Exploració per autor "Dimiccoli, Mariella"
Ara es mostren els items 1-20 de 21
-
Activities of daily living monitoring via a wearable camera: toward real-world applications
Cartas Ayala, Alejandro; Radeva, Petia; Dimiccoli, Mariella (Institute of Electrical and Electronics Engineers (IEEE), 2020)
Article
Accés obertActivity recognition from wearable photo-cameras is crucial for lifestyle characterization and health monitoring. However, to enable its wide-spreading use in real-world applications, a high level of generalization needs ... -
Behavioural and neurophysiological signatures in the retrieval of individual memories of recent and remote real-life routine episodic events
Nicolás, Berta; Wu, Xiongbo; Garcia-Arch, Josué; Dimiccoli, Mariella; Sierpowska, Joanna; Saiz-Masvidal, Cristina; Soriano Mas, Carles; Radeva, Petia; Fuentemilla, Lluís (2021-08)
Article
Accés obertAutobiographical memory (AM) has been largely investigated as the ability to recollect specific events that belong to an individual's past. However, how we retrieve real-life routine episodes and how the retrieval of these ... -
Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learning
Zhang, Wanchang; Dimiccoli, Mariella; Lim, B.H. (Association for Computing Machinery (ACM), 2022)
Text en actes de congrés
Accés obertModel explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject ... -
Enhancing egocentric 3D pose estimation with third person views
Dhamanaskar, Ameya; Dimiccoli, Mariella; Corona Puyane, Enric; Pumarola Peris, Albert; Moreno-Noguer, Francesc (Elsevier, 2023-06)
Article
Accés obertWe propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera. The main technical contribution consists of leveraging high-level features linking ... -
Enhancing temporal segmentation by nonlocal self-similarity
Dimiccoli, Mariella; Wendt, Herwig (2019)
Text en actes de congrés
Accés obertTemporal segmentation of untrimmed videos and photo-streams is currently an active area of research in computer vision and image processing. This paper proposes a new approach to improve the temporal segmentation of ... -
Graph constrained data representation learning for human motion segmentation
Dimiccoli, Mariella; Garrido Beltrán, Lluís; Rodríguez Corominas, Guillem; Wendt, Herwig (Institute of Electrical and Electronics Engineers (IEEE), 2022)
Text en actes de congrés
Accés obertRecently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segmentation (HMS). These approaches leverage ... -
Interaction-GCN: a graph convolutional network based framework for social interaction recognition in egocentric videos
Felicioni, Simone; Dimiccoli, Mariella (Institute of Electrical and Electronics Engineers (IEEE), 2021)
Text en actes de congrés
Accés obertIn this paper we propose a new framework to categorize social interactions in egocentric videos, we named InteractionGCN. Our method extracts patterns of relational and non-relational cues at the frame level and uses them ... -
Introduction to the special issue: egocentric vision and lifelogging
Dimiccoli, Mariella; Gurrin, Cathal; Crandall, David; Giró Nieto, Xavier; Radeva, Petia (2018-06-15)
Article
Accés obert -
Learning event representations for temporal segmentation of image sequences by dynamic graph embedding
Dimiccoli, Mariella; Wendt, Herwig (2021)
Article
Accés obertRecently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood as sets of temporally adjacent images that ... -
Learning grounded word meaning representations on similarity graphs
Dimiccoli, Mariella; Wendt, Herwig; Battle, Pau (PUBLICACIONS EUPBL, ETT-ST/ACLSI/P99/EP2.1, 2021)
Text en actes de congrés
Accés obertThis paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy. The lower level of the hierarchy models modality-specific ... -
LEMoRe: A lifelog engine for moments retrieval at the NTCIR-lifelog LSAT task
de Oliveira Barra, Gabriel; Cartas Ayala, Alejandro; Bolaños, Marc; Dimiccoli, Mariella; Giró Nieto, Xavier; Radeva, Petia (2016)
Comunicació de congrés
Accés obertSemantic image retrieval from large amounts of egocentric visual data requires to leverage powerful techniques for filling in the semantic gap. This paper introduces LEMoRe, a Lifelog Engine for Moments Retrieval, developed ... -
Leveraging triplet loss for unsupervised action segmentation
Bueno Benito, Elena Belén; Tura Vecino, Biel; Dimiccoli, Mariella (Institute of Electrical and Electronics Engineers (IEEE), 2023)
Text en actes de congrés
Accés obertIn this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, without requiring any training data. Our method ... -
Modeling long-term interactions to enhance action recognition
Cartas Ayala, Alejandro; Radeva, Petia; Dimiccoli, Mariella (Institute of Electrical and Electronics Engineers (IEEE), 2021)
Text en actes de congrés
Accés obertIn this paper, we propose a new approach to understand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. At the frame level, we use a region-based approach ... -
Neighborhood filters and the recovery of 3D information
Digne, Julie; Dimiccoli, Mariella; Salembier Clairon, Philippe Jean; Sabater, Neus (2011)
Capítol de llibre
Accés restringit per política de l'editorialFollowing their success in image processing (see Chap. 26), neighborhood filters have been extended to 3D surface processing. This adaptation is not straightforward. It has led to several variants for surfaces depending ... -
Neighborhood filters and the recovery of 3D information
Digne, Julie; Dimiccoli, Mariella; Sabater, Neus; Salembier Clairon, Philippe Jean (2015-09-01)
Capítol de llibre
Accés restringit per política de l'editorial -
Recognizing object surface material from impact sounds for robot manipulation
Dimiccoli, Mariella; Patni, Shubhan; Hoffmann, Matej; Agudo Martínez, Antonio (Institute of Electrical and Electronics Engineers (IEEE), 2022)
Text en actes de congrés
Accés obertWe investigated the use of impact sounds generated during exploratory behaviors in a robotic manipulation setup as cues for predicting object surface material and for recognizing individual objects. We collected and make ... -
Seeing and hearing egocentric actions: how much can we learn?
Cartas Ayala, Alejandro; Luque, Jordi; Radeva, Petia; Segura, Carlos; Dimiccoli, Mariella (2019)
Text en actes de congrés
Accés obertOur interaction with the world is an inherently multi-modal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a single modality. In particular, a limited ... -
Semantic summarization of egocentric photo stream events
Lidon, Aniol; Bolaños, Marc; Dimiccoli, Mariella; Radeva, Petia; Garolera Freixa, Maite; Giró Nieto, Xavier (2017)
Text en actes de congrés
Accés restringit per política de l'editorialWith the rapid increase of users of wearable cameras in recent years and of the amount of data they produce, there is a strong need for automatic retrieval and summarization techniques. This work addresses the problem of ... -
Smartphone picture organization: a hierarchical approach
Lonn, Stefan; Radeva, Petia; Dimiccoli, Mariella (2019-10-01)
Article
Accés obertWe live in a society where the large majority of the population has a camera-equipped smartphone. In addition, hard drives and cloud storage are getting cheaper and cheaper, leading to a tremendous growth in stored personal ... -
Social relation recognition in egocentric photostreams
Sánchez Aimar, Emanuel; Radeva, Petia; Dimiccoli, Mariella (2019)
Text en actes de congrés
Accés obertThis paper proposes an approach to automatically categorize the social interactions of a user wearing a photo-camera (2fpm), by relying solely on what the camera is seeing. The problem is challenging due to the overwhelming ...