Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	46–60 of 157 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

<< 1 2 3 4 5 6 7 8 9 10 >> [11–11]

List View

Citations

Details

	Records
	Author	Xinhang Song; Shuqiang Jiang; Luis Herranz
	Title	Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold			Type	Journal Article
	Year	2017	Publication	IEEE Transactions on Image Processing	Abbreviated Journal	TIP
	Volume	26	Issue	6	Pages	2721-2735
	Keywords
	Abstract	Before the big data era, scene recognition was often approached with two-step inference using localized intermediate representations (objects, topics, and so on). One of such approaches is the semantic manifold (SM), in which patches and images are modeled as points in a semantic probability simplex. Patch models are learned resorting to weak supervision via image labels, which leads to the problem of scene categories co-occurring in this semantic space. Fortunately, each category has its own co-occurrence patterns that are consistent across the images in that category. Thus, discovering and modeling these patterns are critical to improve the recognition performance in this representation. Since the emergence of large data sets, such as ImageNet and Places, these approaches have been relegated in favor of the much more powerful convolutional neural networks (CNNs), which can automatically learn multi-layered representations from the data. In this paper, we address many limitations of the original SM approach and related works. We propose discriminative patch representations using neural networks and further propose a hybrid architecture in which the semantic manifold is built on top of multiscale CNNs. Both representations can be computed significantly faster than the Gaussian mixture models of the original SM. To combine multiple scales, spatial relations, and multiple features, we formulate rich context models using Markov random fields. To solve the optimization problem, we analyze global and local approaches, where a top-down hierarchical algorithm has the best performance. Experimental results show that exploiting different types of contextual relations jointly consistently improves the recognition accuracy.
	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	LAMP; 600.120			Approved	no
	Call Number	Admin @ si @ SJH2017a			Serial	2963
Permanent link to this record



	Author	E. Royer; J. Chazalon; Marçal Rusiñol; F. Bouchara
	Title	Benchmarking Keypoint Filtering Approaches for Document Image Matching			Type	Conference Article
	Year	2017	Publication	14th International Conference on Document Analysis and Recognition	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Best Poster Award. Reducing the amount of keypoints used to index an image is particularly interesting to control processing time and memory usage in real-time document image matching applications, like augmented documents or smartphone applications. This paper benchmarks two keypoint selection methods on a task consisting of reducing keypoint sets extracted from document images, while preserving detection and segmentation accuracy. We first study the different forms of keypoint filtering, and we introduce the use of the CORE selection method on keypoints extracted from document images. Then, we extend a previously published benchmark by including evaluations of the new method, by adding the SURF-BRISK detection/description scheme, and by reporting processing speeds. Evaluations are conducted on the publicly available dataset of ICDAR2015 SmartDOC challenge 1. Finally, we prove that reducing the original keypoint set is always feasible and can be beneficial not only to processing speed but also to accuracy.
	Address	Kyoto; Japan; November 2017
	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	ICDAR
	Notes	DAG; 600.084; 600.121			Approved	no
	Call Number	Admin @ si @ RCR2017			Serial	3000
Permanent link to this record



	Author	Carles Sanchez; Antonio Esteban Lansaque; Agnes Borras; Marta Diez-Ferrer; Antoni Rosell; Debora Gil
	Title	Towards a Videobronchoscopy Localization System from Airway Centre Tracking			Type	Conference Article
	Year	2017	Publication	12th International Conference on Computer Vision Theory and Applications	Abbreviated Journal
	Volume		Issue		Pages	352-359
	Keywords	Video-bronchoscopy; Lung cancer diagnosis; Airway lumen detection; Region tracking; Guided bronchoscopy navigation
	Abstract	Bronchoscopists use fluoroscopy to guide flexible bronchoscopy to the lesion to be biopsied without any kind of incision. Being fluoroscopy an imaging technique based on X-rays, the risk of developmental problems and cancer is increased in those subjects exposed to its application, so minimizing radiation is crucial. Alternative guiding systems such as electromagnetic navigation require specific equipment, increase the cost of the clinical procedure and still require fluoroscopy. In this paper we propose an image based guiding system based on the extraction of airway centres from intra-operative videos. Such anatomical landmarks are matched to the airway centreline extracted from a pre-planned CT to indicate the best path to the nodule. We present a feasibility study of our navigation system using simulated bronchoscopic videos and a multi-expert validation of landmarks extraction in 3 intra-operative ultrathin explorations.
	Address	Porto; Portugal; February 2017
	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	VISAPP
	Notes	IAM; 600.096; 600.075; 600.145			Approved	no
	Call Number	Admin @ si @ SEB2017			Serial	2943
Permanent link to this record



