AIConfPaper
← Search

Eric Granger

24 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

Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI

Mahdi Alehdaghi, Rajarshi Bhattacharya, Pourya Shamsolmoali, Rafael M. O. Cruz, Eric Granger
AAAI 2026technical

As AI systems become more capable, it is important that their decisions are understandable and aligned with human expectations. A key challenge is the lack of interpretability in deep models. Existing methods such as GradCAM generate heatmaps but provide limited conceptual insight, while prototype-b

Cited by 0Source ↗PDF ↗Scholar ↗
2026

DogFit: Domain-guided Fine-tuning for Efficient Transfer Learning of Diffusion Models

Yara Bahram, Mohammadhadi Shateri, Eric Granger
AAAI 2026technical

Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in image fidelity through a trade-off with sample diversity. Howe

Cited by 0Source ↗PDF ↗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 ↗
2026

Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation

Yara Bahram, Mélodie Desbos, Mohammadhadi Shateri, Eric Granger
CVPR 2026

Diffusion models (DMs) produce high-quality images, yet their sampling remains costly when adapted to new domains. Distilled DMs are faster but typically remain confined within their teacher's domain. Thus, fast and high-quality generation for novel domains relies on two-stage pipelines: Adapt-then-

Cited by 0Source ↗code ↗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

Learning Task-Agnostic Representations through Multi-Teacher Distillation

Philippe Formont, Maxime DARRIN, Banafsheh Karimian, Eric Granger, Jackie CK Cheung, Ismail Ben Ayed +2
NeurIPS 2025poster

Casting complex inputs into tractable representations is a critical step across various fields. Diverse embedding models emerge from differences in architectures, loss functions, input modalities and datasets, each capturing unique aspects of the input. Multi-teacher distillation leverages this dive…

Cited by 0Source ↗Scholar ↗
2025

Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation

Nairouz Mrabah, Nicolas Richet, Ismail Ben Ayed, Eric Granger
ICCV 2025poster

Adapting Vision-Language Models (VLMs) to new domains with few labeled samples remains a significant challenge due to severe overfitting and computational constraints. State-of-the-art solutions, such as low-rank reparameterization, mitigate these issues but often struggle with generalization and re…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

TD-Paint: Faster Diffusion Inpainting Through Time-Aware Pixel Conditioning

Tsiry Mayet, Pourya Shamsolmoali, Simon Bernard, Eric Granger, Romain HÉRAULT, Clement Chatelain
ICLR 2025poster

Diffusion models have emerged as highly effective techniques for inpainting, however, they remain constrained by slow sampling rates. While recent advances have enhanced generation quality, they have also increased sampling time, thereby limiting scalability in real-world applications. We investigat…

Cited by 0Source ↗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 ↗
2024

SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution

Soufiane Belharbi, Mara KM Whitford, Phuong Hoang, Shakeeb Murtaza, Luke McCaffrey, Eric Granger
NeurIPS 2024poster

Confocal fluorescence microscopy is one of the most accessible and widely used imaging techniques for the study of biological processes at the cellular and subcellular levels. Scanning confocal microscopy allows the capture of high-quality images from thick three-dimensional (3D) samples, yet suffer…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

SeTformer Is What You Need for Vision and Language

Pourya Shamsolmoali, Masoumeh Zareapoor, Eric Granger, Michael Felsberg
AAAI 2024technical

The dot product self-attention (DPSA) is a fundamental component of transformers. However, scaling them to long sequences, like documents or high-resolution images, becomes prohibitively expensive due to the quadratic time and memory complexities arising from the softmax operation. Kernel methods ar…

Cited by 6Source ↗PDF ↗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 ↗
2023

Recursive Joint Attention for Audio-Visual Fusion in Regression Based Emotion Recognition

R. Gnana Praveen, Eric Granger, Patrick Cardinal
ICASSP 2023accepted

In video-based emotion recognition (ER), it is important to effectively leverage the complementary relationship among audio (A) and visual (V) modalities, while retaining the intramodal characteristics of individual modalities. In this paper, a recursive joint attention model is proposed along with…

Cited by 0Source ↗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 ↗
2020

Encoding Temporal Information For Automatic Depression Recognition From Facial Analysis

Wheidima Carneiro de Melo, Eric Granger, Miguel Bordallo López
ICASSP 2020accepted

Depression is a mental illness that may be harmful to an individual's health. Using deep learning models to recognize the facial expressions of individuals captured in videos has shown promising results for automatic depression detection. Typically, depression levels are recognized using 2D-Convolut…

Cited by 0Source ↗Scholar ↗
2020

Unsupervised Domain Adaptation in the Dissimilarity Space for Person Re-identification

Djebril Mekhazni, Amran Bhuiyan, George Ekladious, Eric Granger
ECCV 2020poster

Person re-identification (ReID) remains a challenging task in many real-word video analytics and surveillance applications, even though state-of-the-art accuracy has improved considerably with the advent of deep learning (DL) models trained on large image datasets. Given the shift in distributions t…

Cited by 156Source ↗PDF ↗code ↗Scholar ↗
2019

Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenses

Jerome Rony, Luiz G. Hafemann, Luiz S. Oliveira, Ismail Ben Ayed, Robert Sabourin, Eric Granger
CVPR 2019oral

Research on adversarial examples in computer vision tasks has shown that small, often imperceptible changes to an image can induce misclassification, which has security implications for a wide range of image processing systems. Considering L2 norm distortions, the Carlini and Wagner attack is presen…

Cited by 392PDF ↗code ↗Scholar ↗