AIConfPaper
← Search

Marco Pedersoli

18 accepted papers

2026

BAH Dataset for Ambivalence/Hesitancy Recognition in Videos for Behavioural Change

Manuela González-González, Soufiane Belharbi, Muhammad Osama Zeeshan, Masoumeh Sharafi, Muhammad Haseeb Aslam, Marco Pedersoli +3
ICLR 2026poster

This paper introduces the Behavioral Ambivalence/Hesitancy (BAH) dataset collected for the Ambivalence/Hesitancy (A/H) recognition task in videos. In particular, this task involves recognizing conflicting emotions linked to A/H from question-and-answer videos captured for behavior analysis. The data…

Cited by 0Source ↗code ↗Scholar ↗
2026

Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method

Masoumeh Sharafi, Soufiane Belharbi, Muhammad Osama Zeeshan, HOUSSEM Ben Salem, Ali Etemad, Alessandro Lameiras Koerich +3
ICLR 2026poster

Facial expression recognition (FER) models are employed in many video-based affective computing applications, such as human-computer interaction and healthcare monitoring. However, deep FER models often struggle with subtle expressions and high inter-subject variability, limiting their performance…

Cited by 0Source ↗Scholar ↗
2025

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

Ahmed Masry, Juan A. Rodriguez, Tianyu Zhang, Suyuchen Wang, Chao Wang, Aarash Feizi +16
NeurIPS 2025poster

Aligning visual features with language embeddings is a key challenge in vision-language models (VLMs). The performance of such models hinges on having a good connector that maps visual features generated by a vision encoder to a shared embedding space with the LLM while preserving semantic similarit…

Cited by 0Source ↗Scholar ↗
2025

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

Juan A. Rodriguez, Xiangru Jian, Siba Smarak Panigrahi, Tianyu Zhang, Aarash Feizi, Abhay Puri +33
ICLR 2025poster

Multimodal AI has the potential to significantly enhance document-understanding tasks, such as processing receipts, understanding workflows, extracting data from documents, and summarizing reports. Code generation tasks that require long-structured outputs can also be enhanced by multimodality. Desp…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups

Masih Aminbeidokhti, Subhankar Roy, Eric Granger, Elisa Ricci, Marco Pedersoli
NeurIPS 2025poster

Real-world datasets typically exhibit long-tailed (LT) distributions, where a few head classes dominate and many tail classes are severely underrepresented. While recent work shows that parameter-efficient fine-tuning (PEFT) methods like LoRA and AdaptFormer preserve tail-class performance on founda…

Cited by 0Source ↗Scholar ↗
2025

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

Juan A. Rodriguez, Haotian Zhang, Abhay Puri, Rishav Pramanik, Aarash Feizi, Pascal Wichmann +9
NeurIPS 2025poster

Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-quality SVG generation by framing the problem as a code generation task and leveraging large-scale pretraining. VLMs are pa…

Cited by 0Source ↗Scholar ↗
2025

StarVector: Generating Scalable Vector Graphics Code from Images and Text

Juan A. Rodriguez, Abhay Puri, Shubham Agarwal, Issam H. Laradji, Sai Rajeswar, David Vazquez +2
AAAI 2025technical

Scalable Vector Graphics (SVG) have become integral to modern image rendering applications due to their infinite scalability and versatility, especially in graphic design and web development. SVGs are essentially long strings of code that adhere to a structured syntax with validity constraints. With…

Cited by 2Source ↗PDF ↗Scholar ↗
2025

StarVector: Generating Scalable Vector Graphics Code from Images and Text

Juan A. Rodriguez, Abhay Puri, Shubham Agarwal, Issam H. Laradji, Pau Rodriguez, Sai Rajeswar +3
CVPR 2025poster

Scalable Vector Graphics (SVGs) are vital for modern image rendering due to their scalability and versatility. Previous SVG generation methods have focused on curve-based vectorization, lacking semantic understanding, often producing artifacts, and struggling with SVG primitives beyond path curves.…

Cited by 7Source ↗PDF ↗Scholar ↗
2025

Visual Modality Prompt for Adapting Vision-Language Object Detectors

Heitor R. Medeiros, Atif Belal, Srikanth Muralidharan, Eric Granger, Marco Pedersoli
ICCV 2025poster

The zero-shot performance of object detectors degrades when tested on different modalities, such as infrared and depth. While recent work has explored image translation techniques to adapt detectors to new modalities, these methods are limited to a single modality and traditional detectors. Recently…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

Modality Translation for Object Detection Adaptation without forgetting prior knowledge

Heitor Rapela Medeiros*, Masih Aminbeidokhti, Fidel A Guerrero Pena, David Latortue, Eric Granger, Marco Pedersoli
ECCV 2024poster

"A common practice in deep learning involves training large neural networks on massive datasets to achieve high accuracy across various domains and tasks. While this approach works well in many application areas, it often fails drastically when processing data from a new modality with a significant…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2023

Re-Basin via Implicit Sinkhorn Differentiation

Fidel A. Guerrero Peña, Heitor Rapela Medeiros, Thomas Dubail, Masih Aminbeidokhti, Eric Granger, Marco Pedersoli
CVPR 2023poster

The recent emergence of new algorithms for permuting models into functionally equivalent regions of the solution space has shed some light on the complexity of error surfaces and some promising properties like mode connectivity. However, finding the permutation that minimizes some objectives is chal…

Cited by 40Source ↗PDF ↗code ↗Scholar ↗
2021

Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels

Jizong Peng, Ping Wang, Christian Desrosiers, Marco Pedersoli
NeurIPS 2021poster

The contrastive pre-training of a recognition model on a large dataset of unlabeled data often boosts the model’s performance on downstream tasks like image classification. However, in domains such as medical imaging, collecting unlabeled data can be challenging and expensive. In this work, we consi…

Cited by 86Source ↗PDF ↗code ↗Scholar ↗
2020

A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses

Malik Boudiaf, Jérôme Rony, Imtiaz Masud Ziko, Eric Granger, Marco Pedersoli, Pablo Piantanida +1
ECCV 2020poster

Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard cross-entropy loss for classification has been largely overlooked i…

Cited by 215Source ↗PDF ↗code ↗Scholar ↗
2015

DeepProposal: Hunting Objects by Cascading Deep Convolutional Layers

Amir Ghodrati, Ali Diba, Marco Pedersoli, Tinne Tuytelaars, Luc Van Gool
ICCV 2015poster

In this paper we evaluate the quality of the activation layers of a convolutional neural network (CNN) for the generation of object proposals. We generate hypotheses in a sliding-window fashion over different activation layers and show that the final convolutional layers can find the object of inter…

Cited by 150PDF ↗Scholar ↗