MO2.L11: Generative AI for World Simulations and Communications & Celebrating 40 Years of Excellence in Education: Honoring Professor Aggelos Katsaggelos (I)
Satellite Workshop
Mon, 15 Sep, 10:00 - 11:30 Anchorage Time (UTC -9)
Location: Dena'ina: Tikahtnu Ballroom D/E
Session Type: Lecture
Track: Satellite Workshops
Click the to view the manuscript on IEEE Xplore Open Preview
Mon, 15 Sep, 10:00 - 10:04 Anchorage Time (UTC -9)

MO2.L11.1: Beyond Initial Design: AI Advancement of Portable Ultrasound Technology for Brain Perfusion Imaging
Mark Banham, BURL Concepts, Inc., United States
Mon, 15 Sep, 10:04 - 10:09 Anchorage Time (UTC -9)

MO2.L11.2: J-SGFT: JOINT SPATIAL AND GRAPH FOURIER DOMAIN LEARNING FOR POINT CLOUD ATTRIBUTE DEBLOCKING
Muhammad Talha, Qi Yang, Zhu Li, University of Missouri-Kansas City, United States; Anique Akhtar, Geert Van Der Auwera, Qualcomm Technologies, United States
Mon, 15 Sep, 10:09 - 10:13 Anchorage Time (UTC -9)

MO2.L11.3: PERCEPTUAL REALNESS OF GENERATIVE AUDIO-VISUAL CONTENT
Devi Klein, Anustup Choudhury, Jaclyn Pytlarz, Scott Daly, Dolby Laboratories Inc., United States
Mon, 15 Sep, 10:13 - 10:18 Anchorage Time (UTC -9)

MO2.L11.4: An Optimal Framework for Airport Luggage Stacking Utilizing Graph-based Representation and Optimization
Miaohong Shi, Reconova Technologies Co., Ltd, China
Mon, 15 Sep, 10:18 - 10:22 Anchorage Time (UTC -9)

MO2.L11.5: CONFORMAL PREDICTIONS FOR HUMAN ACTION RECOGNITION WITH VISION-LANGUAGE MODELS
Tim Bary, Clément Fuchs, Benoît Macq, UCLouvain, Belgium
Mon, 15 Sep, 10:22 - 10:27 Anchorage Time (UTC -9)

MO2.L11.6: Image-Difficulty-Aware Evaluation of Super-resolution Models
Atakan Topaloglu, Ahmet Bilican, Cansu Korkmaz, A. Murat Tekalp, Koç University, Turkey
Mon, 15 Sep, 10:27 - 10:31 Anchorage Time (UTC -9)

MO2.L11.7: Pay Attention to Where You Looked
Alex Berian, JhihYang Wu, Daniel Brignac, Natnael Daba, Abhijit Mahalanobis, The University of Arizona, United States
Mon, 15 Sep, 10:31 - 10:36 Anchorage Time (UTC -9)

MO2.L11.8: BUILD-A-VOLCAP: AUTOMATED SYNTHETIC VALIDATION OF REAL-WORLD VOLUMETRIC CAPTURE QUALITY
Antonella Rech, Giulia Martinelli, Nicola Garau, Nicola Conci, Francesco De Natale, University of Trento, Italy, Italy
Mon, 15 Sep, 10:36 - 10:40 Anchorage Time (UTC -9)

MO2.L11.9: EXPERT OPERATIONAL GANS: TOWARDS REAL-COLOR UNDERWATER IMAGE RESTORATION
Ozer Can Devecioglu, Tampere University, Finland; Serkan Kiranyaz, Qatar University, Qatar; Mehmet Yamac, Moncef Gabbouj, Tampere University, Finland
Mon, 15 Sep, 10:40 - 10:45 Anchorage Time (UTC -9)

MO2.L11.10: SD-URM: STABLE-DIFFUSION BASED ZERO-SHOT UNIVERSAL RESTORATION MODEL
Dae Yeol Lee, Shiv Gehlot, Dolby Laboratories, United States; Lijun Zhang, University of Massachusetts Amherst, United States; Guan-Ming Su, Dolby Laboratories, United States
Mon, 15 Sep, 10:45 - 10:49 Anchorage Time (UTC -9)

