Home [121–130] << 131 132 133 134 135 136 137 138 139 140 >> [141–150]
List View
 | 
Citations
 | 
Details
   web
Records
Author Lei Kang; Juan Ignacio Toledo; Pau Riba; Mauricio Villegas; Alicia Fornes; Marçal Rusiñol
Title Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence Model for Handwritten Word Recognition Type Conference Article
Year 2018 Publication 40th German Conference on Pattern Recognition Abbreviated Journal
Volume Issue Pages 459-472
Keywords (up)
Abstract This paper proposes Convolve, Attend and Spell, an attention based sequence-to-sequence model for handwritten word recognition. The proposed architecture has three main parts: an encoder, consisting of a CNN and a bi-directional GRU, an attention mechanism devoted to focus on the pertinent features and a decoder formed by a one-directional GRU, able to spell the corresponding word, character by character. Compared with the recent state-of-the-art, our model achieves competitive results on the IAM dataset without needing any pre-processing step, predefined lexicon nor language model. Code and additional results are available in https://github.com/omni-us/research-seq2seq-HTR.
Address Stuttgart; Germany; October 2018
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference GCPR
Notes DAG; 600.097; 603.057; 302.065; 601.302; 600.084; 600.121; 600.129 Approved no
Call Number Admin @ si @ KTR2018 Serial 3167
Permanent link to this record
 
 
Author Alicia Fornes; Bart Lamiroy
Title Graphics Recognition, Current Trends and Evolutions Type Book Whole
Year 2018 Publication Graphics Recognition, Current Trends and Evolutions Abbreviated Journal
Volume 11009 Issue Pages
Keywords (up)
Abstract This book constitutes the thoroughly refereed post-conference proceedings of the 12th International Workshop on Graphics Recognition, GREC 2017, held in Kyoto, Japan, in November 2017.
The 10 revised full papers presented were carefully reviewed and selected from 14 initial submissions. They contain both classical and emerging topics of graphics rcognition, namely analysis and detection of diagrams, search and classification, optical music recognition, interpretation of engineering drawings and maps.
Address
Corporate Author Thesis
Publisher Springer International Publishing Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN 978-3-030-02283-9 Medium
Area Expedition Conference
Notes DAG; 600.121 Approved no
Call Number Admin @ si @ FoL2018 Serial 3171
Permanent link to this record
 
 
Author Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas
Title Learning from# Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods Type Conference Article
Year 2018 Publication 15th European Conference on Computer Vision Workshops Abbreviated Journal
Volume 11134 Issue Pages 530-544
Keywords (up)
Abstract Massive tourism is becoming a big problem for some cities, such as Barcelona, due to its concentration in some neighborhoods. In this work we gather Instagram data related to Barcelona consisting on images-captions pairs and, using the text as a supervisory signal, we learn relations between images, words and neighborhoods. Our goal is to learn which visual elements appear in photos when people is posting about each neighborhood. We perform a language separate treatment of the data and show that it can be extrapolated to a tourists and locals separate analysis, and that tourism is reflected in Social Media at a neighborhood level. The presented pipeline allows analyzing the differences between the images that tourists and locals associate to the different neighborhoods. The proposed method, which can be extended to other cities or subjects, proves that Instagram data can be used to train multi-modal (image and text) machine learning models that are useful to analyze publications about a city at a neighborhood level. We publish the collected dataset, InstaBarcelona and the code used in the analysis.
Address Munich; Alemanya; September 2018
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ECCVW
Notes DAG; 600.129; 601.338; 600.121 Approved no
Call Number Admin @ si @ GGG2018b Serial 3176
Permanent link to this record
 
 
Author Y. Patel; Lluis Gomez; Raul Gomez; Marçal Rusiñol; Dimosthenis Karatzas; C.V. Jawahar
Title TextTopicNet-Self-Supervised Learning of Visual Features Through Embedding Images on Semantic Text Spaces Type Miscellaneous
Year 2018 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords (up)
Abstract The immense success of deep learning based methods in computer vision heavily relies on large scale training datasets. These richly annotated datasets help the network learn discriminative visual features. Collecting and annotating such datasets requires a tremendous amount of human effort and annotations are limited to popular set of classes. As an alternative, learning visual features by designing auxiliary tasks which make use of freely available self-supervision has become increasingly popular in the computer vision community.
In this paper, we put forward an idea to take advantage of multi-modal context to provide self-supervision for the training of computer vision algorithms. We show that adequate visual features can be learned efficiently by training a CNN to predict the semantic textual context in which a particular image is more probable to appear as an illustration. More specifically we use popular text embedding techniques to provide the self-supervision for the training of deep CNN.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG; 600.084; 601.338; 600.121 Approved no
Call Number Admin @ si @ PGG2018 Serial 3177
Permanent link to this record
 
