no code implementations • 23 Oct 2023 • Mehdi Fatan, Emanuele Mincato, Dimitra Pintzou, Mariella Dimiccoli
Predicting turn-taking in multiparty conversations has many practical applications in human-computer/robot interaction.
no code implementations • 30 Jan 2022 • Wencan Zhang, Mariella Dimiccoli, Brian Y. Lim
We present Debiased-CAM to recover explanation faithfulness across various bias types and levels by training a multi-input, multi-task model with auxiliary tasks for explanation and bias level predictions.
1 code implementation • 6 Jan 2022 • Ameya Dhamanaskar, Mariella Dimiccoli, Enric Corona, Albert Pumarola, Francesc Moreno-Noguer
In this paper, we propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera.
1 code implementation • EMNLP 2021 • Mariella Dimiccoli, Herwig Wendt, Pau Batlle
This paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy.
1 code implementation • ICCV 2021 • Mariella Dimiccoli, Lluís Garrido, Guillem Rodriguez-Corominas, Herwig Wendt
Recently, 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).
1 code implementation • 28 Apr 2021 • Simone Felicioni, Mariella Dimiccoli
In this paper we propose a new framework to categorize social interactions in egocentric videos, we named InteractionGCN.
no code implementations • 23 Apr 2021 • Alejandro Cartas, Petia Radeva, Mariella Dimiccoli
In this paper, we propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels.
no code implementations • 10 Dec 2020 • Wencan Zhang, Mariella Dimiccoli, Brian Y. Lim
We present Debiased-CAM to recover explanation faithfulness across various bias types and levels by training a multi-input, multi-task model with auxiliary tasks for explanation and bias level predictions.
1 code implementation • 15 Oct 2019 • Alejandro Cartas, Jordi Luque, Petia Radeva, Carlos Segura, Mariella Dimiccoli
Our interaction with the world is an inherently multimodal experience.
no code implementations • 8 Oct 2019 • Mariella Dimiccoli, Herwig Wendt
The main advantage of DGE over state-of-the-art self-supervised approaches is that it does not require any training set, but instead learns iteratively from the data itself a low-dimensional embedding that reflects their temporal and semantic similarity.
1 code implementation • 14 Jun 2019 • Mariella Dimiccoli, Herwig Wendt
Temporal segmentation of untrimmed videos and photo-streams is currently an active area of research in computer vision and image processing.
no code implementations • 3 Jun 2019 • Alejandro Cartas, Jordi Luque, Petia Radeva, Carlos Segura, Mariella Dimiccoli
Sounds are an important source of information on our daily interactions with objects.
no code implementations • 12 May 2019 • Emanuel Sanchez Aimar, Petia Radeva, Mariella Dimiccoli
This 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.
no code implementations • 2 Sep 2018 • Alejandro Cartas, Estefania Talavera, Petia Radeva, Mariella Dimiccoli
Event boundaries play a crucial role as a pre-processing step for detection, localization, and recognition tasks of human activities in videos.
no code implementations • 15 Mar 2018 • Stefan Lonn, Petia Radeva, Mariella Dimiccoli
Unlike photo collections captured by a digital camera, which typically are pre-processed by the user who organizes them into event-related folders, smartphone pictures are automatically stored in the cloud.
1 code implementation • 11 Oct 2017 • Alejandro Cartas, Juan Marin, Petia Radeva, Mariella Dimiccoli
Wearable cameras can gather large a\-mounts of image data that provide rich visual information about the daily activities of the wearer.
no code implementations • 18 Sep 2017 • Maedeh Aghaei, Mariella Dimiccoli, Cristian Canton Ferrer, Petia Radeva
This paper proposes a system for automatic social pattern characterization using a wearable photo-camera.
no code implementations • 8 Sep 2017 • Alejandro Cartas, Mariella Dimiccoli, Petia Radeva
Recently, there has been a growing interest in analyzing human daily activities from data collected by wearable cameras.
