CVC Home

Publicacions CVC

Home |  Show All |  Simple Search |  Advanced Search  | Add Record  | Import
Quick Search:
2086–2100 of 3413 records found matching your query (RSS):
toggle visibility Search & Display Options
Select All    Deselect All [121–130] << 131 132 133 134 135 136 137 138 139 140 >> [141–150]
List View
 | 
Citations
 | 
Details
   print
  Records Links
Author Md.Mostafa Kamal Sarker; Mohammed Jabreel; , Hatem A. Rashwan; Syeda Furruka Banu; Petia Radeva; Domenec Puig edit   pdf
doi  openurl
  Title CuisineNet: Food Attributes Classification using Multi-scale Convolution Network Type Conference Article
  Year 2018 Publication 21st International Conference of the Catalan Association for Artificial Intelligence Abbreviated Journal (up)  
  Volume Issue Pages 365-372  
  Keywords  
  Abstract Diversity of food and its attributes represents the culinary habits of peoples from different countries. Thus, this paper addresses the problem of identifying food culture of people around the world and its flavor by classifying two main food attributes, cuisine and flavor. A deep learning model based on multi-scale convotuional networks is proposed for extracting more accurate features from input images. The aggregation of multi-scale convolution layers with different kernel size is also used for weighting the features results from different scales. In addition, a joint loss function based on Negative Log Likelihood (NLL) is used to fit the model probability to multi labeled classes for multi-modal classification task. Furthermore, this work provides a new dataset for food attributes, so-called Yummly48K, extracted from the popular food website, Yummly. Our model is assessed on the constructed Yummly48K dataset. The experimental results show that our proposed method yields 65% and 62% average F1 score on validation and test set which outperforming the state-of-the-art models.  
  Address Roses; catalonia; 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 CCIA  
  Notes MILAB; no menciona Approved no  
  Call Number Admin @ si @ SJR2018 Serial 3113  
Permanent link to this record
 
 
Author Shanxin Yuan; Guillermo Garcia-Hernando; Bjorn Stenger; Gyeongsik Moon; Ju Yong Chang; Kyoung Mu Lee; Pavlo Molchanov; Jan Kautz; Sina Honari; Liuhao Ge; Junsong Yuan; Xinghao Chen; Guijin Wang; Fan Yang; Kai Akiyama; Yang Wu; Qingfu Wan; Meysam Madadi; Sergio Escalera; Shile Li; Dongheui Lee; Iason Oikonomidis; Antonis Argyros; Tae-Kyun Kim edit   pdf
doi  openurl
  Title Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals Type Conference Article
  Year 2018 Publication 31st IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal (up)  
  Volume Issue Pages 2636 - 2645  
  Keywords Three-dimensional displays; Task analysis; Pose estimation; Two dimensional displays; Joints; Training; Solid modeling  
  Abstract In this paper, we strive to answer two questions: What is the current state of 3D hand pose estimation from depth images? And, what are the next challenges that need to be tackled? Following the successful Hands In the Million Challenge (HIM2017), we investigate the top 10 state-of-the-art methods on three tasks: single frame 3D pose estimation, 3D hand tracking, and hand pose estimation during object interaction. We analyze the performance of different CNN structures with regard to hand shape, joint visibility, view point and articulation distributions. Our findings include: (1) isolated 3D hand pose estimation achieves low mean errors (10 mm) in the view point range of [70, 120] degrees, but it is far from being solved for extreme view points; (2) 3D volumetric representations outperform 2D CNNs, better capturing the spatial structure of the depth data; (3) Discriminative methods still generalize poorly to unseen hand shapes; (4) While joint occlusions pose a challenge for most methods, explicit modeling of structure constraints can significantly narrow the gap between errors on visible and occluded joints.  
  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 CVPR  
  Notes HUPBA; no proj Approved no  
  Call Number Admin @ si @ YGS2018 Serial 3115  
Permanent link to this record
 