 
Author Anguelos Nicolaou; Sounak Dey; V.Christlein; A.Maier; Dimosthenis Karatzas
Title Non-deterministic Behavior of Ranking-based Metrics when Evaluating Embeddings Type Conference Article
Year 2018 Publication International Workshop on Reproducible Research in Pattern Recognition Abbreviated Journal
Volume 11455 Issue Pages 71-82
Keywords (up)
Abstract Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized distances introduce and provide bounds on the effect. We demonstrate that it can have a measurable effect in empirical data in state-of-the-art systems. We also approach the phenomenon from a computer security perspective and demonstrate how someone being evaluated by a third party can exploit this ambiguity and greatly outperform a random predictor without even access to the input data. We also suggest a simple solution making the performance metrics, which rely on ranking, totally deterministic and impervious to such exploits.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG; 600.121; 600.129 Approved no
Call Number Admin @ si @ NDC2018 Serial 3178
Permanent link to this record
 
 
Author Dena Bazazian; Dimosthenis Karatzas; Andrew Bagdanov
Title Word Spotting in Scene Images based on Character Recognition Type Conference Article
Year 2018 Publication IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal
Volume Issue Pages 1872-1874
Keywords (up)
Abstract In this paper we address the problem of unconstrained Word Spotting in scene images. We train a Fully Convolutional Network to produce heatmaps of all the character classes. Then, we employ the Text Proposals approach and, via a rectangle classifier, detect the most likely rectangle for each query word based on the character attribute maps. We evaluate the proposed method on ICDAR2015 and show that it is capable of identifying and recognizing query words in natural scene images.
Address Salt Lake City; USA; June 2018
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference CVPRW
Notes DAG; 600.129; 600.121 Approved no
Call Number BKB2018a Serial 3179
Permanent link to this record
 
 
Author Adrien Gaidon; Antonio Lopez; Florent Perronnin
Title The Reasonable Effectiveness of Synthetic Visual Data Type Journal Article
Year 2018 Publication International Journal of Computer Vision Abbreviated Journal IJCV
Volume 126 Issue 9 Pages 899–901
Keywords (up)
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes ADAS; 600.118 Approved no
Call Number Admin @ si @ GLP2018 Serial 3180
Permanent link to this record
 
 
Author Zhijie Fang; Antonio Lopez
Title Is the Pedestrian going to Cross? Answering by 2D Pose Estimation Type Conference Article
Year 2018 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal
Volume Issue Pages 1271 - 1276
Keywords (up)
Abstract Our recent work suggests that, thanks to nowadays powerful CNNs, image-based 2D pose estimation is a promising cue for determining pedestrian intentions such as crossing the road in the path of the ego-vehicle, stopping before entering the road, and starting to walk or bending towards the road. This statement is based on the results obtained on non-naturalistic sequences (Daimler dataset), i.e. in sequences choreographed specifically for performing the study. Fortunately, a new publicly available dataset (JAAD) has appeared recently to allow developing methods for detecting pedestrian intentions in naturalistic driving conditions; more specifically, for addressing the relevant question is the pedestrian going to cross? Accordingly, in this paper we use JAAD to assess the usefulness of 2D pose estimation for answering such a question. We combine CNN-based pedestrian detection, tracking and pose estimation to predict the crossing action from monocular images. Overall, the proposed pipeline provides new state-ofthe-art results.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IV
Notes ADAS; 600.124; 600.116; 600.118 Approved no
Call Number Admin @ si @ FaL2018 Serial 3181
Permanent link to this record
 
