TU2.PA: Machine Learning in Signal Processing 9
Tue, 16 Sep, 10:00 - 11:30 Anchorage Time (UTC -8)
Location: Poster Area A
Session Type: Poster
Session Chair: Lucio Marcenaro, Università degli Studi di Genova
Track: [ML] Machine Learning in Signal Processing
Click the to view the manuscript on IEEE Xplore Open Preview

TU2.PA.1: JUDGING FROM SUPPORT-SET: A NEW WAY TO UTILIZE FEW-SHOT SEGMENTATION FOR SEGMENTATION REFINEMENT PROCESS
Seonghyeon Moon, Brookhaven National Laboratory, Roblox, United States; Qingze Liu, Haein Kong, Rutgers University, United States; Muhammad Khan, Mohamed Bin Zayed University of Artificial Intelligence, United Arab Emirates

TU2.PA.2: FMG-DET: FOUNDATION MODEL GUIDED ROBUST OBJECT DETECTION
Darryl Hannan, Timothy Doster, Henry Kvinge, Adam Attarian, Yijing Watkins, Pacific Northwest National Laboratory, United States

TU2.PA.3: MULTI-LEVEL AND MULTI-MODAL ACTION ANTICIPATION
Seulgi Kim, Ghazal Kaviani, Mohit Prabhushankar, Ghassan AlRegib, Georgia Institute of Technology, United States

TU2.PA.4: ENACT: ENTROPY-BASED CLUSTERING OF ATTENTION INPUT FOR REDUCING THE COMPUTATIONAL NEEDS OF OBJECT DETECTION TRANSFORMERS
Giorgos Savathrakis, Institute of Computer Science - Foundation for Research and Technology Hellas, Greece; Antonis Argyros, Institute of Computer Science - Foundation for Research and Technology Hellas, University of Crete Department of Computer Science, Greece

TU2.PA.5: Enhancing Autonomous Driving Perception under Complex Weather Conditions through CycleGAN-based Driving Scene Generation
LiTong Liu, Gaoxuan Li, Yaya Huang, Yixuan Dong, Chee Ming Ting, Junn Yong Loo, Monash University, Malaysia

TU2.PA.6: COMPACT LATENT REPRESENTATION FOR IMAGE COMPRESSION (CLRIC)
Ayman A. Ameen, Thomas Richter, Fraunhofer Institute for Integrated Circuits IIS, Germany; André Kaup, Friedrich-Alexander-Universität, Germany

TU2.PA.7: CURVE: CLIP-UTILIZED REINFORCEMENT LEARNING FOR VISUAL IMAGE ENHANCEMENT VIA SIMPLE IMAGE PROCESSING
Yuka Ogino, Takahiro Toizumi, Atsushi Ito, NEC Corporation, Japan

TU2.PA.8: Batch-Aware Active Learning for Object Detection
Mykyta Kovalenko, Peter Eisert, Anna Hilsmann, Sebastian Bosse, Fraunhofer Heinrich-Hertz Institute, Germany

TU2.PA.9: Multi-Teacher Knowledge Distillation for Efficient Object Segmentation
Chengxi Zeng Zeng, Kurt Cutajar, Hanting Xie, Massimo Camplani, Richard Tomsett, Niall Twomey, Jas Kandola, Gavin Cheung, Amazon, United Kingdom

TU2.PA.10: ESwinDNet: Image Demoiréing Using Multiscale Swin Transformer Layers
Karim Alaa, Marwan Torki, Alexandria University, Egypt

TU2.PA.11: RADIUS-ALIGNED TRAINING AND ROTATED IOU METRICS FOR PEDESTRIAN DETECTION IN TOP-VIEW FISHEYE IMAGES
Tsung-Tai Yang, Sheng-Ho Chiang, Tsaipei Wang, National Yang Ming Chiao Tung University, Taiwan

TU2.PA.12: Session Class Prototype Incremental Learning (SCPIL): Mitigating Catastrophic Forgetting with Distance-Based Prototype Learning
Seong Su Kim, Sang Woo Yun, Ill Hwan Kim, Dong Heon Lee, Joon Ki Paik, Chung-Ang University, Korea (South)