Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	286–300 of 1420 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

[1–10] << 11 12 13 14 15 16 17 18 19 20 >> [21–30]

List View

Citations

Details

	Records
	Author	Alejandro Cartas; Jordi Luque; Petia Radeva; Carlos Segura; Mariella Dimiccoli
	Title	Seeing and Hearing Egocentric Actions: How Much Can We Learn?			Type	Conference Article
	Year	2019	Publication	IEEE International Conference on Computer Vision Workshops	Abbreviated Journal
	Volume		Issue		Pages	4470-4480
	Keywords
	Abstract	Our interaction with the world is an inherently multimodal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a single modality. In particular, a limited number of works have considered to integrate the visual and audio modalities for this purpose. In this work, we propose a multimodal approach for egocentric action recognition in a kitchen environment that relies on audio and visual information. Our model combines a sparse temporal sampling strategy with a late fusion of audio, spatial, and temporal streams. Experimental results on the EPIC-Kitchens dataset show that multimodal integration leads to better performance than unimodal approaches. In particular, we achieved a 5.18% improvement over the state of the art on verb classification.
	Address	Seul; Korea; October 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	ICCVW
	Notes	MILAB; no proj			Approved	no
	Call Number	Admin @ si @ CLR2019b			Serial	3385
Permanent link to this record



	Author	Chee-Kheng Chng; Yuliang Liu; Yipeng Sun; Chun Chet Ng; Canjie Luo; Zihan Ni; ChuanMing Fang; Shuaitao Zhang; Junyu Han; Errui Ding; Jingtuo Liu; Dimosthenis Karatzas; Chee Seng Chan; Lianwen Jin
	Title	ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text – RRC-ArT			Type	Conference Article
	Year	2019	Publication	15th International Conference on Document Analysis and Recognition	Abbreviated Journal
	Volume		Issue		Pages	1571-1576
	Keywords
	Abstract	This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text – RRC-ArT that consists of three major challenges: i) scene text detection, ii) scene text recognition, and iii) scene text spotting. A total of 78 submissions from 46 unique teams/individuals were received for this competition. The top performing score of each challenge is as follows: i) T1 – 82.65%, ii) T2.1 – 74.3%, iii) T2.2 – 85.32%, iv) T3.1 – 53.86%, and v) T3.2 – 54.91%. Apart from the results, this paper also details the ArT dataset, tasks description, evaluation metrics and participants' methods. The dataset, the evaluation kit as well as the results are publicly available at the challenge website.
	Address	Sydney; Australia; September 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	ICDAR
	Notes	DAG; 600.121; 600.129			Approved	no
	Call Number	Admin @ si @ CLS2019			Serial	3340
Permanent link to this record



	Author	Ciprian Corneanu; Meysam Madadi; Sergio Escalera
	Title	Deep Structure Inference Network for Facial Action Unit Recognition			Type	Conference Article
	Year	2018	Publication	15th European Conference on Computer Vision	Abbreviated Journal
	Volume	11216	Issue		Pages	309-324
	Keywords	Computer Vision; Machine Learning; Deep Learning; Facial Expression Analysis; Facial Action Units; Structure Inference
	Abstract	Facial expressions are combinations of basic components called Action Units (AU). Recognizing AUs is key for general facial expression analysis. Recently, efforts in automatic AU recognition have been dedicated to learning combinations of local features and to exploiting correlations between AUs. We propose a deep neural architecture that tackles both problems by combining learned local and global features in its initial stages and replicating a message passing algorithm between classes similar to a graphical model inference approach in later stages. We show that by training the model end-to-end with increased supervision we improve state-of-the-art by 5.3% and 8.2% performance on BP4D and DISFA datasets, respectively.
	Address	Munich; 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	ECCV
	Notes	HUPBA; no proj			Approved	no
	Call Number	Admin @ si @ CME2018			Serial	3205
Permanent link to this record