 
Author Jiaolong Xu; Peng Wang; Heng Yang; Antonio Lopez
Title Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving Type Conference Article
Year 2019 Publication IEEE International Conference on Robotics and Automation Abbreviated Journal
Volume Issue Pages 2379-2384
Keywords (up)
Abstract Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection. Recent deep convolutional neural network based object detectors have achieved state-of-the-art accuracy. However, such models are trained with numerous parameters and their high computational costs and large storage prohibit the deployment to memory and computation resource limited systems. Low-precision neural networks are popular techniques for reducing the computation requirements and memory footprint. Among them, binary weight neural network (BWN) is the extreme case which quantizes the float-point into just bit. BWNs are difficult to train and suffer from accuracy deprecation due to the extreme low-bit representation. To address this problem, we propose a knowledge transfer (KT) method to aid the training of BWN using a full-precision teacher network. We built DarkNet-and MobileNet-based binary weight YOLO-v2 detectors and conduct experiments on KITTI benchmark for car, pedestrian and cyclist detection. The experimental results show that the proposed method maintains high detection accuracy while reducing the model size of DarkNet-YOLO from 257 MB to 8.8 MB and MobileNet-YOLO from 193 MB to 7.9 MB.
Address Montreal; Canada; May 2019
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICRA
Notes ADAS; 600.124; 600.116; 600.118 Approved no
Call Number Admin @ si @ XWY2018 Serial 3182
Permanent link to this record
 
 
Author Akhil Gurram; Onay Urfalioglu; Ibrahim Halfaoui; Fahd Bouzaraa; Antonio Lopez
Title Monocular Depth Estimation by Learning from Heterogeneous Datasets Type Conference Article
Year 2018 Publication IEEE Intelligent Vehicles Symposium Abbreviated Journal
Volume Issue Pages 2176 - 2181
Keywords (up)
Abstract Depth estimation provides essential information to perform autonomous driving and driver assistance. Especially, Monocular Depth Estimation is interesting from a practical point of view, since using a single camera is cheaper than many other options and avoids the need for continuous calibration strategies as required by stereo-vision approaches. State-of-the-art methods for Monocular Depth Estimation are based on Convolutional Neural Networks (CNNs). A promising line of work consists of introducing additional semantic information about the traffic scene when training CNNs for depth estimation. In practice, this means that the depth data used for CNN training is complemented with images having pixel-wise semantic labels, which usually are difficult to annotate (eg crowded urban images). Moreover, so far it is common practice to assume that the same raw training data is associated with both types of ground truth, ie, depth and semantic labels. The main contribution of this paper is to show that this hard constraint can be circumvented, ie, that we can train CNNs for depth estimation by leveraging the depth and semantic information coming from heterogeneous datasets. In order to illustrate the benefits of our approach, we combine KITTI depth and Cityscapes semantic segmentation datasets, outperforming state-of-the-art results on Monocular Depth Estimation.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference IV
Notes ADAS; 600.124; 600.116; 600.118 Approved no
Call Number Admin @ si @ GUH2018 Serial 3183
Permanent link to this record
 
 
Author Alejandro Cartas; Estefania Talavera; Petia Radeva; Mariella Dimiccoli
Title On the Role of Event Boundaries in Egocentric Activity Recognition from Photostreams Type Miscellaneous
Year 2018 Publication Arxiv Abbreviated Journal
Volume Issue Pages
Keywords (up)
Abstract Event boundaries play a crucial role as a pre-processing step for detection, localization, and recognition tasks of human activities in videos. Typically, although their intrinsic subjectiveness, temporal bounds are provided manually as input for training action recognition algorithms. However, their role for activity recognition in the domain of egocentric photostreams has been so far neglected. In this paper, we provide insights of how automatically computed boundaries can impact activity recognition results in the emerging domain of egocentric photostreams. Furthermore, we collected a new annotated dataset acquired by 15 people by a wearable photo-camera and we used it to show the generalization capabilities of several deep learning based architectures to unseen users.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes MILAB; no proj Approved no
Call Number Admin @ si @ CTR2018 Serial 3184
Permanent link to this record
 
 
Author Md. Mostafa Kamal Sarker; Hatem A. Rashwan; Hatem A. Rashwan; Estefania Talavera; Syeda Furruka Banu; Petia Radeva; Domenec Puig
Title MACNet: Multi-scale Atrous Convolution Networks for Food Places Classification in Egocentric Photo-streams Type Conference Article
Year 2018 Publication European Conference on Computer Vision workshops Abbreviated Journal
Volume Issue Pages 423-433
Keywords (up)
Abstract First-person (wearable) camera continually captures unscripted interactions of the camera user with objects, people, and scenes reflecting his personal and relational tendencies. One of the preferences of people is their interaction with food events. The regulation of food intake and its duration has a great importance to protect against diseases. Consequently, this work aims to develop a smart model that is able to determine the recurrences of a person on food places during a day. This model is based on a deep end-to-end model for automatic food places recognition by analyzing egocentric photo-streams. In this paper, we apply multi-scale Atrous convolution networks to extract the key features related to food places of the input images. The proposed model is evaluated on an in-house private dataset called “EgoFoodPlaces”. Experimental results shows promising results of food places classification recognition in egocentric photo-streams.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LCNS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ECCVW
Notes MILAB; no menciona Approved no
Call Number Admin @ si @ SRR2018b Serial 3185
Permanent link to this record
 