 
Author Albert Clapes; Ozan Bilici; Dariia Temirova; Egils Avots; Gholamreza Anbarjafari; Sergio Escalera edit   pdf
doi  openurl
  Title From apparent to real age: gender, age, ethnic, makeup, and expression bias analysis in real age estimation Type Conference Article
  Year 2018 Publication IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops Abbreviated Journal (up)  
  Volume Issue Pages 2373-2382  
  Keywords  
  Abstract  
  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 HUPBA Approved no  
  Call Number Admin @ si @ Serial 3116  
Permanent link to this record
 
 
Author Mohammad A. Haque; Ruben B. Bautista; Kamal Nasrollahi; Sergio Escalera; Christian B. Laursen; Ramin Irani; Ole K. Andersen; Erika G. Spaich; Kaustubh Kulkarni; Thomas B. Moeslund; Marco Bellantonio; Golamreza Anbarjafari; Fatemeh Noroozi edit   pdf
doi  openurl
  Title Deep Multimodal Pain Recognition: A Database and Comparision of Spatio-Temporal Visual Modalities, Faces and Gestures Type Conference Article
  Year 2018 Publication 13th IEEE Conference on Automatic Face and Gesture Recognition Abbreviated Journal (up)  
  Volume Issue Pages 250 - 257  
  Keywords  
  Abstract Pain is a symptom of many disorders associated with actual or potential tissue damage in human body. Managing pain is not only a duty but also highly cost prone. The most primitive state of pain management is the assessment of pain. Traditionally it was accomplished by self-report or visual inspection by experts. However, automatic pain assessment systems from facial videos are also rapidly evolving due to the need of managing pain in a robust and cost effective way. Among different challenges of automatic pain assessment from facial video data two issues are increasingly prevalent: first, exploiting both spatial and temporal information of the face to assess pain level, and second, incorporating multiple visual modalities to capture complementary face information related to pain. Most works in the literature focus on merely exploiting spatial information on chromatic (RGB) video data on shallow learning scenarios. However, employing deep learning techniques for spatio-temporal analysis considering Depth (D) and Thermal (T) along with RGB has high potential in this area. In this paper, we present the first state-of-the-art publicly available database, 'Multimodal Intensity Pain (MIntPAIN)' database, for RGBDT pain level recognition in sequences. We provide a first baseline results including 5 pain levels recognition by analyzing independent visual modalities and their fusion with CNN and LSTM models. From the experimental evaluation we observe that fusion of modalities helps to enhance recognition performance of pain levels in comparison to isolated ones. In particular, the combination of RGB, D, and T in an early fusion fashion achieved the best recognition rate.  
  Address Xian; China; 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 FG  
  Notes HUPBA; no proj Approved no  
  Call Number Admin @ si @ HBN2018 Serial 3117  
Permanent link to this record
 
 
Author Rain Eric Haamer; Kaustubh Kulkarni; Nasrin Imanpour; Mohammad Ahsanul Haque; Egils Avots; Michelle Breisch; Kamal Nasrollahi; Sergio Escalera; Cagri Ozcinar; Xavier Baro; Ahmad R. Naghsh-Nilchi; Thomas B. Moeslund; Gholamreza Anbarjafari edit   pdf
doi  openurl
  Title Changes in Facial Expression as Biometric: A Database and Benchmarks of Identification Type Conference Article
  Year 2018 Publication 8th International Workshop on Human Behavior Understanding Abbreviated Journal (up)  
  Volume Issue Pages  
  Keywords  
  Abstract Facial dynamics can be considered as unique signatures for discrimination between people. These have started to become important topic since many devices have the possibility of unlocking using face recognition or verification. In this work, we evaluate the efficacy of the transition frames of video in emotion as compared to the peak emotion frames for identification. For experiments with transition frames we extract features from each frame of the video from a fine-tuned VGG-Face Convolutional Neural Network (CNN) and geometric features from facial landmark points. To model the temporal context of the transition frames we train a Long-Short Term Memory (LSTM) on the geometric and the CNN features. Furthermore, we employ two fusion strategies: first, an early fusion, in which the geometric and the CNN features are stacked and fed to the LSTM. Second, a late fusion, in which the prediction of the LSTMs, trained independently on the two features, are stacked and used with a Support Vector Machine (SVM). Experimental results show that the late fusion strategy gives the best results and the transition frames give better identification results as compared to the peak emotion frames.  
  Address Xian; China; 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 FGW  
  Notes HUPBA; no proj Approved no  
  Call Number Admin @ si @ HKI2018 Serial 3118  
Permanent link to this record
 