MO2.L11.11: NOVEL FEATURE PREDICTION USING RESIDUAL NETWORKS FOR PLANAR-DECOMPOSITION BASED DYNAMIC SCENE RADIANCE FIELDS
Bishshoy Das, Dolby Technology India Pvt. Ltd., India; Guan-Ming Su, Dolby Laboratories, United States
Mon, 15 Sep, 10:49 - 10:54 Anchorage Time (UTC -9)

MO2.L11.12: A NOVEL EDGE-AWARE BILATERAL FILTER FOR ANTIALIASING AND DENOISING IN LOW-DOSE CBCT IMAGING
Simin Mirzaei, Hamid Reza Tohidypour, Shahriar Mirabbasi, Panos Nasiopoulos, The University of British Columbia, Canada
Mon, 15 Sep, 10:54 - 10:58 Anchorage Time (UTC -9)

MO2.L11.13: Domain-Adaptive Image Inpainting for Scene Editing in 3D Virtual Environments
Hyeongseok Oh, Chung-Ang University, Korea (South); Jinmo Byeon, Korean Bible University, Korea (South); Joonki Paik, Chung-Ang University, Korea (South)
Mon, 15 Sep, 10:58 - 11:03 Anchorage Time (UTC -9)

MO2.L11.14: THE LIMITS OF LOCAL METRICS: INVESTIGATING THE RELATIONSHIP BETWEEN LOCAL QUANTIZATION ERROR AND TASK LOSS IN DEEP LEARNING VISION MODELS
Ruixiang Chai, Northwestern University, United States; Peng Kang, University of Illinois Springfield, United States
Mon, 15 Sep, 11:03 - 11:07 Anchorage Time (UTC -9)

MO2.L11.15: SEMANTICBOX: BOUNDING BOX-GUIDED CAPTION ENHANCED ACTION RECOGNITION FOR INSTRUCTIONAL VIDEOS
Jonathan McGee, Chongyu He, Peter Youngs, Scott T. Acton, Matthew Korban, University of Virginia, United States
Mon, 15 Sep, 11:07 - 11:12 Anchorage Time (UTC -9)

MO2.L11.16: Generative Face Restoration via Gallery and Physical Identity Cues
Xijun Wang, Xingguang Zhang, Yu Yuan, Bole Ma, Prateek Chennuri, Stanley Chan, Purdue University, United States
Mon, 15 Sep, 11:12 - 11:16 Anchorage Time (UTC -9)

MO2.L11.17: MULTI-PATH MAMBA DIFFUSION FOR 3D POINT CLOUD SEMANTIC SCENE COMPLETION
Li Liang, The University of Western Australia, Australia; Naveed Akhtar, The University of Melbourne, Australia; Jordan Vice, The University of Western Australia, Australia; Anwaar Ulhaq, Central Queensland University, Australia; Ajmal Mian, The University of Western Australia, Australia
Mon, 15 Sep, 11:16 - 11:21 Anchorage Time (UTC -9)

MO2.L11.18: Plug-and-Play Diffusion Models for Inverse Problems with Data Consistency Projection
Xiaodong Wang, Ping Wang, Zhangyuan Li, Yuan Xin, Westlake, China
Mon, 15 Sep, 11:21 - 11:25 Anchorage Time (UTC -9)

MO2.L11.19: VARIATIONAL BAYESIAN DEHAZING WITH ATMOSPHERIC SCATTERING MODEL FOR SYNTHETIC-TO-REAL GENERALIZATION
Stepan Babayan, National Polytechnic University of Armenia, Armenia; Francisco Javier Sáez-Maldonado, Javier Mateos, Rafael Molina, Universidad de Granada, Spain
Mon, 15 Sep, 11:25 - 11:30 Anchorage Time (UTC -9)

MO2.L11.20: PLUG-AND-PLAY DIFFUSION MODELS FOR IMAGE COMPRESSIVE SENSING WITH DATA CONSISTENCY PROJECTION
Xiaodong Wang, Ping Wang, Zhangyuan Li, Xin Yuan, Westlake University, China