	Author	Ciprian Corneanu; Meysam Madadi; Sergio Escalera; Aleix M. Martinez
	Title	What does it mean to learn in deep networks? And, how does one detect adversarial attacks?			Type	Conference Article
	Year	2019	Publication	32nd IEEE Conference on Computer Vision and Pattern Recognition	Abbreviated Journal
	Volume		Issue		Pages	4752-4761
	Keywords
	Abstract	The flexibility and high-accuracy of Deep Neural Networks (DNNs) has transformed computer vision. But, the fact that we do not know when a specific DNN will work and when it will fail has resulted in a lack of trust. A clear example is self-driving cars; people are uncomfortable sitting in a car driven by algorithms that may fail under some unknown, unpredictable conditions. Interpretability and explainability approaches attempt to address this by uncovering what a DNN models, i.e., what each node (cell) in the network represents and what images are most likely to activate it. This can be used to generate, for example, adversarial attacks. But these approaches do not generally allow us to determine where a DNN will succeed or fail and why. i.e., does this learned representation generalize to unseen samples? Here, we derive a novel approach to define what it means to learn in deep networks, and how to use this knowledge to detect adversarial attacks. We show how this defines the ability of a network to generalize to unseen testing samples and, most importantly, why this is the case.
	Address	California; June 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	CVPR
	Notes	HuPBA; no proj			Approved	no
	Call Number	Admin @ si @ CME2019			Serial	3332
Permanent link to this record



	Author	Ciprian Corneanu; Meysam Madadi; Sergio Escalera; Aleix Martinez
	Title	Explainable Early Stopping for Action Unit Recognition			Type	Conference Article
	Year	2020	Publication	Faces and Gestures in E-health and welfare workshop	Abbreviated Journal
	Volume		Issue		Pages	693-699
	Keywords
	Abstract	A common technique to avoid overfitting when training deep neural networks (DNN) is to monitor the performance in a dedicated validation data partition and to stop training as soon as it saturates. This only focuses on what the model does, while completely ignoring what happens inside it. In this work, we open the “black-box” of DNN in order to perform early stopping. We propose to use a novel theoretical framework that analyses meso-scale patterns in the topology of the functional graph of a network while it trains. Based on it, we decide when it transitions from learning towards overfitting in a more explainable way. We exemplify the benefits of this approach on a state-of-the art custom DNN that jointly learns local representations and label structure employing an ensemble of dedicated subnetworks. We show that it is practically equivalent in performance to early stopping with patience, the standard early stopping algorithm in the literature. This proves beneficial for AU recognition performance and provides new insights into how learning of AUs occurs in DNNs.
	Address	Virtual; November 2020
	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	FGW
	Notes	HUPBA;			Approved	no
	Call Number	Admin @ si @ CME2020			Serial	3514
Permanent link to this record



	Author	Felipe Codevilla; Matthias Muller; Antonio Lopez; Vladlen Koltun; Alexey Dosovitskiy
	Title	End-to-end Driving via Conditional Imitation Learning			Type	Conference Article
	Year	2018	Publication	IEEE International Conference on Robotics and Automation	Abbreviated Journal
	Volume		Issue		Pages	4693 - 4700
	Keywords
	Abstract	Deep networks trained on demonstrations of human driving have learned to follow roads and avoid obstacles. However, driving policies trained via imitation learning cannot be controlled at test time. A vehicle trained end-to-end to imitate an expert cannot be guided to take a specific turn at an upcoming intersection. This limits the utility of such systems. We propose to condition imitation learning on high-level command input. At test time, the learned driving policy functions as a chauffeur that handles sensorimotor coordination but continues to respond to navigational commands. We evaluate different architectures for conditional imitation learning in vision-based driving. We conduct experiments in realistic three-dimensional simulations of urban driving and on a 1/5 scale robotic truck that is trained to drive in a residential area. Both systems drive based on visual input yet remain responsive to high-level navigational commands. The supplementary video can be viewed at this https URL
	Address	Brisbane; Australia; May 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	ICRA
	Notes	ADAS; 600.116; 600.124; 600.118			Approved	no
	Call Number	Admin @ si @ CML2018			Serial	3108
Permanent link to this record



