Dominique Vaufreydaz

Dominique Vaufreydaz

Auto-generated profile, based on publicly available information

Dominique Vaufreydaz

LIG, University of Grenoble Alpes, Saint-Martin-d'hères, France

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 August 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YWYangtao Wang
Yangtao Wang
XSXi Shen
Xi Shen
YYYuan Yuan
Yuan Yuan
YDYuming Du
Yuming Du
MLMaomao Li
Maomao Li
DVDominique Vaufreydaz
Dominique Vaufreydaz
In this paper, we describe a graph-based algorithm that uses the features obtained by a self-supervised transformer to detect and segment salient objects in images and videos. With this approach, the image patches that compose an image or video are organised into a fully connected graph, in which the edge between each pair of patches is labeled with a similarity score based on the features learned by the transformer. Detection and segmentation of salient objects can then be formulated as a graph-cut problem and solved using the classical Normalized Cut algorithm. Despite the simplicity of this approach, it achieves state-of-the-art results on several common image and video detection and segmentation tasks. For unsupervised object discovery, this approach outperforms the competing approaches by a margin of 6.1%, 5.7%, and 2.6% when tested with the VOC07, VOC12, and COCO20 K datasets. For the unsupervised saliency detection task in images, this method improves the score for Intersection over Union (IoU) by 4.4%, 5.6% and 5.2%. When tested with the ECSSD, DUTS, and DUT-OMRON datasets. This method also achieves competitive results for unsupervised video object segmentation tasks with the DAVIS, SegTV2, and FBMS datasets.

1 October 2017
Verified
Conference Paper
Open access
PVPavan Vasishta
Pavan Vasishta
DVDominique Vaufreydaz
Dominique Vaufreydaz
ASAnne Spalanzani
Anne Spalanzani
This paper proposes to model pedestrian behaviour in urban scenes by combining the principles of urban planning and the sociological concept of Natural Vision. This model assumes that the environment perceived by pedestrians is composed of multiple potential fields that influence their behaviour. These fields are derived from static scene elements like side-walks, cross-walks, buildings, shops entrances and dynamic obstacles like cars and buses for instance. Using this model, autonomous cars increase their level of situational awareness in the local urban space, with the ability to infer probable pedestrian paths in the scene to predict, for example, legal and illegal crossings.

9 October 2023
Verified
Conference Paper
Open access
AAAnderson Augusma
Anderson Augusma
DVDominique Vaufreydaz
Dominique Vaufreydaz
FLFrédérique Letué
Frédérique Letué
This paper explores privacy-compliant group-level emotion recognition "in-the-wild" within the EmotiW Challenge 2023. Group-level emotion recognition can be useful in many fields including social robotics, conversational agents, e-coaching and learning analytics. This research imposes itself using only global features avoiding individual ones, i.e. all features that can be used to identify or track people in videos (facial landmarks, body poses, audio diarization, etc.). The proposed multimodal model is composed of a video and an audio branches with a cross-attention between modalities. The video branch is based on a fine-tuned ViT architecture. The audio branch extracts Mel-spectrograms and feed them through CNN blocks into a transformer encoder. Our training paradigm includes a generated synthetic dataset to increase the sensitivity of our model on facial expression within the image in a data-driven way. The extensive experiments show the significance of our methodology. Our privacy-compliant proposal performs fairly on the EmotiW challenge, with 79.24% and 75.13% of accuracy respectively on validation and test set for the best models. Noticeably, our findings highlight that it is possible to reach this accuracy level with privacy-compliant features using only 5 frames uniformly distributed on the video.

1 January 2020 in Distances et Médiations des Savoirs
Verified
Journal Article
Open access
PDF file
RLRomain Laurent
Romain Laurent
PDPhilippe Dessus
Philippe Dessus
DVDominique Vaufreydaz
Dominique Vaufreydaz
Introduction À la question « Quelle ingénierie pédagogique à l’ère numérique ? », Peraya et Peltier (2020) nous rappellent que ni la question de l’autonomie de l’apprenant ni la maîtrise des compétences informationnelles ne sont des nécessités nouvelles posées à l’ingénierie pédagogique. Ils nous interrogent en retour sur les dynamiques politique, sociale, économique, technologique qui pourraient, ou impliqueraient de, renouveler les pratiques ingéniériales, en réponse aux demandes des niveau...

16 December 2024 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
LALouis Airale
Louis Airale
Xavier Alameda-PinedaXavier Alameda-Pineda
Xavier Alameda-Pineda
SLStéphane Lathuilière
Stéphane Lathuilière
DVDominique Vaufreydaz
Dominique Vaufreydaz
In this work, we address the task of unconditional head motion generation to animate still human faces in a low-dimensional semantic space from a single reference pose. Different from traditional audio-conditioned talking head generation that seldom puts emphasis on realistic head motions, we devise a GAN-based architecture that learns to synthesize rich head motion sequences over long duration while maintaining low error-accumulation levels. In particular, the autoregressive generation of incremental outputs ensures smooth trajectories, while a multi-scale discriminator on input pairs drives generation toward better handling of high- and low-frequency signals and less mode collapse. We experimentally demonstrate the relevance of the proposed method and show its superiority compared to models that attained state-of-the-art performances on similar tasks.

30 September 2026 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Verified
Journal Article
Open access
XCXi Chen
Xi Chen
JCJulien Cumin
Julien Cumin
FRFano Ramparany
Fano Ramparany
DVDominique Vaufreydaz
Dominique Vaufreydaz
Ambient sensors offer a privacy-preserving solution for activity recognition in smart homes, yet they face a critical challenge in multi-resident environments known as Data Association, which aims to identify the resident triggering a specific anonymous sensor event. Existing approaches fundamentally fail to maintain global consistency by often yielding conflicting associations for silent residents. Additionally, these methods frequently suffer from severe trajectory fragmentation caused by the ontological mismatch of applying continuous physical motion models to discrete logical behaviors. To address these limitations, we propose a novel framework that reformulates data association as a sequential decision-making task within a Markov Decision Process (MDP). We solve the defined MDP via Behavior Cloning (BC) to avoid complex reward engineering by directly learning from expert demonstrations. We instantiate the policy using two complementary architectures, including a lightweight Transformer that treats association as a multi-label classification task over linearized event histories, and a fine-tuned Large Language Model (LLM) that reformulates the problem as conditional text generation to leverage pre-trained semantic knowledge. Extensive evaluations on three diverse datasets demonstrate that our approach significantly outperforms state-of-the-art baselines, particularly in resolving concurrent multi-resident events. Furthermore, the LLM-based policy shows preliminary cross-environment transfer potential under benchmark settings, while its robustness in real deployments still requires further validation.