Oral Presentations

LightNet:  Generative Model for Enhancement of Low-Light Images

Desai, Chaitra D; Akalwadi, Nikhil; Joshi, Amogh Mukund; Malagi, Sampada M; Mandi, Chinmayee P; Tabib, Ramesh  Ashok; Patil, Ujwala; Mudenagudi, Uma

Embedded Deformation-based Compression for Human 3D Dynamic Meshes with Changing Topology

Hoang, Huong; Chen, Kunyao; Nguyen, Truong; Cosman , Pamela

Full Papers

SynDrone – Multi-modal UAV Dataset for Urban Scenarios

Rizzoli, Giulia; Barbato, Francesco; Caligiuri, Matteo; Zanuttigh, Pietro

Do Planar Constraints Improve Camera Pose Estimation in Monocular SLAM?

Arndt, Charlotte; Sabzevari, Reza; Civera, Javier

Domain Adversarial Learning Towards Underwater Image Enhancement

Kapoor, Meghna; Baghel, Rohan; Subudhi, Badri N; Jakhetiya, Vinit; Bansal, Ankur

Window-based Model Averaging Improves Generalization in Heterogeneous Federated Learning

Caldarola, Debora; Caputo, Barbara; Ciccone, Marco

TP-NoDe: Topology-aware Progressive Noising and Denoising  of Point Clouds towards Upsampling

Kumbar, Akash; Anvekar, Tejas; Vikrama, Tulasi Amitha; Tabib, Ramesh  Ashok; Mudenagudi, Uma

Extended Abstracts

Action Anticipation with Goal Consistency

Zatsarynna, Olga; Gall, Jurgen

Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer

Izzo, Elena; Camporese, Guglielmo; Ziliotto, Filippo; Parolari, Luca; Ballan, Lamberto

Parametric Loss-Based Super-Resolution for Scene Text Recognition

Viriyavisuthisakul, Supatta; Sanguansat, Parinya; Racharak, Teeradaj; Minh, Nguyen Le; Kaothanthong, Natsuda; Haruechaiyasak, Choochart; Yamasaki, Toshihiko

Tailoring Convolutional Neural Networks to Embedded Processors with Varying Processing Capabilities

Harkati, Chiraz Rayene; Bahl, Gaetan

Assessing robustness and generalization of a deep neural network for brain MS lesion segmentation on real-world data

Chaves, Hernan; Serra, Maria M.; Shalom, DIego; Anania, Pilar; Rueda, Fernanda; Osa Sanz, Emilia ; Stefanoff, Nadia Ivanna; Rodriguez Murua, Sofia; Costa, Martin E.; Kitamura, Felipe C; Yañez, Paulina; Cejas, Claudia; Correale, Jorge; Ferrante, Enzo; Fernandez Slezak, Diego; Farez, Mauricio F.

Light Field Coding with Hybrid Multiplicative and Fourier Disparity Layers for Autostereoscopic Displays

Ravishankar, Joshitha

Leverage Generative Art for Content-Style Disentanglement

Wu, Yankun; Nakashima, Yuta; Garcia, Noa

NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models

Tai, Chi-en A; Li, Jason; Kumar, Sriram; Nair, Saeejith; Chen, Yuhao; XI, PENGCHENG; Wong, Alexander

Learning Situation Hyper-Graphs for Video Question Answering

Urooj, Aisha; Kuehne, Hilde; Wu, Bo; Chheu, Kim; Bousselham, Walid; Gan, Chuang; da Vitoria Lobo, Niels; Shah, Mubarak

Convolution kernel adaptation to calibrated fisheye

Santos-Villafranca, Maria; Berenguel-Baeta, Bruno; Bermudez-Cameo, Jesus; Perez Yus, Alejandro; Guerrero, Josechu

Prototype Learning for Explainable Regression

Hesse, Linde S.; Dinsdale, Nicola K; Namburete, Ana Ineyda L

SFHarmony: Source Free Domain Adaptation for Distributed Neuroimaging Analysis

Dinsdale, Nicola K; Jenkinson, Mark ; Namburete, Ana Ineyda L

Tyche: Stochastic In-Context Learning Model for Medical Image Segmentation

Rakic, Marianne; Gonzalez Ortiz, Jose Javier; Wong, Hallee E; Guttag, John; Dalca, Adrian V

To trust or not to trust: Assessing calibration error under covariate shift without labels

Popordanoska, Teodora; Tiulpin, Aleksei; Blaschko, Matthew B.