	Author	Manuel Carbonell; Joan Mas; Mauricio Villegas; Alicia Fornes; Josep Llados
	Title	End-to-End Handwritten Text Detection and Transcription in Full Pages			Type	Conference Article
	Year	2019	Publication	2nd International Workshop on Machine Learning	Abbreviated Journal
	Volume	5	Issue		Pages	29-34
	Keywords	Handwritten Text Recognition; Layout Analysis; Text segmentation; Deep Neural Networks; Multi-task learning
	Abstract	When transcribing handwritten document images, inaccuracies in the text segmentation step often cause errors in the subsequent transcription step. For this reason, some recent methods propose to perform the recognition at paragraph level. But still, errors in the segmentation of paragraphs can affect the transcription performance. In this work, we propose an end-to-end framework to transcribe full pages. The joint text detection and transcription allows to remove the layout analysis requirement at test time. The experimental results show that our approach can achieve comparable results to models that assume segmented paragraphs, and suggest that joining the two tasks brings an improvement over doing the two tasks separately.
	Address	Sydney; Australia; September 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	ICDAR WML
	Notes	DAG; 600.140; 601.311; 600.140			Approved	no
	Call Number	Admin @ si @ CMV2019			Serial	3353
Permanent link to this record



	Author	Francesco Ciompi; Oriol Pujol; Simone Balocco; Xavier Carrillo; J. Mauri; Petia Radeva
	Title	Automatic Key Frames Detection in Intravascular Ultrasound Sequences			Type	Conference Article
	Year	2011	Publication	In MICCAI 2011 Workshop on Computing and Visualization for Intra Vascular Imaging	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	We present a method for the automatic detection of key frames in Intravascular Ultrasound (IVUS) sequences. The key frames are markers delimiting morphological changes along the vessel. The aim of defining key frames is two-fold: (1) they allow to summarize the content of the pullback into few representative frames; (2) they represent the basis for the automatic detection of clinical events in IVUS. The proposed approach achieved a compression ratio of 0.016 with respect to the original sequence and an average inter-frame distance of 61.76 frame, minimizing the number of missed clinical events.
	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	CVII
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ CPB2011			Serial	1767
Permanent link to this record



	Author	Francesco Ciompi; Oriol Pujol; Carlo Gatta; Xavier Carrillo; J. Mauri; Petia Radeva
	Title	A Holistic Approach for the Detection of Media-Adventitia Border in IVUS			Type	Conference Article
	Year	2011	Publication	14th International Conference on Medical Image Computing and Computer Assisted Intervention	Abbreviated Journal
	Volume	6893	Issue		Pages	401-408
	Keywords
	Abstract	In this paper we present a methodology for the automatic detection of media-adventitia border (MAb) in Intravascular Ultrasound. A robust computation of the MAb is achieved through a holistic approach where the position of the MAb with respect to other tissues of the vessel is used. A learned quality measure assures that the resulting MAb is optimal with respect to all other tissues. The mean distance error computed through a set of 140 images is 0.2164 (±0.1326) mm.
	Address	Toronto, Canada
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LNCS
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-23625-9	Medium
	Area		Expedition		Conference	MICCAI
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ CPG2011			Serial	1739
Permanent link to this record



	Author	Francesco Ciompi; A. Palaioroutas; M. Loeve; Oriol Pujol; Petia Radeva; H. Tiddens; M. de Bruijne
	Title	Lung Tissue Classification in Severe Advanced Cystic Fibrosis from CT Scans			Type	Conference Article
	Year	2011	Publication	In MICCAI 2011 4th International Workshop on Pulmonary Image Analysis	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract
	Address	Toronto, Canada
	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	PIA
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ CPL2011			Serial	1798
Permanent link to this record



	Author	Diego Cheda; Daniel Ponsa; Antonio Lopez
	Title	Monocular Egomotion Estimation based on Image Matching			Type	Conference Article
	Year	2012	Publication	1st International Conference on Pattern Recognition Applications and Methods	Abbreviated Journal
	Volume		Issue		Pages	425-430
	Keywords	SLAM
	Abstract
	Address	Portugal
	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	ICPRAM
	Notes	ADAS			Approved	no
	Call Number	Admin @ si @ CPL2012a;; ADAS @ adas @			Serial	2011
Permanent link to this record



	Author	Diego Cheda; Daniel Ponsa; Antonio Lopez
	Title	Monocular Depth-based Background Estimation			Type	Conference Article
	Year	2012	Publication	7th International Conference on Computer Vision Theory and Applications	Abbreviated Journal
	Volume		Issue		Pages	323-328
	Keywords
	Abstract	In this paper, we address the problem of reconstructing the background of a scene from a video sequence with occluding objects. The images are taken by hand-held cameras. Our method composes the background by selecting the appropriate pixels from previously aligned input images. To do that, we minimize a cost function that penalizes the deviations from the following assumptions: background represents objects whose distance to the camera is maximal, and background objects are stationary. Distance information is roughly obtained by a supervised learning approach that allows us to distinguish between close and distant image regions. Moving foreground objects are filtered out by using stationariness and motion boundary constancy measurements. The cost function is minimized by a graph cuts method. We demonstrate the applicability of our approach to recover an occlusion-free background in a set of sequences.
	Address	Roma
	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	ADAS			Approved	no
	Call Number	Admin @ si @ CPL2012b; ADAS @ adas @ cpl2012e			Serial	2012
Permanent link to this record