	Author	Karim Lekadir; Alfiia Galimzianova; Angels Betriu; Maria del Mar Vila; Laura Igual; Daniel L. Rubin; Elvira Fernandez-Giraldez; Petia Radeva; Sandy Napel
	Title	A Convolutional Neural Network for Automatic Characterization of Plaque Composition in Carotid Ultrasound			Type	Journal Article
	Year	2017	Publication	IEEE Journal Biomedical and Health Informatics	Abbreviated Journal	J-BHI
	Volume	21	Issue	1	Pages	48-55
	Keywords
	Abstract	Characterization of carotid plaque composition, more specifically the amount of lipid core, fibrous tissue, and calcified tissue, is an important task for the identification of plaques that are prone to rupture, and thus for early risk estimation of cardiovascular and cerebrovascular events. Due to its low costs and wide availability, carotid ultrasound has the potential to become the modality of choice for plaque characterization in clinical practice. However, its significant image noise, coupled with the small size of the plaques and their complex appearance, makes it difficult for automated techniques to discriminate between the different plaque constituents. In this paper, we propose to address this challenging problem by exploiting the unique capabilities of the emerging deep learning framework. More specifically, and unlike existing works which require a priori definition of specific imaging features or thresholding values, we propose to build a convolutional neural network (CNN) that will automatically extract from the images the information that is optimal for the identification of the different plaque constituents. We used approximately 90 000 patches extracted from a database of images and corresponding expert plaque characterizations to train and to validate the proposed CNN. The results of cross-validation experiments show a correlation of about 0.90 with the clinical assessment for the estimation of lipid core, fibrous cap, and calcified tissue areas, indicating the potential of deep learning for the challenging task of automatic characterization of plaque composition in carotid ultrasound.
	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 menciona			Approved	no
	Call Number	Admin @ si @ LGB2017			Serial	2931
Permanent link to this record



	Author	Jorge Bernal; Nima Tajkbaksh; F. Javier Sanchez; Bogdan J. Matuszewski; Hao Chen; Lequan Yu; Quentin Angermann; Olivier Romain; Bjorn Rustad; Ilangko Balasingham; Konstantin Pogorelov; Sungbin Choi; Quentin Debard; Lena Maier Hein; Stefanie Speidel; Danail Stoyanov; Patrick Brandao; Henry Cordova; Cristina Sanchez Montes; Suryakanth R. Gurudu; Gloria Fernandez Esparrach; Xavier Dray; Jianming Liang; Aymeric Histace
	Title	Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results from the MICCAI 2015 Endoscopic Vision Challenge			Type	Journal Article
	Year	2017	Publication	IEEE Transactions on Medical Imaging	Abbreviated Journal	TMI
	Volume	36	Issue	6	Pages	1231 - 1249
	Keywords	Endoscopic vision; Polyp Detection; Handcrafted features; Machine Learning; Validation Framework
	Abstract	Colonoscopy is the gold standard for colon cancer screening though still some polyps are missed, thus preventing early disease detection and treatment. Several computational systems have been proposed to assist polyp detection during colonoscopy but so far without consistent evaluation. The lack of publicly available annotated databases has made it difficult to compare methods and to assess if they achieve performance levels acceptable for clinical use. The Automatic Polyp Detection subchallenge, conducted as part of the Endoscopic Vision Challenge (http://endovis.grand-challenge.org) at the international conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2015, was an effort to address this need. In this paper, we report the results of this comparative evaluation of polyp detection methods, as well as describe additional experiments to further explore differences between methods. We define performance metrics and provide evaluation databases that allow comparison of multiple methodologies. Results show that convolutional neural networks (CNNs) are the state of the art. Nevertheless it is also demonstrated that combining different methodologies can lead to an improved overall performance.
	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	MV; 600.096; 600.075			Approved	no
	Call Number	Admin @ si @ BTS2017			Serial	2949
Permanent link to this record