With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning

Barraco, Manuele; Sarto, Sara; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita

Sparse Optimal Path in the Latent Space of Variational AutoEncoder by Dynamic Programming

Niu, Xinlei; Walder, Christian; Zhang, Jing; Martin, Charles Patrick

Advancing Fairness with Cross-Domain Learning

Iurada, Leonardo; Bucci, Silvia; Hospedales, Timothy; Tommasi, Tatiana

Reduce, Reuse, Recycle: Modular Multi-Object Navigation

Raychaudhuri, Sonia; Campari, Tommaso; Jain, Unnat; Savva, Manolis; Chang, Angel X

HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities

Biswas, Shristi Das; Kosta, Adarsh K; Liyanagedera , Chamika M; Apolinario, Marco P.; Roy, Kaushik

Efficient, Self-Supervised Human Pose Estimation with Inductive Prior Tuning

Yoo, Nobline; Russakovsky, Olga

VQA Therapy: Exploring Answer Differences by Visually Grounding Answers

Chen, Chongyan; Anjum, Samreen; Gurari, Danna

Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment

Ibrahimi, Sarah; Sun, Xiaohang; Wang, Pichao; Garg, Amanmeet; Sanan, Ashutosh; Omar, Mohamed

Face Recognition, Image Distortions and Biased Predictions

Mittal, Surbhi; Majumdar, Puspita; Singh, Richa; Vatsa, Mayank

Leveraging Synthetic Data for Skin Lesion Analysis

Carrasco Limeros, Sandra; Majchrowska, Sylwia*

Optical flow estimation in real dental scenes without ground truth

Lewandowska, Emilia; Jezierska, Anna; Wesierski, Daniel

Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

Ji, Jie; Li, Gen; Ma, Xiaolong

Learning by Sorting: Self-supervised Learning with Group Ordering Constraints

Shvetsova, Nina; Petersen, Felix; Kukleva, Anna; Schiele, Bernt; Kuehne, Hilde

SLACK: Stable Learning of Augmentations with Cold-start and KL regularization

Marrie, Juliette; Arbel, Michael; Larlus, Diane; Mairal, Julien

Jumping through Local Minima: Quantization in the Loss Landscape  of Vision Transformers

Frumkin, Natalia; Gope, Dibakar; Marculescu, Diana

Enhancing Generalization through Non-I.I.D. Distribution Learning with Federated and Continual Learning

Proietto Salanitri, Federica; Sorrenti, Amelia; Hendrix, Rutger  R; Pennisi, Matteo; Bellitto, Giovanni

Going Beyond Nouns With Vision & Language Models Using Synthetic Data

Cascante-Bonilla, Paola; Shehada, Khaled; Smith, James; Doveh, Sivan; Kim, Donghyun; Panda, Rameswar; Varol, Gul; Oliva, Aude; Ordonez, Vicente; Feris, Rogerio; Karlinsky, Leonid

Maximum Class Separation as Inductive Bias in One Matrix

Kasarla, Tejaswi; Burghouts, Gertjan; van Spengler, Max WF; van der Pol, Elise; Cucchiara, Rita; Mettes, Pascal

Few-Shot styled Handwritten Text Generation of Long-Tail Characters

Pippi, Vittorio; Cascianelli, Silvia; Cucchiara, Rita

SCoRD: Subject-Conditional Relation Detection with Text-Augmented Data

Yang, Ziyan; Kafle, Kushal; Lin, Zhe; Cohen, Scott; Ding, Zhihong; Ordonez, Vicente

LOAD: Local Attribute Debiasing for Pretrained Vision Models

Lee, Seohyeon; Nam, Juhyeon; Kwon, Junseok

Synthetic Medical Image Generation Using Latent Diffusion Models and Large Language Models

Sasikumar, Nevasini NA

Locomotion-Action-Manipulation: Synthesizing Human-Scene Interactions in Complex 3D Environments

Lee, Jiye; Joo, Hanbyul

Attacking Vision Transformers Based Object Detectors via Attentive-PGD Adversarial Perturbation

Jain, Anubhooti; Vatsa, Mayank ; Singh, Richa

VideoSalon: Video-based Hairstyle Transfer

Khwanmuang, Sasikarn; Sangkloy, Patsorn; Suwajanakorn, Supasorn

PFADE: Path Feature Attributions via Debiased Explanations

Choi, Ching Lam; Duplessis, Alexandre