Jenny Benois‐Pineau
YOU?
Author Swipe
View article: There is More to Attention: Statistical Filtering Enhances Explanations in Vision Transformers
There is More to Attention: Statistical Filtering Enhances Explanations in Vision Transformers Open
Explainable AI (XAI) has become increasingly important with the rise of large transformer models, yet many explanation methods designed for CNNs transfer poorly to Vision Transformers (ViTs). Existing ViT explanations often rely on attenti…
View article: FusWay: Multimodal hybrid fusion approach. Application to Railway Defect Detection
FusWay: Multimodal hybrid fusion approach. Application to Railway Defect Detection Open
Multimodal fusion is a multimedia technique that has become popular in the wide range of tasks where image information is accompanied by a signal/audio. The latter may not convey highly semantic information, such as speech or music, but so…
View article: Identifying Surgical Instruments in Laparoscopy Using Deep Learning Instance Segmentation
Identifying Surgical Instruments in Laparoscopy Using Deep Learning Instance Segmentation Open
Recorded videos from surgeries have become an increasingly important information source for the field of medical endoscopy, since the recorded footage shows every single detail of the surgery. However, while video recording is straightforw…
View article: Object segmentation in the wild with foundation models: application to vision assisted neuro-prostheses for upper limbs
Object segmentation in the wild with foundation models: application to vision assisted neuro-prostheses for upper limbs Open
In this work, we address the problem of semantic object segmentation using foundation models. We investigate whether foundation models, trained on a large number and variety of objects, can perform object segmentation without fine-tuning o…
View article: Pulmonary vein isolation and low-voltage areas ablation in sinus rhythm for persistent atrial fibrillation (SCAR-AF study)
Pulmonary vein isolation and low-voltage areas ablation in sinus rhythm for persistent atrial fibrillation (SCAR-AF study) Open
Background Substrate ablation strategies in addition to pulmonary vein isolation (PVI) for the maintenance of sinus rhythm (SR) are still debated. Targeting low voltage areas (LVA) in addition to PVI may represent an efficient strategy for…
View article: Mean Opinion Score as a New Metric for User-Evaluation of XAI Methods
Mean Opinion Score as a New Metric for User-Evaluation of XAI Methods Open
This paper investigates the use of Mean Opinion Score (MOS), a common image quality metric, as a user-centric evaluation metric for XAI post-hoc explainers. To measure the MOS, a user experiment is proposed, which has been conducted with e…
View article: Asymmetric Multi-Task Learning for Interpretable Gaze-Driven Grasping Action Forecasting
Asymmetric Multi-Task Learning for Interpretable Gaze-Driven Grasping Action Forecasting Open
This work tackles the automatic prediction of grasping intention of humans observing their environment. Our target application is the assistance to people with motor disabilities and potential cognitive impairments, using assistive robotic…
View article: Data and code for 3D-ARM-Gaze: a public dataset of 3D Arm Reaching Movements with Gaze information in virtual reality
Data and code for 3D-ARM-Gaze: a public dataset of 3D Arm Reaching Movements with Gaze information in virtual reality Open
This repository contains data and code for Lento B., Segas E., Leconte V., Doat E., Danion F., Péteri R., Benois-Pineau J., de Rugy A. (2024). 3D-ARM-Gaze: a public dataset of 3D Arm Reaching Movements with Gaze information in virtual real…
View article: A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information
A Hybrid System for Defect Detection on Rail Lines through the Fusion of Object and Context Information Open
Defect detection on rail lines is essential for ensuring safe and efficient transportation. Current image analysis methods with deep neural networks (DNNs) for defect detection often focus on the defects themselves while ignoring the relat…
View article: SportsVideo: A Multimedia Dataset for Sports Event and Position Detection in Table Tennis and Swimming
SportsVideo: A Multimedia Dataset for Sports Event and Position Detection in Table Tennis and Swimming Open
International audience
View article: 3D-ARM-Gaze: a public dataset of 3D Arm Reaching Movements with Gaze information in virtual reality
3D-ARM-Gaze: a public dataset of 3D Arm Reaching Movements with Gaze information in virtual reality Open
3D-ARM-Gaze is a public dataset designed to provide natural arm movements together with visual and gaze information when reaching objects in a wide reachable space from a precisely controlled, comfortably seated posture. Participants were …
View article: Data and code for 3D-ARM-Gaze: a public dataset of 3D Arm Reaching Movements with Gaze information in virtual reality
