Full-Papers

Oral Presentations

Leveraging Intermediate Features of Vision Transformer for Face Anti-Spoofing 

Mika Feng, Koichi Ito, Takafumi Aoki, Tetsushi Ohki, Masakatsu Nishigaki.

Document Image Rectification using Stable Diffusion Transformer

Pooja Kumari, Sukhendu Das

Knowledge Distillation Approach for SOS Fusion Staging: Towards Fully Automated Skeletal Maturity Assessment

Omid Halimi Milani, Amanda N Nikho, Marouane Tliba, Lauren Mills, Rashid Ansari, Ahmet Enis Cetin, Mohammed Hossameldeen Saad Elnagar

Leveraging Fixed and Dynamic Pseudo-Labels in Cross-Supervision Framework for Semi-Supervised Medical Image Segmentation

Suruchi Kumari, Pravendra Singh

Domain Adaptation for Skin Lesion: Evaluating Real-World Generalisation

Nurjahan Sultana, Wenqi Lu, Xinqi Fan, Moi Hoon Yap

Posters

Enhanced Multi-View Pedestrian Detection Using Probabilistic Occupancy Volume

Reef Alturki, Adrian Hilton, Jean-Yves Guillemaut

Uncertainty-guided Style-aware Perceptual Quality Assessment for AI-Generated Images

Tushar Shinde, Shivaanee Eswaran

LLaVA-SCo: Teach Vision Language Models to Self-Correct

Zixuan Liu, Guangkai Jiang, khajavi siavash

Exploiting Adversarial Learning and Topology Augmentation for Open-Set Visual Recognition

Rosa Zuccarà, Georgia Fargetta, Alessandro Ortis, Sebastiano Battiato

Improved Out-of-Distribution Detection with Additive Angular Margin Loss

Deepak Ravikumar, Efstathia Soufleri, Kaushik Roy

Low-Resource Video Super-Resolution using Memory, Wavelets, and Deformable Convolutions

Kavitha Viswanathan, Amit Sethi, Shashwat Pathak, Piyush Bharambe, Harsh Choudhary

IdolDanceNet:Indian Heritage idol Dance Pose Classification

S Kanimozhi, Sabari Nathan, Sasithradevi A, P Prakash, S Mohamed Mansoor Roomi

Dust to Detail: Restoring Sand-dust Images with Frequency-Guided Attention and Multi-Scale Features

Romala Mishra, Sobhan Dhara

Training Data Reconstruction: Privacy due to Uncertainty?

Christina Runkel, Kanchana Vaishnavi Gandikota, Jonas Geiping, Carola-Bibiane Schönlieb, Michael Moeller

Extended Abstracts

Consistent Amortized Image Clustering via Generative Flow Networks

Irit chelly (Ben Gurion University of the Negev)*; Roy Uziel (Ben Gurion University of the Negev); Oren Freifeld (Ben Gurion University of the Negev); Ari Pakman (Ben Gurion University of the Negev)

A Class- and Data-Agnostic Regularization Strategy for Rehearsal-Based Continual Learning

Lama Alssum (King Abdullah University of Science and Technology)*; Hasan Abed Al Kader Hammoud (King Abdullah University of Science and Technology); Motasem Alfarra (King Abdullah University of Science and Technology); Juan Leon (King Abdullah University of Science and Technology); Bernard Ghanem (King Abdullah University of Science and Technology)

Diffusion Classifiers Understand Compositionality, but Conditions Apply

Yujin Jeong (TU Darmstadt)*; Arnas Uselis (Tübingen AI Center, University of Tübingen); Seong Joon Oh (Tübingen AI Center, University of Tübingen); Anna Rohrbach (TU Darmstadt, hessian.AI)

SKULPT Yourself: A Data-Driven Facial Reconstruction Pipeline

Maida Aizaz (KAIST)*; Khadija Rajabova (KAIST); Seon Gyeom Kim (KAIST); Won Joon Lee (NFS Korea); Joon Yeol Ryu (NFS Korea); Hyobong Jang (NFS Korea); Soojung Park (NFS Korea); Kiwan Jeon (NIMS); Hyoung Suk Park (NIMS); Sung Ho Kang (NIMS); Tak Yeon Lee (KAIST)

Explainable AI for Enhancing Image Transformations in Cellular Neural Networks

Georgia Fargetta (University of Catania)*; Francesco Rundo (University of Catania); Sebastiano Battiato (University of Catania)

DN-CBM: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery

Sukrut Rao (Max Planck Institute for Informatics); Sweta Mahajan (MPI for Informatics)*; Moritz Böhle (Kyutai); Bernt Schiele (Max Planck Institute for Informatics )

Emuru: An Autoregressive Paradigm for Generalizable Text Image Generation

Vittorio Pippi (University of Modena and Reggio Emilia); Fabio Quattrini (University of Modena and Reggio Emilia); Silvia Cascianelli (Università di Modena e Reggio Emilia)*; Alessio Tonioni (Google); Rita Cucchiara (University of Modena and Reggio Emilia)

Generative Video Editing: From unconfident to confident

Kseniia Buzko (University of Waterloo)*; David Clausi (University of Waterloo); Yuhao Chen (University of Waterloo)

Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval

Davide Caffagni (University of Modena and Reggio Emilia); Sara Sarto (University of Modena and Reggio Emilia)*; Marcella Cornia (University of Modena and Reggio Emilia); Lorenzo Baraldi ( University of Modena and Reggio Emilia); Rita Cucchiara (University of Modena and Reggio Emilia)