 
Author Mohammad N. S. Jahromi; Morten Bojesen Bonderup; Maryam Asadi-Aghbolaghi; Egils Avots; Kamal Nasrollahi; Sergio Escalera; Shohreh Kasaei; Thomas B. Moeslund; Gholamreza Anbarjafari edit  doi
openurl 
  Title Automatic Access Control Based on Face and Hand Biometrics in a Non-cooperative Context Type Conference Article
  Year 2018 Publication IEEE Winter Applications of Computer Vision Workshops Abbreviated Journal (up)  
  Volume Issue Pages 28-36  
  Keywords IEEE Winter Applications of Computer Vision Workshops  
  Abstract Automatic access control systems (ACS) based on the human biometrics or physical tokens are widely employed in public and private areas. Yet these systems, in their conventional forms, are restricted to active interaction from the users. In scenarios where users are not cooperating with the system, these systems are challenged. Failure in cooperation with the biometric systems might be intentional or because the users are incapable of handling the interaction procedure with the biometric system or simply forget to cooperate with it, due to for example, illness like dementia. This work introduces a challenging bimodal database, including face and hand information of the users when they approach a door to open it by its handle in a noncooperative context. We have defined two (an easy and a challenging) protocols on how to use the database. We have reported results on many baseline methods, including deep learning techniques as well as conventional methods on the database. The obtained results show the merit of the proposed database and the challenging nature of access control with non-cooperative users.  
  Address Lake Tahoe; USA; March 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 WACVW  
  Notes HUPBA; 602.133 Approved no  
  Call Number Admin @ si @ JBA2018 Serial 3121  
Permanent link to this record
 
 
Author Cesar de Souza edit  openurl
  Title Action Recognition in Videos: Data-efficient approaches for supervised learning of human action classification models for video Type Book Whole
  Year 2018 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal (up)  
  Volume Issue Pages  
  Keywords  
  Abstract In this dissertation, we explore different ways to perform human action recognition in video clips. We focus on data efficiency, proposing new approaches that alleviate the need for laborious and time-consuming manual data annotation. In the first part of this dissertation, we start by analyzing previous state-of-the-art models, comparing their differences and similarities in order to pinpoint where their real strengths come from. Leveraging this information, we then proceed to boost the classification accuracy of shallow models to levels that rival deep neural networks. We introduce hybrid video classification architectures based on carefully designed unsupervised representations of handcrafted spatiotemporal features classified by supervised deep networks. We show in our experiments that our hybrid model combine the best of both worlds: it is data efficient (trained on 150 to 10,000 short clips) and yet improved significantly on the state of the art, including deep models trained on millions of manually labeled images and videos. In the second part of this research, 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 then introduce deep multi-task representation learning architectures to mix synthetic and real videos, even if the action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance, outperforming fine-tuning state-of-the-art unsupervised generative models of videos.  
  Address April 2018  
  Corporate Author Thesis Ph.D. thesis  
  Publisher Ediciones Graficas Rey Place of Publication Editor Antonio Lopez;Naila Murray  
  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 @ Sou2018 Serial 3127  
Permanent link to this record
 
