETECTION VIA DISCRIMINATIVE PROTOTYPES CONTRAST

Junyi Wang, Chengdu Institute of Computer Application, Chinese Academy of Sciences, China; Bin Chen, Harbin Institute of Technology(Shenzhen), China; Wenrui Fan, Chongqing Research Institute, Harbin Institute of Technology, China; Yongjiang Liu, Chengdu Institute of Computer Application, Chinese Academy of Sciences, China
 

MLSP-P38.2: SOD-UAV: small object detection for unmanned aerial vehicle images via improved YOLOv7

Yujie Li, Yifu Wang, Zihang Ma, Xinghe Wang, Yutao Tang, Guilin University of Electronic Technology, China
 

MLSP-P38.3: SELF-KNOWLEDGE DISTILLATION WITH LEARNING FROM ROLE-MODEL SAMPLES

Kai Xu, Lichun Wang, Huiyong Zhang, Baocai Yin, Beijing University of Technology, China
 

MLSP-P38.4: DIFF-HOD: DIFFUSION MODEL FOR OBJECT DETECTION IN HAZY WEATHER CONDITIONS

Yizhan Li, Rongwei Yu, Junjie Shi, Lina Wang, Wuhan University, China
 

MLSP-P38.5: Counting Network for Learning from Majority Label

Kaito Shiku, Shinnosuke Matsuo, Kyushu university, Japan; Daiki Suehiro, Yokohama City University, Japan; Ryoma Bise, Kyushu university, Japan
 

MLSP-P38.7: PROBMCL: SIMPLE PROBABILISTIC CONTRASTIVE LEARNING FOR MULTI-LABEL VISUAL CLASSIFICATION

Ahmad Sajedi, Samir Khaki, Yuri A. Lawryshyn, Konstantinos N. Plataniotis, University of Toronto, Canada
 

MLSP-P38.8: DIFFUSION-BASED POSE REFINEMENT AND MULTI-HYPOTHESIS GENERATION FOR 3D HUMAN POSE ESTIMATION

Hongbo Kang, Yong Wang, Chongqing University Of Technology, China; Mengyuan Liu, Peking University, China; Doudou Wu, Peng Liu, Chongqing University Of Technology, China; Xinlin Yuan, Chongqing University of Technology, China; Wenming Yang, Tsinghua University, China
 

MLSP-P38.9: Towards Multi-domain Face Landmark Detection with Synthetic Data from Diffusion Model

Yuanming Li, Gwantae Kim, Jeonggi Kwak, Bon-hwa Ku, Hanseok Ko, Korea University, China
 

MLSP-P38.10: Test-Time Distribution Learning Adapter For Cross-Modal Visual Reasoning

Yi Zhang, Feng AI Lab, Zhimeifenghua Smart Home, China; Ce Zhang, Carnegie Mellon University, Pittsburgh, United States, United States of America
 

MLSP-P38.11: VISION TRANSFORMER WITH 2D EXPLICIT POSITION ENCODING

Yujie Li, Zihang Ma, Xinghe Wang, Yifu Wang, Benying Tan, Guilin University of Electronic Technology, China

MLSP-P38.12: ON MEASURES OF UNCERTAINTY IN CLASSIFICATION

Saloua Chlaily, Debanshu Ratha, UiT the Arctic University of Norway, Norway; Pigi Lozou, National Technical University of Athens, Norway; Andrea Marinoni, UiT the Arctic University of Norway, Norway