Ponències/Comunicacions de congressos
Enviaments recents
-
3D point cloud segmentation using a fully connected conditional random field
(Institute of Electrical and Electronics Engineers (IEEE), 2017)
Comunicació de congrés
Accés restringit per política de l'editorialTraditional image segmentation methods working with low level image features are usually difficult to adapt to higher level tasks, such as object recognition and scene understanding. Object segmentation emerges as a new ... -
An interactive lifelog search engine for LSC2018
(Association for Computing Machinery (ACM), 2018)
Comunicació de congrés
Accés obertIn this work, we describe an interactive lifelog search engine developed for the LSC 2018 search challenge at ACM ICMR 2018. The paper introduces the four-step process required to support lifelog search engines and describes ... -
Masked V-Net: an approach to brain tumor segmentation
(2017)
Comunicació de congrés
Accés restringit per política de l'editorialThis paper introduces Masked V-Net architecture, a variant of the recently introduced V-Net[13] that reformulates the residual connections and uses a ROI mask to constrain the network to train only on relevant voxels. ... -
Comparing fixed and adaptive computation time for recurrent neural networks
(2018)
Text en actes de congrés
Accés obertDeep networks commonly perform better than shallow ones, but allocating the proper amount of computation for each particular input sample remains an open problem. This issue is particularly challenging in sequential tasks, ... -
Skip RNN: learning to skip state updates in recurrent neural networks
(2018)
Comunicació de congrés
Accés obertRecurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty ... -
Foreground objects segmentation for moving camera scenarios based on SCGMM
(2011)
Text en actes de congrés
Accés restringit per política de l'editorialIn this paper we present a new system for segmenting non-rigid objects in moving camera sequences for indoor and outdoor scenarios that achieves a correct object segmentation via global MAP-MRF framework formulation for ... -
Motion analysis of image sequences using connected operators
(International Society for Photo-Optical Instrumentation Engineers (SPIE), 1997)
Text en actes de congrés
Accés restringit per política de l'editorialThis paper deals with a class of morphological operators called connected operators. These operators interact with the signal by merging flat zones. As a results, they do not create any new contours and are very attractive ... -
Active mesh coding and rate-distortion theory
(Institute of Electrical and Electronics Engineers (IEEE), 1996)
Comunicació de congrés
Accés obertThis paper presents a video coding scheme for very low bit rate applications. The coding approach relies on active meshes and can be viewed as a particular case of region-based coding. The active mesh is used to efficiently ... -
SaltiNet: scan-path prediction on 360 degree images using saliency volumes
(IEEE Press, 2018)
Comunicació de congrés
Accés obertWe introduce SaltiNet, a deep neural network for scan-path prediction trained on 360-degree images. The model is based on a temporal-aware novel representation of saliency information named the saliency volume. The first ... -
Cost-effective active learning for melanoma segmentation
(2017)
Comunicació de congrés
Accés obertWe propose a novel Active Learning framework capable to train effectively a convolutional neural network for semantic segmentation of medical imaging, with a limited amount of training labeled data. Our contribution is a ... -
Towards large scale multimedia indexing: a case study on person discovery in broadcast news
(Association for Computing Machinery (ACM), 2017)
Text en actes de congrés
Accés restringit per política de l'editorialThe rapid growth of multimedia databases and the human interest in their peers make indices representing the location and identity of people in audio-visual documents essential for searching archives. Person discovery ... -
Two level continuous speech recognition using demisyllable-based HMM word spotting
(1991)
Text en actes de congrés
Accés obertThis paper describes a two level Spanish Continuous Speech Recognition System based on Demisyllable HMM modelling, word-spotting and finite-state lexical and syntactic knowledge. The first level, the word level, is based ...
RSS 1.0