 
Author Hassan Ahmed Sial; S. Sancho; Ramon Baldrich; Robert Benavente; Maria Vanrell edit   pdf
url  openurl
  Title Color-based data augmentation for Reflectance Estimation Type Conference Article
  Year 2018 Publication 26th Color Imaging Conference Abbreviated Journal (up)  
  Volume Issue Pages 284-289  
  Keywords  
  Abstract Deep convolutional architectures have shown to be successful frameworks to solve generic computer vision problems. The estimation of intrinsic reflectance from single image is not a solved problem yet. Encoder-Decoder architectures are a perfect approach for pixel-wise reflectance estimation, although it usually suffers from the lack of large datasets. Lack of data can be partially solved with data augmentation, however usual techniques focus on geometric changes which does not help for reflectance estimation. In this paper we propose a color-based data augmentation technique that extends the training data by increasing the variability of chromaticity. Rotation on the red-green blue-yellow plane of an opponent space enable to increase the training set in a coherent and sound way that improves network generalization capability for reflectance estimation. We perform some experiments on the Sintel dataset showing that our color-based augmentation increase performance and overcomes one of the state-of-the-art methods.  
  Address Vancouver; November 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 CIC  
  Notes CIC Approved no  
  Call Number Admin @ si @ SSB2018a Serial 3129  
Permanent link to this record
 
 
Author Yaxing Wang; Chenshen Wu; Luis Herranz; Joost Van de Weijer; Abel Gonzalez-Garcia; Bogdan Raducanu edit   pdf
url  openurl
  Title Transferring GANs: generating images from limited data Type Conference Article
  Year 2018 Publication 15th European Conference on Computer Vision Abbreviated Journal (up)  
  Volume 11210 Issue Pages 220-236  
  Keywords Generative adversarial networks; Transfer learning; Domain adaptation; Image generation  
  Abstract ransferring knowledge of pre-trained networks to new domains by means of fine-tuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep networks. Therefore, we study domain adaptation applied to image generation with generative adversarial networks. We evaluate several aspects of domain adaptation, including the impact of target domain size, the relative distance between source and target domain, and the initialization of conditional GANs. Our results show that using knowledge from pre-trained networks can shorten the convergence time and can significantly improve the quality of the generated images, especially when target data is limited. We show that these conclusions can also be drawn for conditional GANs even when the pre-trained model was trained without conditioning. Our results also suggest that density is more important than diversity and a dataset with one or few densely sampled classes is a better source model than more diverse datasets such as ImageNet or Places.  
  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 LAMP; 600.109; 600.106; 600.120 Approved no  
  Call Number Admin @ si @ WWH2018a Serial 3130  
Permanent link to this record
 
 
Author Yaxing Wang; Joost Van de Weijer; Luis Herranz edit   pdf
doi  openurl
  Title Mix and match networks: encoder-decoder alignment for zero-pair image translation Type Conference Article
  Year 2018 Publication 31st IEEE Conference on Computer Vision and Pattern Recognition Abbreviated Journal (up)  
  Volume Issue Pages 5467 - 5476  
  Keywords  
  Abstract We address the problem of image translation between domains or modalities for which no direct paired data is available (i.e. zero-pair translation). We propose mix and match networks, based on multiple encoders and decoders aligned in such a way that other encoder-decoder pairs can be composed at test time to perform unseen image translation tasks between domains or modalities for which explicit paired samples were not seen during training. We study the impact of autoencoders, side information and losses in improving the alignment and transferability of trained pairwise translation models to unseen translations. We show our approach is scalable and can perform colorization and style transfer between unseen combinations of domains. We evaluate our system in a challenging cross-modal setting where semantic segmentation is estimated from depth images, without explicit access to any depth-semantic segmentation training pairs. Our model outperforms baselines based on pix2pix and CycleGAN models.  
  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 CVPR  
  Notes LAMP; 600.109; 600.106; 600.120 Approved no  
  Call Number Admin @ si @ WWH2018b Serial 3131  
Permanent link to this record
 
