Pasar al contenido principal

RECONOCIMIENTO VISUAL CON METODOLOGIAS DE APRENDIZAJE DE PRINCIPIO A FIN: MIRANDO LAS PERSONAS Y ENTENDIENDO LAS ESCENAS

TIN2015-66951-C2-2-R

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2015
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Dirección General de Investigación Científica y Técnica
Centro beneficiario FUNDACIO PER A LA UNIVERSITAT OBERTA DE CATALUNYA
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 8
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Artículo de revisión (ReviewArticle)

Learnheuristics, Hybridizing metaheuristics with machine learning for optimization with dynamic inputs

  • Calvet, Laura|||0000-0001-8425-1381
  • Armas, Jésica De
  • Masip, David
  • Juan, Ángel A.|||0000-0003-1392-1776
This paper reviews the existing literature on the combination of metaheuristics with machine learning methods and then introduces the concept of learnheuristics, a novel type of hybrid algorithms. Learnheuristics can be used to solve combinatorial optimization problems with dynamic inputs (COPDIs). In these COPDIs, the problem inputs (elements either located in the objective function or in the constraints set) are not fixed in advance as usual. On the contrary, they might vary in a predictable (non-random) way as the solution is partially built according to some heuristic-based iterative process. For instance, a consumer's willingness to spend on a specific product might change as the availability of this product decreases and its price rises. Thus, these inputs might take different values depending on the current solution configuration. These variations in the inputs might require from a coordination between the learning mechanism and the metaheuristic algorithm: at each iteration, the learning method updates the inputs model used by the metaheuristic.
UPCommons. Portal del coneixement obert de la UPC
Publicación Artículo científico (JournalArticle)

RVOS: end-to-end recurrent network for video object segmentation

  • Ventura Royo, Carles|||0000-0002-3055-339X
  • Bellver, Míriam
  • Girbau Xalabarder, Andreu
  • Salvador Aguilera, Amaia|||0000-0002-9908-1685
  • Marqués Acosta, Fernando|||0000-0001-8311-1168
  • Giró Nieto, Xavier|||0000-0002-9935-5332
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU., This research was supported by the Spanish Ministry ofEconomy and Competitiveness and the European RegionalDevelopment Fund (TIN2015-66951-C2-2-R, TIN2015-65316-P & TEC2016-75976-R), the BSC-CNS SeveroOchoa SEV-2015-0493 and LaCaixa-Severo Ochoa Inter-national Doctoral Fellowship programs, the 2017 SGR 1414and the Industrial Doctorates 2017-DI-064 & 2017-DI-028from the Government of Catalonia, Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Using simulation and reliability concepts to set starting times in multitask projects with a common deadline

  • Juan Pérez, Ángel Alejandro
  • Calvet Liñán, Laura
  • Serrat Piè, Carles|||0000-0002-1504-5354
  • Hatami, Sara|||0000-0002-8000-4989
In production and transportation logistics, it is frequent to have projects in which different tasks must be processed in parallel and completed before a common deadline. Usually, it is not desirable to assign scarce resources to a new project earlier than strictly necessary, since they might be currently occupied in other projects. When these tasks have random completion times, some natural questions arise: (i) how much can we delay the starting time of each task in the new project so that it can be completed by the deadline with a given probability? and (ii) how to compute these ‘optimal’ starting times when not all tasks need to be necessarily finished to consider the project as completed? This paper proposes a hybrid approach, combining reliability concepts with simulation and optimization techniques, to support decision makers in finding the optimal starting times for each task under the described uncertainty scenario., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

RVOS: end-to-end recurrent network for video object segmentation

  • Ventura Royo, Carles|||0000-0002-3055-339X
  • Bellver Bueno, Míriam
  • Girbau Xalabarder, Andreu
  • Salvador Aguilera, Amaia|||0000-0002-9908-1685
  • Marqués Acosta, Fernando|||0000-0001-8311-1168
  • Giró Nieto, Xavier|||0000-0002-9935-5332
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU., Peer Reviewed
O2, repositorio institucional de la UOC
Publicación Contribución de congreso (ConferenceOutput)

Emotion Recognition in Context

  • KOSTI, RONAK
  • Alvarez, Jose Manuel
  • Recasens Continente, Adria
  • Lapedriza, Agata
Understanding what a person is experiencing from her frame of reference is essential in our everyday life. For this reason, one can think that machines with this type of ability would interact better with people. However, there are no current systems capable of understanding in detail peoples emotional states. Previous research on computer vision to recognize emotions has mainly focused on analyzing the facial expression, usually classifying it into the 6 basic emotions [11]. However, the context plays an important role in emotion perception, and when the context is incorporated, we can infer more emotional states. In this paper we present the Emotions in Context Database (EMCO), a dataset of images containing people in context in non-controlled environments. In these images, people are annotated with 26 emotional categories and also with the continuous dimensions valence, arousal, and dominance [21]. With the EMCO dataset, we trained a Convolutional Neural Network model that jointly analyzes the person and the whole scene to recognize rich information about emotional states. With this, we show the importance of considering the context for recognizing peoples emotions in images, and provide a benchmark in the task of emotion recognition in visual context.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Using simulation and reliability concepts to set starting times in multitask projects with a common deadline

  • Juan Pérez, Ángel Alejandro
  • Calvet Liñán, Laura
  • Serrat Piè, Carles
  • Hatami, Sara
In production and transportation logistics, it is frequent to have projects in which different tasks must be processed in parallel and completed before a common deadline. Usually, it is not desirable to assign scarce resources to a new project earlier than strictly necessary, since they might be currently occupied in other projects. When these tasks have random completion times, some natural questions arise: (i) how much can we delay the starting time of each task in the new project so that it can be completed by the deadline with a given probability? and (ii) how to compute these ‘optimal’ starting times when not all tasks need to be necessarily finished to consider the project as completed? This paper proposes a hybrid approach, combining reliability concepts with simulation and optimization techniques, to support decision makers in finding the optimal starting times for each task under the described uncertainty scenario., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

RVOS: end-to-end recurrent network for video object segmentation

  • Ventura Royo, Carles
  • Bellver, Míriam
  • Girbau Xalabarder, Andreu
  • Salvador Aguilera, Amaia
  • Marqués Acosta, Fernando
  • Giró Nieto, Xavier
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU., This research was supported by the Spanish Ministry ofEconomy and Competitiveness and the European RegionalDevelopment Fund (TIN2015-66951-C2-2-R, TIN2015-65316-P & TEC2016-75976-R), the BSC-CNS SeveroOchoa SEV-2015-0493 and LaCaixa-Severo Ochoa Inter-national Doctoral Fellowship programs, the 2017 SGR 1414and the Industrial Doctorates 2017-DI-064 & 2017-DI-028from the Government of Catalonia, Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

RVOS: end-to-end recurrent network for video object segmentation

  • Ventura Royo, Carles
  • Bellver Bueno, Míriam
  • Girbau Xalabarder, Andreu
  • Salvador Aguilera, Amaia
  • Marqués Acosta, Fernando
  • Giró Nieto, Xavier
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU., Peer Reviewed, Postprint (published version)