	Author	David Vazquez; Jorge Bernal; F. Javier Sanchez; Gloria Fernandez Esparrach; Antonio Lopez; Adriana Romero; Michal Drozdzal; Aaron Courville
	Title	A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images			Type	Journal Article
	Year	2017	Publication	Journal of Healthcare Engineering	Abbreviated Journal	JHCE
	Volume		Issue		Pages	2040-2295
	Keywords	Colonoscopy images; Deep Learning; Semantic Segmentation
	Abstract	Colorectal cancer (CRC) is the third cause of cancer death world-wide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for polyps and colonoscopy is the screening tool of choice. The main limitations of this screening procedure are polyp miss- rate and inability to perform visual assessment of polyp malignancy. These drawbacks can be reduced by designing Decision Support Systems (DSS) aim- ing to help clinicians in the different stages of the procedure by providing endoluminal scene segmentation. Thus, in this paper, we introduce an extended benchmark of colonoscopy image segmentation, with the hope of establishing a new strong benchmark for colonoscopy image analysis research. The proposed dataset consists of 4 relevant classes to inspect the endolumninal scene, tar- geting different clinical needs. Together with the dataset and taking advantage of advances in semantic segmentation literature, we provide new baselines by training standard fully convolutional networks (FCN). We perform a compar- ative study to show that FCN significantly outperform, without any further post-processing, prior results in endoluminal scene segmentation, especially with respect to polyp segmentation and localization.
	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; MV; 600.075; 600.085; 600.076; 601.281; 600.118			Approved	no
	Call Number	VBS2017b			Serial	2940
Permanent link to this record



	Author	David Vazquez; Jorge Bernal; F. Javier Sanchez; Gloria Fernandez Esparrach; Antonio Lopez; Adriana Romero; Michal Drozdzal; Aaron Courville
	Title	A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images			Type	Conference Article
	Year	2017	Publication	31st International Congress and Exhibition on Computer Assisted Radiology and Surgery	Abbreviated Journal
	Volume		Issue		Pages
	Keywords	Deep Learning; Medical Imaging
	Abstract	Colorectal cancer (CRC) is the third cause of cancer death worldwide. Currently, the standard approach to reduce CRC-related mortality is to perform regular screening in search for polyps and colonoscopy is the screening tool of choice. The main limitations of this screening procedure are polyp miss-rate and inability to perform visual assessment of polyp malignancy. These drawbacks can be reduced by designing Decision Support Systems (DSS) aiming to help clinicians in the different stages of the procedure by providing endoluminal scene segmentation. Thus, in this paper, we introduce an extended benchmark of colonoscopy image, with the hope of establishing a new strong benchmark for colonoscopy image analysis research. We provide new baselines on this dataset by training standard fully convolutional networks (FCN) for semantic segmentation and significantly outperforming, without any further post-processing, prior results in endoluminal scene segmentation.
	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	CARS
	Notes	ADAS; MV; 600.075; 600.085; 600.076; 601.281; 600.118			Approved	no
	Call Number	ADAS @ adas @ VBS2017a			Serial	2880
Permanent link to this record



