ACCEPTED PAPERS

Full papers

• Oral presentations

NExNet Seg: Neuron Expansion Network for Medical Image Segmentation. Abel Reyes-Angulo (Michigan Technological University)*; Sidike Paheding (Fairfield University)

Slot Attention-based Feature Filtering for Few-Shot Learning. Javier Ródenas Cumplido (Universitat de Barcelona)*; Petia Radeva (Universitat de Barcelona); Eduardo Aguilar (Universitat de Barcelona)

Scaling laws in zero-shot gender classification using CLIP. Lucas Ceschini (Federal University of Rio Grande do Sul)*; Gabriel Ramos (Universidade do Vale do Rio dos Sinos); Claudio Jung (Federal University of Rio Grande do Sul)

• Posters

HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detection. Esteban Rivera (TUMünchen)*; Surya Prabhakaran (TUMünchen); Markus Lienkamp (TUMünchen)

Emotions in LatAm: A new dataset and benchmark for emotion recognition in Latin America. Pooja Kishore Kumar (University of Twente); Willams Costa (Voxar Labs)*; Renato Nogueira Ferraz e Oliveira (Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco); Veronica Teichrieb (Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco); Estefania Talavera Martinez (University of Twente)

Towards Faster and More Compact Foundation Models for Molecular Property Prediction. Yasir Ghunaim (KAUST)*; Andrés Villa (KAUST); Gergo Ignacz (KAUST); Gyorgy Szekely (KAUST); Motasem Alfarra (KAUST); Bernard Ghanem (KAUST)

Enhancing Vision Transformer Explainability Using Artificial Astrocytes. Nicolas Echevarrieta-Catalan (University of Miami); Ana Ribas-Rodriguez (Universidade da Coruna); Francisco Cedron (Universidade da Coruna); Odelia Schwartz (University of Miami); Vanessa Aguiar-Pulido (University of Miami)*

PineSORT: A Simple Online Real-time Tracking Framework for Drone Videos in Agriculture. Danny Xie-Li (Instituto Tecnológico de Costa Rica); Fabian Fallas-Moya (Universidad de Costa Rica)*

Dream-box: Object-wise Outlier Generation for Out-of-Distribution Detection. Brian Isaac Medina (Durham University)*; Toby Breckon (Durham University)

Extended abstracts

• Posters

GauCho: Gaussian Distributions with Cholesky Decomposition for Oriented Object Detection. José Henrique Marques (Federal University of Rio Grande do Sul)*; Jeffri Murrugarra Llerena (Stony Brook University); Cláudio Jung (Federal University of Rio Grande do Sul)

NamedCurves: Learned Image Enhancement via Color Naming. David Serrano-Lozano (Computer Vision Center)*; Luis Herranz (Universidad Autónoma de Madrid); Michael S. Brown (York University); Javier Vazquez-Corral (Computer Vision Center)

Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise. Brayan Monroy (Universidad Industrial de Santander)*; Jorge Bacca (Universidad Industrial de Santander); Julián Tachella (CNRS, ENS de Lyon)

CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment. Edson Araujo (Goethe University Frankfurt)*; Andrew Rouditchenko (MIT); Yuan Gong (MIT); Saurabhchand Bhati (MIT); Samuel Thomas (IBM Research); Brian Kingsbury (IBM Research); Leonid Karlinsky (IBM Research); Rogerio Feris (IBM Research); James R. Glass (MIT); Hilde Kuehne (University of Tübingen)

NFL-BA: Improving Endoscopic SLAM with Near-Field Light Bundle Adjustment. Andrea Dunn Beltran (UNC)*; Roni Sengupta (UNC)

Prototype-Augmented Hypernetworks for Continual Learning. Neil De La Fuente (Computer Vision Center; Autonomous University of Barcelona); Maria Pilligua (Computer Vision Centre)*; Daniel Vidal Guerra (Computer Vision Center; Autonomous University of Barcelona); Albin Soutif (Computer Vision Center); Andrey Barsky (Computer Vision Center; Autonomous University of Barcelona)