Data and code for 3D-ARM-Gaze: a public dataset of 3D Arm Reaching Movements with Gaze information in virtual reality Open
This repository contains data and code for Lento B., Segas E., Leconte V., Doat E., Danion F., Péteri R., Benois-Pineau J., de Rugy A. (2024). 3D-ARM-Gaze: a public dataset of 3D Arm Reaching Movements with Gaze information in virtual real…
View article: JEI Updates Research Topic Categories
JEI Updates Research Topic Categories Open
International audience
View article: On the stability, correctness and plausibility of visual explanation methods based on feature importance
On the stability, correctness and plausibility of visual explanation methods based on feature importance Open
In the field of Explainable AI, multiples evaluation metrics have been proposed in order to assess the quality of explanation methods w.r.t. a set of desired properties. In this work, we study the articulation between the stability, correc…
View article: On the stability, correctness and plausibility of visual explanation methods based on feature importance
On the stability, correctness and plausibility of visual explanation methods based on feature importance Open
International audience
View article: Sport Task: Fine Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2022
Sport Task: Fine Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2022 Open
Sports video analysis is a widespread research topic. Its applications are very diverse, like events detection during a match, video summary, or fine-grained movement analysis of athletes. As part of the MediaEval 2022 benchmarking initiat…
View article: Evaluation of Explanation Methods of AI - CNNs in Image Classification Tasks with Reference-based and No-reference Metrics
Evaluation of Explanation Methods of AI - CNNs in Image Classification Tasks with Reference-based and No-reference Metrics Open
The most popular methods in AI-machine learning paradigm are mainly black boxes. This is why explanation of AI decisions is of emergency. Although dedicated explanation tools have been massively developed, the evaluation of their quality r…
View article: Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics
Evaluation of Explanation Methods of AI -- CNNs in Image Classification Tasks with Reference-based and No-reference Metrics Open
The most popular methods in AI-machine learning paradigm are mainly black boxes. This is why explanation of AI decisions is of emergency. Although dedicated explanation tools have been massively developed, the evaluation of their quality r…
View article: Hybrid FPGA–CPU-Based Architecture for Object Recognition in Visual Servoing of Arm Prosthesis
Hybrid FPGA–CPU-Based Architecture for Object Recognition in Visual Servoing of Arm Prosthesis Open
The present paper proposes an implementation of a hybrid hardware–software system for the visual servoing of prosthetic arms. We focus on the most critical vision analysis part of the system. The prosthetic system comprises a glass-worn ey…
View article: Sports Video: Fine-Grained Action Detection and Classification of Table\n Tennis Strokes from Videos for MediaEval 2021
Sports Video: Fine-Grained Action Detection and Classification of Table\n Tennis Strokes from Videos for MediaEval 2021 Open
Sports video analysis is a prevalent research topic due to the variety of\napplication areas, ranging from multimedia intelligent devices with\nuser-tailored digests up to analysis of athletes' performance. The Sports Video\ntask is part o…
View article: Sports Video: Fine-Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2021
Sports Video: Fine-Grained Action Detection and Classification of Table Tennis Strokes from Videos for MediaEval 2021 Open
Sports video analysis is a prevalent research topic due to the variety of application areas, ranging from multimedia intelligent devices with user-tailored digests up to analysis of athletes' performance. The Sports Video task is part of t…
View article: Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis
Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis Open
International audience
View article: Review of white box methods for explanations of convolutional neural networks in image classification tasks
Review of white box methods for explanations of convolutional neural networks in image classification tasks Open
In recent years, deep learning has become prevalent to solve applications\nfrom multiple domains. Convolutional Neural Networks (CNNs) particularly have\ndemonstrated state of the art performance for the task of image classification.\nHowe…
View article: Falls Detection and Prevention Systems in Home Care for Older Adults: Myth or Reality?
Falls Detection and Prevention Systems in Home Care for Older Adults: Myth or Reality? Open
There is an exponential increase in the range of digital products and devices promoting aging in place, in particular, devices aiming at preventing or detecting falls. However, their deployment is still limited and only few studies have be…