	Author	Quentin Angermann; Jorge Bernal; Cristina Sanchez Montes; Gloria Fernandez Esparrach; Xavier Gray; Olivier Romain; F. Javier Sanchez; Aymeric Histace
	Title	Towards Real-Time Polyp Detection in Colonoscopy Videos: Adapting Still Frame-Based Methodologies for Video Sequences Analysis			Type	Conference Article
	Year	2017	Publication	4th International Workshop on Computer Assisted and Robotic Endoscopy	Abbreviated Journal
	Volume		Issue		Pages	29-41
	Keywords	Polyp detection; colonoscopy; real time; spatio temporal coherence
	Abstract	Colorectal cancer is the second cause of cancer death in United States: precursor lesions (polyps) detection is key for patient survival. Though colonoscopy is the gold standard screening tool, some polyps are still missed. Several computational systems have been proposed but none of them are used in the clinical room mainly due to computational constraints. Besides, most of them are built over still frame databases, decreasing their performance on video analysis due to the lack of output stability and not coping with associated variability on image quality and polyp appearance. We propose a strategy to adapt these methods to video analysis by adding a spatio-temporal stability module and studying a combination of features to capture polyp appearance variability. We validate our strategy, incorporated on a real-time detection method, on a public video database. Resulting method detects all polyps under real time constraints, increasing its performance due to our adaptation strategy.
	Address	Quebec; Canada; September 2017
	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	CARE
	Notes	MV; 600.096; 600.075			Approved	no
	Call Number	Admin @ si @ ABS2017b			Serial	2977
Permanent link to this record



	Author	Antonio Lopez; Gabriel Villalonga; Laura Sellart; German Ros; David Vazquez; Jiaolong Xu; Javier Marin; Azadeh S. Mozafari
	Title	Training my car to see using virtual worlds			Type	Journal Article
	Year	2017	Publication	Image and Vision Computing	Abbreviated Journal	IMAVIS
	Volume	38	Issue		Pages	102-118
	Keywords
	Abstract	Computer vision technologies are at the core of different advanced driver assistance systems (ADAS) and will play a key role in oncoming autonomous vehicles too. One of the main challenges for such technologies is to perceive the driving environment, i.e. to detect and track relevant driving information in a reliable manner (e.g. pedestrians in the vehicle route, free space to drive through). Nowadays it is clear that machine learning techniques are essential for developing such a visual perception for driving. In particular, the standard working pipeline consists of collecting data (i.e. on-board images), manually annotating the data (e.g. drawing bounding boxes around pedestrians), learning a discriminative data representation taking advantage of such annotations (e.g. a deformable part-based model, a deep convolutional neural network), and then assessing the reliability of such representation with the acquired data. In the last two decades most of the research efforts focused on representation learning (first, designing descriptors and learning classifiers; later doing it end-to-end). Hence, collecting data and, especially, annotating it, is essential for learning good representations. While this has been the case from the very beginning, only after the disruptive appearance of deep convolutional neural networks that it became a serious issue due to their data hungry nature. In this context, the problem is that manual data annotation is a tiresome work prone to errors. Accordingly, in the late 00’s we initiated a research line consisting of training visual models using photo-realistic computer graphics, especially focusing on assisted and autonomous driving. In this paper, we summarize such a work and show how it has become a new tendency with increasing acceptance.
	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 @ LVS2017			Serial	2985
Permanent link to this record



	Author	Debora Gil; Oriol Ramos Terrades; Elisa Minchole; Carles Sanchez; Noelia Cubero de Frutos; Marta Diez-Ferrer; Rosa Maria Ortiz; Antoni Rosell
	Title	Classification of Confocal Endomicroscopy Patterns for Diagnosis of Lung Cancer			Type	Conference Article
	Year	2017	Publication	6th Workshop on Clinical Image-based Procedures: Translational Research in Medical Imaging	Abbreviated Journal
	Volume	10550	Issue		Pages	151-159
	Keywords
	Abstract	Confocal Laser Endomicroscopy (CLE) is an emerging imaging technique that allows the in-vivo acquisition of cell patterns of potentially malignant lesions. Such patterns could discriminate between inflammatory and neoplastic lesions and, thus, serve as a first in-vivo biopsy to discard cases that do not actually require a cell biopsy. The goal of this work is to explore whether CLE images obtained during videobronchoscopy contain enough visual information to discriminate between benign and malign peripheral lesions for lung cancer diagnosis. To do so, we have performed a pilot comparative study with 12 patients (6 adenocarcinoma and 6 benign-inflammatory) using 2 different methods for CLE pattern analysis: visual analysis by 3 experts and a novel methodology that uses graph methods to find patterns in pre-trained feature spaces. Our preliminary results indicate that although visual analysis can only achieve a 60.2% of accuracy, the accuracy of the proposed unsupervised image pattern classification raises to 84.6%. We conclude that CLE images visual information allow in-vivo detection of neoplastic lesions and graph structural analysis applied to deep-learning feature spaces can achieve competitive results.
	Address	Quebec; Canada; September 2017
	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	CLIP
	Notes	IAM; 600.096; 600.075; 600.145			Approved	no
	Call Number	Admin @ si @ GRM2017			Serial	2957
Permanent link to this record