no code implementations • 5 Sep 2017 • Maedeh Aghaei, Mariella Dimiccoli, Cristian Canton Ferrer, Petia Radeva
Following the increasingly popular trend of social interaction analysis in egocentric vision, this manuscript presents a comprehensive study for automatic social pattern characterization of a wearable photo-camera user, by relying on the visual analysis of egocentric photo-streams.
no code implementations • 25 Aug 2017 • Alejandro Cartas, Mariella Dimiccoli, Petia Radeva
However, one of its main technical challenges is to deal with the low frame rate of wearable photo-cameras, which causes abrupt appearance changes between consecutive frames.
no code implementations • 13 Apr 2017 • Alejandro Cartas, Juan Marín, Petia Radeva, Mariella Dimiccoli
Recognizing Activities of Daily Living (ADLs) has a large number of health applications, such as characterize lifestyle for habit improvement, nursing and rehabilitation services.
no code implementations • 10 Apr 2017 • Ionut Sorodoc, Sandro Pezzelle, Aurélie Herbelot, Mariella Dimiccoli, Raffaella Bernardi
We however argue that precisely identifying the composition of the sets is not only beyond current state-of-the-art models but perhaps even detrimental to a task that is most efficiently performed by refining the approximate numerosity estimator of the system.
no code implementations • 10 Apr 2017 • Estefania Talavera, Mariella Dimiccoli, Marc Bolaños, Maedeh Aghaei, Petia Radeva
In this paper, we present a new method for egocentric video temporal segmentation based on integrating a statistical mean change detector and agglomerative clustering(AC) within an energy-minimization framework.
no code implementations • 7 Apr 2017 • Maedeh Aghaei, Federico Parezzan, Mariella Dimiccoli, Petia Radeva, Marco Cristani
In our society and century, clothing is not anymore used only as a means for body protection.
no code implementations • 6 Mar 2017 • Maedeh Aghaei, Mariella Dimiccoli, Petia Radeva
Given an unconstrained stream of images captured by a wearable photo-camera (2fpm), we propose an unsupervised bottom-up approach for automatic clustering appearing faces into the individual identities present in these data.
no code implementations • 13 May 2016 • Maedeh Aghaei, Mariella Dimiccoli, Petia Radeva
Given a user wearing a low frame rate wearable camera during a day, this work aims to automatically detect the moments when the user gets engaged into a social interaction solely by reviewing the automatically captured photos by the worn camera.
1 code implementation • 22 Dec 2015 • Mariella Dimiccoli, Marc Bolaños, Estefania Talavera, Maedeh Aghaei, Stavri G. Nikolov, Petia Radeva
While wearable cameras are becoming increasingly popular, locating relevant information in large unstructured collections of egocentric images is still a tedious and time consuming processes.
no code implementations • 26 Nov 2015 • Maria Oliver, Gloria Haro, Mariella Dimiccoli, Baptiste Mazin, Coloma Ballester
This paper presents a computational model to recover the most likely interpretation of the 3D scene structure from a planar image, where some objects may occlude others.
1 code implementation • 2 Nov 2015 • Aniol Lidon, Marc Bolaños, Mariella Dimiccoli, Petia Radeva, Maite Garolera, Xavier Giró-i-Nieto
With 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.
no code implementations • 23 Jul 2015 • Jean-Pascal Jacob, Mariella Dimiccoli, Lionel Moisan
The investigation of spatio-temporal dynamics of bacterial cells and their molecular components requires automated image analysis tools to track cell shape properties and molecular component locations inside the cells.
no code implementations • 22 Jul 2015 • Marc Bolaños, Mariella Dimiccoli, Petia Radeva
Visual lifelogging consists of acquiring images that capture the daily experiences of the user by wearing a camera over a long period of time.
no code implementations • 22 Jul 2015 • Mariella Dimiccoli, Jean-Pascal Jacob, Lionel Moisan
This paper proposes a probabilistic approach for the detection and the tracking of particles in fluorescent time-lapse imaging.
no code implementations • 16 Jul 2015 • Maedeh Aghaei, Mariella Dimiccoli, Petia Radeva
In this paper, we propose a novel method to find correspondences of multiple faces in low temporal resolution egocentric videos acquired through a wearable camera.