TP8a: Speech, Image, and Video Processing
Tue, 27 Oct, 13:30 - 15:10 PT (UTC -7)
Location: Merrill Hall
Session Type: Poster
Track: Speech, Image and Video Processing

TP8a.1: CHASM : Cross-Scanner Image Harmonization via Approximate Schrödinger Matching

Samarth Singh, Scott Acton, University of Virginia, United States

TP8a.2: A Multiresolution Approach to Accelerating Iterative Deep Generative Models

Michael McCann, Brendt Wohlberg, Cristina Garcia-Cardona, Los Alamos National Laboratory, United States

TP8a.3: MV-SA-CLIP: A Stage-Wise Hybrid Vision Encoder for Cross-Modal Retrieval and Zero-Shot Classification

Ambarish Parthasarathy, Sumohana Channappayya, Indian Institute of Technology, Hyderabad, India

TP8a.4: Multi-Modal Speaker Classification in Educational Settings

Nitya Khamar, Chongyu He, Jonathan McGee, Peter Youngs, Scott Acton, University of Virginia, United States

TP8a.5: Lightweight Contrastive Adaptation of EO Foundation Models for Cross-Modal Classification

Stefanos Koutoupis, Michaela Areti Zervou, Panagiotis Tsakalides, Grigorios Tsagkatakis, University of Crete; Foundation for Research and Technology - Hellas, Greece

TP8a.6: Beyond Random: Learned Image Masking Policies

Jonathan McGee, Scott T. Acton, University of Virginia, United States

TP8a.7: Deep Pseudo-Proximal Map: A Self-Supervised Data-Fitting Agent for Iterative Reconstruction

Haley Duba-Sullivan, Purdue University, United States; Emma J. Reid, Oak Ridge National Laboratory, United States; Charles A. Bouman, Gregery T. Buzzard, Purdue University, United States

TP8a.8: Layout-Aware Sparse Phase Retrieval for Ptychographic Mask Inspection

Aleix Boquet-Pujadas, Benjamín Béjar Haro, Swiss Data Science Center Hub at Paul Scherrer Institute, Switzerland

TP8a.9: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models

Yangyue Wang, Harshvardhan Sikka, Fig, United States; Yash Mathur, Tony Zhou, Jinu Nyachhyon, Manifold Research Group, United States; Pranav Guruprasad, Fig, United States

TP8a.10: Skinclusive AI: Towards Equitable Skin Cancer Detection for Deployment on Edge Devices

Joseph Galicinao, Jane Zhang, California Polytechnic State University, San Luis Obispo, United States

TP8a.11: Necessary Information Measure for Neural Reconstruction of Radiance Fields

Tiyasa Sarkar, Flip Phillips, Rochester Institute of Technology, United States

TP8a.12: Detection of Adversarial Attacks on Super-Resolvers Using Spectral Features

Emma J. Reid, Haley Duba-Sullivan, Oak Ridge National Laboratory, United States

TP8a.13: Multimodal Fusion Model for Action Segmentation in Suturing Datase

PrasanthSai Gouripeddi, Nupur Thakur, Baoxin Li, Arizona State University, United States; Hannah Eherenfeldt, Benjamin Knapp, ReSuture, United States

TP8a.14: Visual Consensus: Toward Using Visual Perception in Point Cloud Registration

Amit Efraim, Sami-Shamoon College of Engineering, Israel

TP8a.15: FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder

Dan Jacobellis, Neeraja J. Yadwadkar, University of Texas at Austin, United States

TP8a.16: SplatStream: Fine Granular Scalable Gaussian Splatting for Adaptive 3D Scene Streaming

Muhammad Talha, University of Missouri-Kansas City, United States; William Gordon, BASIS Independent Silicon Valley, United States; Sajid Umair, Zhu Li, University of Missouri-Kansas City, United States; Anique Akhtar, Joel Jung, Qualcomm, Inc., United States

TP8a.17: Fixed Pattern Noise Removal Using a Physics-Inspired CycleGAN

Benjamin Marty, William Guicquero, Laurent Dussopt, CEA-Leti, France

TP8a.18: GTNet: An Efficient GAN-Transformer Pair for AV1 In-loop Super-resolution and Restoration

Yuming Han, Zixiang Xiong, Texas A&M University, United States; Anders Host-Madsen, University of Hawaii at Manoa, United States

TP8a.19: Leveraging Graph Neural Networks for Robust Dynamic Sound Source Tracking

Priyadarshini Dwivedi, Muskan -, Indian Institute of Technology Kanpur, India; Gyanajyoti Routray, SRM University AP Amaravati, India; Rajesh M. Hegde, Indian Institute of Technology Kanpur, India

TP8a.20: Adversarial Masking Approach for Robust Target Source Localization in the SH Domain

Gyanajyoti Routray, SRM University AP Amaravati, India; Priyadarshini Dwivedi, Indian Institute of Technology Kanpur, India; Rahul Peter, BITS Pilani, India; Rajesh M. Hegde, Indian Institute of Technology Kanpur, India

TP8a.21: ASR-Style Transcript Normalization Removes Useful Pragmatic Signal for Dialogue Act Classification

Lucky Onyekwelu-Udoka, Shafiqul Islam, Iowa State University, United States

TP8a.22: Listener-Aware Speech Representations for Hearing-Aid Applications

Sarthak Mangla, Afagh Farhadi, Michael Heinz, Purdue University, United States

TP8a.23: MULTISpoof: A Multilingual Dataset for Cross-Lingual Synthetic Speech Detection

Maria Risques, Kratika Bhagtani, Amit Kumar Singh Yadav, Edward J. Delp, Purdue University, Spain