	Author	Rosa Maria Ortiz; Debora Gil; Elisa Minchole; Marta Diez-Ferrer; Noelia Cubero de Frutos
	Title	Classification of Confolcal Endomicroscopy Patterns for Diagnosis of Lung Cancer			Type	Conference Article
	Year	2017	Publication	18th World Conference on Lung Cancer	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Confocal Laser Endomicroscopy (CLE) is an emerging imaging technique that allows the in-vivo acquisition of cell patterns of potentially malignant lesions. Such patterns could discriminate between inflammatory and neoplastic lesions and, thus, serve as a first in-vivo biopsy to discard cases that do not actually require a cell biopsy. The goal of this work is to explore whether CLE images obtained during videobronchoscopy contain enough visual information to discriminate between benign and malign peripheral lesions for lung cancer diagnosis. To do so, we have performed a pilot comparative study with 12 patients (6 adenocarcinoma and 6 benign-inflammatory) using 2 different methods for CLE pattern analysis: visual analysis by 3 experts and a novel methodology that uses graph methods to find patterns in pre-trained feature spaces. Our preliminary results indicate that although visual analysis can only achieve a 60.2% of accuracy, the accuracy of the proposed unsupervised image pattern classification raises to 84.6%. We conclude that CLE images visual information allow in-vivo detection of neoplastic lesions and graph structural analysis applied to deep-learning feature spaces can achieve competitive results.
	Address	Yokohama; Japan; October 2017
	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	IASLC WCLC
	Notes	IAM; 600.096; 600.075; 600.145			Approved	no
	Call Number	Admin @ si @ OGM2017			Serial	3044
Permanent link to this record



	Author	Ivet Rafegas; Maria Vanrell
	Title	Color representation in CNNs: parallelisms with biological vision			Type	Conference Article
	Year	2017	Publication	ICCV Workshop on Mutual Benefits ofr Cognitive and Computer Vision	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Convolutional Neural Networks (CNNs) trained for object recognition tasks present representational capabilities approaching to primate visual systems [1]. This provides a computational framework to explore how image features are efficiently represented. Here, we dissect a trained CNN [2] to study how color is represented. We use a classical methodology used in physiology that is measuring index of selectivity of individual neurons to specific features. We use ImageNet Dataset [20] images and synthetic versions of them to quantify color tuning properties of artificial neurons to provide a classification of the network population. We conclude three main levels of color representation showing some parallelisms with biological visual systems: (a) a decomposition in a circular hue space to represent single color regions with a wider hue sampling beyond the first layer (V2), (b) the emergence of opponent low-dimensional spaces in early stages to represent color edges (V1); and (c) a strong entanglement between color and shape patterns representing object-parts (e.g. wheel of a car), objectshapes (e.g. faces) or object-surrounds configurations (e.g. blue sky surrounding an object) in deeper layers (V4 or IT).
	Address	Venice; Italy; October 2017
	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	ICCV-MBCC
	Notes	CIC; 600.087; 600.051			Approved	no
	Call Number	Admin @ si @ RaV2017			Serial	2984
Permanent link to this record



