Full-Papers

Oral Presentations

AdaMSCoL: Adaptive Multi-Scale Structural Consistency for Unsupervised Underwater Image Enhancement

Aparna Tiwari, Hitika Tiwari, Dong-Lin Li

Beyond Gradients: Curvature-Aware Part-Level Explanations for Vision Models

Maisha Maliha, Dean F. Hougen

Hardware-aware Low Light Image Enhancement on Edge

Sowmya Vajrala, Sravanth Kodavanti, Srinivas Soumitri Miriyala

VIPER: Video-Informed PDE Extraction and Recovery

Farhat Shaikh, Ayan Banerjee, Sandeep Gupta

SAM3Count for Zero-Shot Open Vocabulary Counting in Images and Videos

Joana Konadu Owusu, Shivanand Venkanna Sheshappanavar

Posters

Structured Multivariate Time-Series Modeling for Diffusion-Based EEG-to-Image Reconstruction

Jyoti Nigam, Asmita Ankush Kamble, Arnav Bhavsar

Agentic Causal Disentanglement (ACD) Framework: Reversing the Generalization–Tail Trade-Off via Clinical Knowledge Integration in Medical AI

Midhat Urooj, Ayan Banerjee, Sandeep Gupta

Contrast-Enhanced Gating in GRUs for Robust Low-Data Sequence Learning

Barathi Subramanian, Rathinaraja Jeyaraj, Anand Paul

A Survey of Spatial Memory Representations for Efficient Robot Navigation

Ma. Madecheen S. Pangaliman, Steven S. Sison, Erwin P. Quilloy, Rowel Atienza

Hierarchy Matters: Learning Vision–Language Representations in Hyperbolic Space

Kathy Wu, Sarthak Srivastava

GROVE: Geometry-Aware Optimization for Robust Vision-Language Model

Kathy Wu, Sarthak Srivastava

Extended Abstracts

Invisible Labor in Computer Vision: A Quantitative Study of Gender Disparities in Dataset and Experimental Work

Mahule Roy, Subhas Roy

From Seeing to Believing: Tracing Multimodal Hallucinations to Their Training Data Origins

Yixu Huang

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde

Adaptive Confidence Regularization for Multimodal Failure Detection

Moru Liu, Hao Dong, Olga Fink, Mario Trapp

pFedDGA: Personalized Federated Domain Generalization via Decoupled Representation and Generalization-Aware Aggregation

Anamta Khan, Monu Verma, Mohamed Saeed Abdel-Mottaleb

MCMA-Net for Clinical Glioma Segmentation: Zero-Shot Transfer of a BraTS-Pretrained Model to Bimodal Hospital Data with Expert Radiologist Validation

Jihan Alameddine, Brahim BORNI, Céline THOMARAT, Christine Fernandez-Maloigne, Remy Guillevin, Carole Guillevin

BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection

Melissa Schween, Mathis Kruse, Bodo Rosenhahn

MUFASA: A Multi-Layer Framework for Slot Attention

Leonie Schüßler, Sebastian Bock, Krishnakant Singh, Simone Schaub-Meyer, Stefan Roth

An Integrated Data-Driven Scheme for Dynamic Light Field Representation and Coding via Dynamic Mode Decomposition

Joshitha R

RoadTones: Tone Controllable Text Generation from Road Event Videos

Siddhi Pravin Lipare, Chirag Parikh, Ravi Kiran Sarvadevabhatla

AdaCRAD: Adaptive Compression via Representation-Aware Drift for Ranking Preservation in AIGC-IQA

Tushar Shinde, Sreejita Roy

AViON4D: Audio-Visual Open-Vocabulary 4D Egocentric Scene Understanding

Irene Ballester, Pedro Hermosilla, Wei Lin, James R. Glass, Muhammad Jehanzeb Mirza, Martin Kampel

Causal Discovery of Biomechanical Dependencies for Auxiliary Supervision in Locomotion Forecasting

Hui-Yun Deng, Chia-Yun Chiang, Yen-Chen Chen, Yu-Hui Huang

PhysHead: Simulation-Ready Gaussian Head Avatars

Berna Kabadayi, Vanessa Sklyarova, Wojciech Zielonka, Justus Thies, Gerard Pons-Moll

A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations

Neelu Madan, Àlex Pujol Vidal, Andreas Møgelmose, Sergio Escalera, Kamal Nasrollahi, Graham W. Taylor, Thomas B. Moeslund

Model-Agnostic, Training-Free Discovery of Semantic Directions for Text-to-Image Editing

Ritika Allada, Pinar Yanardag

Spectral-Faithful HSI Dehazing via Physics-Aware Wavelength-Adaptive Loss

Jungeun Park, Sungho Kim

ZCFD: A Depth-Aware Global Context and Hallucination Metric for Object Removal

Yoojeong Lee, Kibeom Hong

TexTAR : Textual Attribute Recognition in Multi-domain and Multi-lingual Document Images

Jyothi Swaroopa Jinka

Addressing Data Scarcity in Depth-Based Human Action Recognition via Zero-Shot Depth Estimation

Rebeka Angyal, Pedro Hermosilla, Martin Kampel, Irene Ballester

Hoi! - A Multimodal Dataset for Force-Grounded, Cross-View Articulated Manipulation

Tim Engelbracht, René Zurbrügg, Matteo Wohlrapp, Martin Büchner, Abhinav Valada, Marc Pollefeys, Hermann Blum, Zuria Bauer

The Nonverbal Blind Spot: A Computer Vision Research Agenda for Safer Online Dating

Ratna Kandala, Niva Manchanda, Akshata Kishore Moharir

Real-Time Detection Transformer (RT-DETR) for Instance-Level Malaria Parasite Detection Across Thick and Thin Blood Smears

Martha Kachweka, Carine Mukamakuza, kevin Harerimana, Gabriel Anyaele

Improved Vision-Language Alignment via Text-Conditioned Image Embeddings using Sparse Autoencoders

Sweta Mahajan, Sukrut Rao, Jiahao Xie, Alexander Koller, Bernt Schiele

PRISM-CAFO: Prior-conditioned Remote-sensing Infrastructure Segmentation and Mapping for CAFOs

Oishee Bintey Hoque

Continual Learning Via Constrained Stochastic Optimization: A Drift Plus Penalty Framework

Nazreen Shah, Govinda Arya, Bharath B N, Ranjitha Prasad

Learning What To Ask For When: Image Ordering for In-Context Interactive Medical Image Segmentation

Gianna Torpey, John Guttag, Hallee E. Wong

Hallucination Mitigation for Large Vision Language Models via Implicit Feature Stabilization and Hierarchical Alignment Optimization

Aditi Sarker, Prashant Khanduri

How Well Do Vision Foundation Models See Underwater? Benchmarking Pretrained Backbones on SUIM

Yuechun Wei

Bio-Kinematic Refinement: Differentiable Screw Theory and Impedance Constraints for Stable 3D Human Pose Estimation

VINDUJA T, ajay waghumbare, Ashish M., Upasna Singh