DHiSS: A New OCR Dataset for Document Text Recognition in Historical Documents from the Chilean Dictatorship. Cristobal Vasquez Rosel (Pontificia Universidad Catolica de Chile)*; Luis Miranda (Pontificia Universidad Catolica de Chile); Darwin Sanhueza ( Pontificia Universidad Catolica de Chile); Jocelyn Dunstan (Pontificia Universidad Catolica de Chile); Domingo Mery ( Pontificia Universidad Catolica de Chile)

Interpretable CNN-Based Classification of Tauopathies from NFTs in Immunofluorescence Microscopy. Jesus Dassaef López-Barrios (Tecnologico de Monterrey)*; Miguel Angel Ontiveros-Torres (Tecnologico de Monterrey); Jose Antonio Cantoral-Ceballos (Tecnologico de Monterrey); José Luna-Muñoz (Universidad Politécnica de Pachuca)

HyperNVD: Accelerating Neural Video Decomposition via Hypernetworks. Maria Pilligua (Computer Vision Centre)*; Danna Xue (Autonomous University of Barcelona;Computer Vision Center); Javier Vazquez-Corral (Autonomous University of Barcelona;Computer Vision Center)

Beyond Blanket Masking: Examining Granularity for Privacy Protection in Images Captured by Blind and Low Vision Users. Jeffri Murrugarra Llerena (Stony Brook University)*; Haoran Niu (University of Texas at Austin); Suzanne Barber (University of Texas at Austin); Hal Daumé III (University of Maryland, College Park); Yang Trista Cao (University of Texas at Austin); Paola Cascante-Bonilla (State University of New York at Stony Brook)

Leveraging Visual Embeddings from Instagram for Credit Scoring of Informal Microbusinesses in Latin America. Omar Gonzales (Quipu)*; Viviana Siless (Quipu, Universidad Torcuato Di Tella); Michael Moreno (Quipu)

eBIRD: Event-Based Image Reconstruction by a Denoising Diffusion Probabilistic Model Control. Fabian Valderrama (University of O'Higgins); Ignacio Bugueno-Cordova (University of Chile; University of O'Higgins)*; Rodrigo Verschae (University of O'Higgins)

SignAttention: On the Explainability of Transformer Models for Sign Language Translation. Oscar Stanchi (CONICET)*; Pedro Dal Bianco (III-LIDI); Facundo Quiroga (III-LIDI); Franco Ronchetti (III-LIDI); Enzo Ferrante (LIAA-ICC)

Privacy-preserving Optics for Enhancing Protection in Face De-identification. Jhon Lopez (Universidad Industrial de Santander)*; Carlos Hinojosa (King Abdullah University of Science and Technology)

RAPTOR: Automatic Recognition of Trajectory Patterns from Radar Observation for Maritime Surveillance. Joao Dantas (Institute for Advanced Studies)*; Douglas Honorio (Institute for Advanced Studies); Jelton Cunha (Institute for Advanced Studies); Gabriel Dietzsch (Institute for Advanced Studies)

SignERT: An Efficient Pose-Only Transformer for Sign Language Recognition. Cristian Lazo Quispe (Universidad Nacional de Ingenieria)*; Gissella Bejarano (Marist University)

Deep Learning for Emotion Prediction in Children with Down Syndrome: Integrating Facial and EEG Data in Therapeutic Settings. Jesús Jaime Moreno Escobar (Instituto Poliécnico Nacional (IPN))*; Mauro Daniel Castillo Pérez (Instituto Poliécnico Nacional (IPN)); Erika Yolanda Aguilar del Villar (Instituto Politecnico Nacional, Centro de Investigación en Computación, Laboratorio de Ciencias Cognitivas Computacionales (CsCog))

Structural Image-Based Classification of Loxosceles Phospholipases Using Computer Vision and Transfer Learning. Karla Aguilar (Universidad Técnica de Machala)*