	Author	Cesar de Souza; Adrien Gaidon; Yohann Cabon; Antonio Lopez
	Title	Procedural Generation of Videos to Train Deep Action Recognition Networks			Type	Conference Article
	Year	2017	Publication	30th IEEE Conference on Computer Vision and Pattern Recognition	Abbreviated Journal
	Volume		Issue		Pages	2594-2604
	Keywords
	Abstract	Deep learning for human action recognition in videos is making significant progress, but is slowed down by its dependency on expensive manual labeling of large video collections. In this work, we investigate the generation of synthetic training data for action recognition, as it has recently shown promising results for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation and other computer graphics techniques of modern game engines. We generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for ”Procedural Human Action Videos”. It contains a total of 39, 982 videos, with more than 1, 000 examples for each action of 35 categories. Our approach is not limited to existing motion capture sequences, and we procedurally define 14 synthetic actions. We introduce a deep multi-task representation learning architecture to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF101 and HMDB51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, significantly outperforming fine-tuning state-of-the-art unsupervised generative models of videos.
	Address	Honolulu; Hawaii; July 2017
	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	CVPR
	Notes	ADAS; 600.076; 600.085; 600.118			Approved	no
	Call Number	Admin @ si @ SGC2017			Serial	3051
Permanent link to this record



	Author	Marc Masana; Joost Van de Weijer; Luis Herranz;Andrew Bagdanov; Jose Manuel Alvarez
	Title	Domain-adaptive deep network compression			Type	Conference Article
	Year	2017	Publication	17th IEEE International Conference on Computer Vision	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. This has the advantage that representations learned in the large source domain can be exploited on smaller target domains. However, networks designed to be optimal for the source task are often prohibitively large for the target task. In this work we address the compression of networks after domain transfer. We focus on compression algorithms based on low-rank matrix decomposition. Existing methods base compression solely on learned network weights and ignore the statistics of network activations. We show that domain transfer leads to large shifts in network activations and that it is desirable to take this into account when compressing. We demonstrate that considering activation statistics when compressing weights leads to a rank-constrained regression problem with a closed-form solution. Because our method takes into account the target domain, it can more optimally remove the redundancy in the weights. Experiments show that our Domain Adaptive Low Rank (DALR) method significantly outperforms existing low-rank compression techniques. With our approach, the fc6 layer of VGG19 can be compressed more than 4x more than using truncated SVD alone – with only a minor or no loss in accuracy. When applied to domain-transferred networks it allows for compression down to only 5-20% of the original number of parameters with only a minor drop in performance.
	Address	Venice; Italy; October 2017
	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	ICCV
	Notes	LAMP; 601.305; 600.106; 600.120			Approved	no
	Call Number	Admin @ si @			Serial	3034
Permanent link to this record



	Author	Xinhang Song; Shuqiang Jiang; Luis Herranz
	Title	Combining Models from Multiple Sources for RGB-D Scene Recognition			Type	Conference Article
	Year	2017	Publication	26th International Joint Conference on Artificial Intelligence	Abbreviated Journal
	Volume		Issue		Pages	4523-4529
	Keywords	Robotics and Vision; Vision and Perception
	Abstract	Depth can complement RGB with useful cues about object volumes and scene layout. However, RGB-D image datasets are still too small for directly training deep convolutional neural networks (CNNs), in contrast to the massive monomodal RGB datasets. Previous works in RGB-D recognition typically combine two separate networks for RGB and depth data, pretrained with a large RGB dataset and then fine tuned to the respective target RGB and depth datasets. These approaches have several limitations: 1) only use low-level filters learned from RGB data, thus not being able to exploit properly depth-specific patterns, and 2) RGB and depth features are only combined at high-levels but rarely at lower-levels. In this paper, we propose a framework that leverages both knowledge acquired from large RGB datasets together with depth-specific cues learned from the limited depth data, obtaining more effective multi-source and multi-modal representations. We propose a multi-modal combination method that selects discriminative combinations of layers from the different source models and target modalities, capturing both high-level properties of the task and intrinsic low-level properties of both modalities.
	Address	Melbourne; Australia; August 2017
	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	IJCAI
	Notes	LAMP; 600.120			Approved	no
	Call Number	Admin @ si @ SJH2017b			Serial	2966
Permanent link to this record