 
Author Mariella Dimiccoli; Cathal Gurrin; David J. Crandall; Xavier Giro; Petia Radeva
Title Introduction to the special issue: Egocentric Vision and Lifelogging Type Journal Article
Year 2018 Publication Journal of Visual Communication and Image Representation Abbreviated Journal JVCIR
Volume 55 Issue Pages 352-353
Keywords (up)
Abstract
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes MILAB; no proj Approved no
Call Number Admin @ si @ DGC2018 Serial 3187
Permanent link to this record
 
 
Author L. Rothacker; Marçal Rusiñol; Josep Llados; G.A. Fink
Title A Two-stage Approach to Segmentation-Free Query-by-example Word Spotting Type Journal
Year 2014 Publication Manuscript Cultures Abbreviated Journal
Volume 7 Issue Pages 47-58
Keywords (up)
Abstract With the ongoing progress in digitization, huge document collections and archives have become available to a broad audience. Scanned document images can be transmitted electronically and studied simultaneously throughout the world. While this is very beneficial, it is often impossible to perform automated searches on these document collections. Optical character recognition usually fails when it comes to handwritten or historic documents. In order to address the need for exploring document collections rapidly, researchers are working on word spotting. In query-by-example word spotting scenarios, the user selects an exemplary occurrence of the query word in a document image. The word spotting system then retrieves all regions in the collection that are visually similar to the given example of the query word. The best matching regions are presented to the user and no actual transcription is required.
An important property of a word spotting system is the computational speed with which queries can be executed. In our previous work, we presented a relatively slow but high-precision method. In the present work, we will extend this baseline system to an integrated two-stage approach. In a coarse-grained first stage, we will filter document images efficiently in order to identify regions that are likely to contain the query word. In the fine-grained second stage, these regions will be analyzed with our previously presented high-precision method. Finally, we will report recognition results and query times for the well-known George Washington
benchmark in our evaluation. We achieve state-of-the-art recognition results while the query times can be reduced to 50% in comparison with our baseline.
Address
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference
Notes DAG; 600.061; 600.077 Approved no
Call Number Admin @ si @ Serial 3190
Permanent link to this record
 
 
Author Patricia Suarez; Angel Sappa; Boris X. Vintimilla
Title Vegetation Index Estimation from Monospectral Images Type Conference Article
Year 2018 Publication 15th International Conference on Images Analysis and Recognition Abbreviated Journal
Volume 10882 Issue Pages 353-362
Keywords (up)
Abstract This paper proposes a novel approach to estimate Normalized Difference Vegetation Index (NDVI) from just the red channel of a RGB image. The NDVI index is defined as the ratio of the difference of the red and infrared radiances over their sum. In other words, information from the red channel of a RGB image and the corresponding infrared spectral band are required for its computation. In the current work the NDVI index is estimated just from the red channel by training a Conditional Generative Adversarial Network (CGAN). The architecture proposed for the generative network consists of a single level structure, which combines at the final layer results from convolutional operations together with the given red channel with Gaussian noise to enhance
details, resulting in a sharp NDVI image. Then, the discriminative model
estimates the probability that the NDVI generated index came from the training dataset, rather than the index automatically generated. Experimental results with a large set of real images are provided showing that a Conditional GAN single level model represents an acceptable approach to estimate NDVI index.
Address Povoa de Varzim; Portugal; June 2018
Corporate Author Thesis
Publisher Place of Publication Editor
Language Summary Language Original Title
Series Editor Series Title Abbreviated Series Title LNCS
Series Volume Series Issue Edition
ISSN ISBN Medium
Area Expedition Conference ICIAR
Notes MSIAU; 600.086; 600.130; 600.122 Approved no
Call Number Admin @ si @ SSV2018c Serial 3196
Permanent link to this record