no code implementations • MADiMa Workshop in ACM Multimedia 2023 • Jesús M. Rodríguez-de-Vera, Pablo Villacorta, Imanol G. Estepa, Marc Bolaños, Ignacio Sarasúa, Bhalaji Nagarajan, Petia Radeva
Trained through an end-to-end multi-task learning process, this method enhances performance in the fine-grained food recognition task, showing exceptional prowess with highly similar classes.
Ranked #4 on Fine-Grained Image Classification on Food-101
Fine-Grained Image Classification Fine-Grained Image Recognition +2
no code implementations • 16 Mar 2023 • Pablo Villacorta, Jesús M. Rodríguez-de-Vera, Marc Bolaños, Ignacio Sarasúa, Bhalaji Nagarajan, Petia Radeva
Extensive experimentation shows improvements in the SoTA FGVR benchmarks of up to +1. 3% of accuracy using both CNNs and transformer-based networks.
Fine-Grained Image Recognition Fine-Grained Visual Recognition
1 code implementation • 30th ACM International Conference on Multimedia 2022 • Javier Ródenas, Bhalaji Nagarajan, Marc Bolaños, Petia Radeva
We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets.
Ranked #1 on Fine-Grained Image Classification on FoodX-251
no code implementations • 14 Nov 2017 • Eduardo Aguilar, Beatriz Remeseiro, Marc Bolaños, Petia Radeva
The increase in awareness of people towards their nutritional habits has drawn considerable attention to the field of automatic food analysis.
no code implementations • 14 Sep 2017 • Eduardo Aguilar, Marc Bolaños, Petia Radeva
One of the most common critical factors directly related to the cause of a chronic disease is unhealthy diet consumption.
no code implementations • 14 Sep 2017 • Eduardo Aguilar, Marc Bolaños, Petia Radeva
With the arrival of convolutional neural networks, the complex problem of food recognition has experienced an important improvement in recent years.
no code implementations • 27 Jul 2017 • Gabriel Oliveira-Barra, Marc Bolaños, Estefania Talavera, Adrián Dueñas, Olga Gelonch, Maite Garolera
Mild cognitive impairment is the early stage of several neurodegenerative diseases, such as Alzheimer's.
2 code implementations • 27 Jul 2017 • Marc Bolaños, Aina Ferrà, Petia Radeva
Automatically constructing a food diary that tracks the ingredients consumed can help people follow a healthy diet.
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.
1 code implementation • 7 Apr 2017 • Marc Bolaños, Álvaro Peris, Francisco Casacuberta, Sergi Soler, Petia Radeva
We propose a novel methodology that exploits information from temporally neighboring events, matching precisely the nature of egocentric sequences.
1 code implementation • 12 Dec 2016 • Marc Bolaños, Álvaro Peris, Francisco Casacuberta, Petia Radeva
In this paper, we address the problem of visual question answering by proposing a novel model, called VIBIKNet.
no code implementations • 29 Jul 2016 • Pedro Herruzo, Marc Bolaños, Petia Radeva
In a complete diet recognition of dishes from Mediterranean diet, enlarged with the Food-101 dataset for international dishes recognition, we achieve a top-1 accuracy of 68. 07\%, and top-5 of 89. 53\%, for a total of 115+101 food classes.
no code implementations • 27 Apr 2016 • Marc Bolaños, Petia Radeva
The development of automatic nutrition diaries, which would allow to keep track objectively of everything we eat, could enable a whole new world of possibilities for people concerned about their nutrition patterns.
1 code implementation • 12 Apr 2016 • Álvaro Peris, Marc Bolaños, Petia Radeva, Francisco Casacuberta
Although traditionally used in the machine translation field, the encoder-decoder framework has been recently applied for the generation of video and image descriptions.
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.
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 • 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.
1 code implementation • 5 May 2015 • Marc Bolaños, Ricard Mestre, Estefanía Talavera, Xavier Giró-i-Nieto, Petia Radeva
Building a visual summary from an egocentric photostream captured by a lifelogging wearable camera is of high interest for different applications (e. g. memory reinforcement).
1 code implementation • 7 Apr 2015 • Marc Bolaños, Petia Radeva
Given an egocentric video/images sequence acquired by the camera, our algorithm uses both the appearance extracted by means of a convolutional neural network and an object refill methodology that allows to discover objects even in case of small amount of object appearance in the collection of images.