Robust Training for Sinusoidal Neural Networks

Diana Aldana Moreno (Instituto de Matematica Pura e Aplicada)*; Andre Araujo (Google DeepMind); Luiz Velho (IMPA); Tiago Novello (IMPA)

The Deepfake Doctor: Diagnosing and Treating Audio-Video Fake Detection

Carlotta Segna (TU Darmstadt)*; Marcel Klemt (TU Darmstadt); Anna Rohrbach (TU Darmstadt)

Towards Controlling HTG Style with Latent Diffusion Models

Konstantina Nikolaidou (Luleå University of Technology)*

Knowledge-Tracing Machine Unlearning For Large Vision-Language Models

Yuwen Tan (Boston University); Boqing Gong (Boston University)*

VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment

Darshana Saravanan (IIIT Hyderabad)*; Varun Gupta (IIIT Hyderabad); Darshan Singh (IIIT Hyderabad); Zeeshan Khan (Inria, Paris); Vineet Gandhi (IIIT Hyderabad); Makarand Tapaswi (IIIT Hyderabad)

RoadSocial: A Diverse VideoQA Dataset and Benchmark for Road Event Understanding from Social Video Narratives

Deepti Rawat (International Institute of Information Technology)*

HAIKYU: Hockey Action Identification and Keypose Understanding

Kseniia Buzko (University of Waterloo)*; David Clausi (University of Waterloo); Yuhao Chen (University of Waterloo)

Unmasking Evaluation Artifacts: Rethinking Gender Bias Metrics in Vision-Language Retrieval

Sadie Askari (Indiana University)*; David Crandall (Indiana University)

3D-WAG: Wavelet-Guided Autoregressive Generation for 3D Shapes

Tejaswini Medi (University of Mannheim)*; Arianna Rampini (Autodesk); Pradyumna Reddy (Autodesk); Pradeep Kumar Jayaraman (Autodesk); Margret Keuper (University of Mannheim)

A Distractor-Aware Memory for Visual Object Tracking with SAM2

Jovana Videnović (University of Ljubljana)*; Alan Lukežič (University of Ljubljana ); Matej Kristan (University of Ljubljana )

PRISM-FL: Privacy-preserving Image Synthesis Mechanism for Federated Learning

Efstathia Soufleri (Purdue University)*

ReKon3D: Relation-Knowledge Aware Multi-Modal Embedding and Contrastive GAN for Zero-Shot 3D Recognition

Sejuti Rahman (University of Dhaka)*

How many classes do we need to see for novel class discovery?

Akanksha Sarkar (Cornell University)*; Been Kim (Google Deepmind); Jennifer Sun (Cornell University)

L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformers

Sofia Casarin (Free University Of Bozen-Bolzano)*

Beyond STE: A Curriculum-Driven Backpropagation Method for Quantization-Aware Training

Kaiqi Zhao (Arizona State University)*

HD-VILA-Caption: A Diverse Video-Text Dataset Derived from ASR Narrations

Maheen Saleh (MPI-Informatics Saarbrucken)*; Nina Shvetsova (Goethe University Frankfurt); Anna Kukleva (MPI-Informatics Saarbrucken); Hilde Kuehne (Goethe University Frankfurt); Bernt Schiele (MPI-Informatics Saarbrucken)

Parallel ViT-Based Lung Severity Quantification from CXRs and CT Scans

Bouthaina Slika (University of the Basque Country)*; Fadi Dornaika (IKERBASQUE, Basque Foundation for Science); Karim Hammoudi (Department of Computer Science, IRIMAS, Université de Haute-Alsace)

Local Learning in Low-Rank Space: A Feedback Alignment Perspective

Arani Roy (Purdue University)*; Kaushik Roy (Purdue University)

Multimodal Selective State Space Learning for Efficient Action Quality Assessment

Yaoxin Li (University of Waterloo)*; Alexander Wong (University of Waterloo)

Network Inversion for Uncertainty-Aware Out-of-Distribution Detection

Pirzada Suhail (IIT Bombay)*; Rehna Afroz (IIT Bombay); Amit Sethi (IIT Bombay)

DeepTextile: Open Dataset for Textile Recycling via Machine Learning and Near Infrared Spectroscopy

Danika Gupta (The Harker Upper School)*

Towards AI-Driven Adaptive Lab Evolution: Fine Tuning Protein Language Models for Mutational Effects

Silba Dowell (University of Wyoming)*; Shivanand Sheshappanavar (University of Wyoming)

Beyond Vision: Language-Guided Unsupervised Learning for Robust Semantic Segmentation Across Domains

Chang Liu (University of Waterloo)*

TLPath: Leveraging the Digital Pathology Foundational model for Telomere Length Prediction

Anamika Yadav (Sanford Burnham Prebys Medical Discovery Institute)*; Kyle Alvarez (Sanford Burnham Prebys Medical Discovery Institute ); Akanimoh Adeleye (Sanford Burnham Prebys Medical Discovery Institute ); Sanju Sinha (Sanford Burnham Prebys Medical Discovery Institute )

Shortcut Learning Susceptibility in Vision Classifiers

Pirzada Suhail (IIT Bombay)*; Vrinda Goel (IIT Bombay); Amit Sethi (IIT Bombay)

Lighting the Way: NFL-BA for Robust Endoscopic SLAM

Andrea Dunn Beltran (UNC)*; Roni Sengupta (UNC)

Hyperbolic Safety-Aware Vision-Language Models

Tobia Poppi (University of Modena and Reggio Emilia); Tejaswi Kasarla (University of Amsterdam)*; Pascal Mettes (University of Amsterdam); Lorenzo Baraldi (University of Modena and Reggio Emilia); Rita Cucchiara (University of Modena and Reggio Emilia)