	Author	Diego Cheda; Daniel Ponsa; Antonio Lopez
	Title	Pedestrian Candidates Generation using Monocular Cues			Type	Conference Article
	Year	2012	Publication	IEEE Intelligent Vehicles Symposium	Abbreviated Journal
	Volume		Issue		Pages	7-12
	Keywords	pedestrian detection
	Abstract	Common techniques for pedestrian candidates generation (e.g., sliding window approaches) are based on an exhaustive search over the image. This implies that the number of windows produced is huge, which translates into a significant time consumption in the classification stage. In this paper, we propose a method that significantly reduces the number of windows to be considered by a classifier. Our method is a monocular one that exploits geometric and depth information available on single images. Both representations of the world are fused together to generate pedestrian candidates based on an underlying model which is focused only on objects standing vertically on the ground plane and having certain height, according with their depths on the scene. We evaluate our algorithm on a challenging dataset and demonstrate its application for pedestrian detection, where a considerable reduction in the number of candidate windows is reached.
	Address
	Corporate Author				Thesis
	Publisher	IEEE Xplore	Place of Publication		Editor
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN	1931-0587	ISBN	978-1-4673-2119-8	Medium
	Area		Expedition		Conference	IV
	Notes	ADAS			Approved	no
	Call Number	Admin @ si @ CPL2012c; ADAS @ adas @ cpl2012d			Serial	2013
Permanent link to this record



	Author	Pierluigi Casale; Oriol Pujol; Petia Radeva
	Title	Human Activity Recognition from Accelerometer Data using a Wearable Device			Type	Conference Article
	Year	2011	Publication	5th Iberian Conference on Pattern Recognition and Image Analysis	Abbreviated Journal
	Volume	6669	Issue		Pages	289-296
	Keywords
	Abstract	Activity Recognition is an emerging field of research, born from the larger fields of ubiquitous computing, context-aware computing and multimedia. Recently, recognizing everyday life activities becomes one of the challenges for pervasive computing. In our work, we developed a novel wearable system easy to use and comfortable to bring. Our wearable system is based on a new set of 20 computationally efficient features and the Random Forest classifier. We obtain very encouraging results with classification accuracy of human activities recognition of up to 94%.
	Address	Las Palmas de Gran Canaria. Spain
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor	Vitria, Jordi; Sanches, João Miguel Raposo; Hernández, Mario
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LNCS
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-21256-7	Medium
	Area		Expedition		Conference	IbPRIA
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ CPR2011a			Serial	1735
Permanent link to this record



	Author	Pierluigi Casale; Oriol Pujol; Petia Radeva
	Title	Approximate Convex Hulls Family for One-Class Cassification			Type	Conference Article
	Year	2011	Publication	10th International Workshop on Multiple Classifier Systems	Abbreviated Journal
	Volume	6713	Issue		Pages	106-115
	Keywords
	Abstract	In this work, a new method for one-class classification based on the Convex Hull geometric structure is proposed. The new method creates a family of convex hulls able to fit the geometrical shape of the training points. The increased computational cost due to the creation of the convex hull in multiple dimensions is circumvented using random projections. This provides an approximation of the original structure with multiple bi-dimensional views. In the projection planes, a mechanism for noisy points rejection has also been elaborated and evaluated. Results show that the approach performs considerably well with respect to the state the art in one-class classification.
	Address	Napoli, Italy
	Corporate Author				Thesis
	Publisher	Springer Berlin Heidelberg	Place of Publication		Editor	Carlo Sansone; Josef Kittler; Fabio Roli
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title	LNCS
	Series Volume		Series Issue		Edition
	ISSN	0302-9743	ISBN	978-3-642-21556-8	Medium
	Area		Expedition		Conference	MCS
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ CPR2011b			Serial	1761
Permanent link to this record