MO2.L12: Generative AI for World Simulations and Communications & Celebrating 40 Years of Excellence in Education: Honoring Professor Aggelos Katsaggelos (II)
Satellite Workshop
Mon, 15 Sep, 10:00 - 11:30 Anchorage Time (UTC -9)
Location: Dena'ina: Tikahtnu Ballroom B
Session Type: Lecture
Track: Satellite Workshops
Click the to view the manuscript on IEEE Xplore Open Preview
Mon, 15 Sep, 10:00 - 10:06 Anchorage Time (UTC -9)

MO2.L12.1: WHEN PIGS FLY: EVALUATING SEMANTIC OVERCONFIDENCE IN DEEP NEURAL NETWORK CLASSIFIERS
Panagiotis Dimitrakopoulos, University of Edinburgh, United Kingdom; Paraskevas Pegios, University of Denmark, Denmark; Steven McDonagh, Sotirios A. Tsaftaris, University of Edinburgh, United Kingdom
Mon, 15 Sep, 10:06 - 10:12 Anchorage Time (UTC -9)

MO2.L12.2: Deep Sparse Prior: Enhancing Deblurring Deep Priors with Sparsity Constraints
Francisco M Castro-Macías, Miguel Vega, Rafael Molina, University of Granada, Spain
Mon, 15 Sep, 10:12 - 10:18 Anchorage Time (UTC -9)

MO2.L12.3: A NOVEL IMAGE SIMILARITY METRIC FOR SCENE COMPOSITION STRUCTURE
Md Redwanul Haque, Manzur Murshed, Deakin University, Australia; Manoranjan Paul, Charles Sturt University, Australia; Tsz-Kwan Lee, Deakin University, Australia
Mon, 15 Sep, 10:18 - 10:24 Anchorage Time (UTC -9)

MO2.L12.4: Hallucination-Free Automatic Question & Answer Generation for Intuitive Learning
Nicholas Wang, Stellar Learning Technologies, United States; Aggelos Katsaggelos, Northwestern University, United States
Mon, 15 Sep, 10:24 - 10:30 Anchorage Time (UTC -9)

MO2.L12.5: Diffusion-Based Limited-Angle CT Reconstruction under Noisy Conditions
Jiaqi Guo, Santiago Lopez-Tapia, Northwestern University, United States
Mon, 15 Sep, 10:30 - 10:36 Anchorage Time (UTC -9)

MO2.L12.6: DRL-STNET++: UNCERTAINTY-AWARE SELF-TRAINING FOR CROSS-MODALITY SEGMENTATION WITH GENERATIVE TRANSLATION
Hui Lin, Daniel Kim, Aggelos K. Katsaggelos, Northwestern University, United States
Mon, 15 Sep, 10:36 - 10:42 Anchorage Time (UTC -9)

MO2.L12.7: Cross-Modal Contrastive Learning with Attention for Enhanced Facial Feature Extraction in Multimodal Emotion Recognition
Miaohong Shi, Baozhi Jia, Reconova Technologies Co., Ltd, China
Mon, 15 Sep, 10:42 - 10:48 Anchorage Time (UTC -9)

MO2.L12.8: CAN LOCAL VISION-LANGUAGE MODELS IMPROVE ACTIVITY RECOGNITION OVER VISION TRANSFORMERS? - CASE STUDY ON NEWBORN RESUSCITATION
Enrico Guerriero, Kjersti Engan, Øyvind Meinich-Bache, University of Stavanger, Norway
Mon, 15 Sep, 10:48 - 10:54 Anchorage Time (UTC -9)

MO2.L12.9: GIVE: A MULTI-AGENT FRAMEWORK FOR GENERATING IMMERSIVE MULTI-MODAL VIRTUAL ENVIRONMENTS FOR 3D GAMES
Shantanu Vyas, Texas A&M University, United States; Sandeep Bangalore Venkatesh, Guan-Ming Su, Dolby Laboratories, United States
Mon, 15 Sep, 10:54 - 11:00 Anchorage Time (UTC -9)

MO2.L12.10: CAPTION-DRIVEN EXPLAINABILITY: PROBING CNNS FOR BIAS VIA CLIP
Patrick Koller, Northwestern University, United States; Amil Dravid, University of California, Berkeley, United States; Guido Schuster, Eastern Switzerland University of Applied Sciences, Switzerland; Aggelos Katsaggelos, Northwestern University, United States
Mon, 15 Sep, 11:00 - 11:06 Anchorage Time (UTC -9)

MO2.L12.11: A Composite Sentiment Index for Technology Adoption & Investment
James Brailean, Karmel Capital, United States
Mon, 15 Sep, 11:06 - 11:12 Anchorage Time (UTC -9)

MO2.L12.12: NEURAL REPRESENTATIONS FOR EVENT VOXEL GRID
Tsung-Wei Huang, Anustup Choudhury, Guan-Ming Su, Dolby Laboratories, Inc., United States
Mon, 15 Sep, 11:12 - 11:18 Anchorage Time (UTC -9)

MO2.L12.13: EVALUATING HUMAN-CURATED AND AI-GENERATED AFFECTIVE IMAGES IN THE VALENCE–AROUSAL SPACE USING A MULTIMODAL AI AGENT
Leandros Stefanopoulos, Northwestern University, Greece
Mon, 15 Sep, 11:18 - 11:24 Anchorage Time (UTC -9)

MO2.L12.14: SIZE-INFORMED REPRESENTATIONS FOR UNSUPERVISED IMAGE CLUSTERING
Philipp Srivastava, Charilaos Apostolidis, Saumya Pailwan, Patrick Koller, Leandros Stefanopoulos, Northwestern University, United States
Mon, 15 Sep, 11:24 - 11:30 Anchorage Time (UTC -9)

MO2.L12.15: ADAPTIVE X-RAY FLUORESCENCE IMAGE SAMPLING OF ARTWORKS VIA SELF-SUPERVISED LEARNING
Henry Chopp, Oscar Depp, Northwestern University, United States; Matthias Alfeld, Delft University of Technology, Netherlands; Aggelos Katsaggelos, Northwestern University, United States