 
Author Esmitt Ramirez; Carles Sanchez; Agnes Borras; Marta Diez-Ferrer; Antoni Rosell; Debora Gil edit   pdf
url  openurl
  Title Image-Based Bronchial Anatomy Codification for Biopsy Guiding in Video Bronchoscopy Type Conference Article
  Year 2018 Publication OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis Abbreviated Journal (up)  
  Volume 11041 Issue Pages  
  Keywords Biopsy guiding; Bronchoscopy; Lung biopsy; Intervention guiding; Airway codification  
  Abstract Bronchoscopy examinations allow biopsy of pulmonary nodules with minimum risk for the patient. Even for experienced bronchoscopists, it is difficult to guide the bronchoscope to most distal lesions and obtain an accurate diagnosis. This paper presents an image-based codification of the bronchial anatomy for bronchoscopy biopsy guiding. The 3D anatomy of each patient is codified as a binary tree with nodes representing bronchial levels and edges labeled using their position on images projecting the 3D anatomy from a set of branching points. The paths from the root to leaves provide a codification of navigation routes with spatially consistent labels according to the anatomy observes in video bronchoscopy explorations. We evaluate our labeling approach as a guiding system in terms of the number of bronchial levels correctly codified, also in the number of labels-based instructions correctly supplied, using generalized mixed models and computer-generated data. Results obtained for three independent observers prove the consistency and reproducibility of our guiding system. We trust that our codification based on viewer’s projection might be used as a foundation for the navigation process in Virtual Bronchoscopy systems.  
  Address Granada; 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 MICCAIW  
  Notes IAM; 600.096; 600.075; 601.323; 600.145 Approved no  
  Call Number Admin @ si @ RSB2018b Serial 3137  
Permanent link to this record
 
 
Author Pau Rodriguez; Josep M. Gonfaus; Guillem Cucurull; Xavier Roca; Jordi Gonzalez edit   pdf
url  openurl
  Title Attend and Rectify: A Gated Attention Mechanism for Fine-Grained Recovery Type Conference Article
  Year 2018 Publication 15th European Conference on Computer Vision Abbreviated Journal (up)  
  Volume 11212 Issue Pages 357-372  
  Keywords Deep Learning; Convolutional Neural Networks; Attention  
  Abstract We propose a novel attention mechanism to enhance Convolutional Neural Networks for fine-grained recognition. It learns to attend to lower-level feature activations without requiring part annotations and uses these activations to update and rectify the output likelihood distribution. In contrast to other approaches, the proposed mechanism is modular, architecture-independent and efficient both in terms of parameters and computation required. Experiments show that networks augmented with our approach systematically improve their classification accuracy and become more robust to clutter. As a result, Wide Residual Networks augmented with our proposal surpasses the state of the art classification accuracies in CIFAR-10, the Adience gender recognition task, Stanford dogs, and UEC Food-100.  
  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 ISE; 600.098; 602.121; 600.119 Approved no  
  Call Number Admin @ si @ RGC2018 Serial 3139  
Permanent link to this record
 
 
Author Boris N. Oreshkin; Pau Rodriguez; Alexandre Lacoste edit   pdf
url  openurl
  Title TADAM: Task dependent adaptive metric for improved few-shot learning Type Conference Article
  Year 2018 Publication 32nd Annual Conference on Neural Information Processing Systems Abbreviated Journal (up)  
  Volume Issue Pages  
  Keywords  
  Abstract Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-shot algorithm parameter updates. Metric scaling provides improvements up to 14% in accuracy for certain metrics on the mini-Imagenet 5-way 5-shot classification task. We further propose a simple and effective way of conditioning a learner on the task sample set, resulting in learning a task-dependent metric space. Moreover, we propose and empirically test a practical end-to-end optimization procedure based on auxiliary task co-training to learn a task-dependent metric space. The resulting few-shot learning model based on the task-dependent scaled metric achieves state of the art on mini-Imagenet. We confirm these results on another few-shot dataset that we introduce in this paper based on CIFAR100.  
  Address Montreal; Canada; December 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 NIPS  
  Notes ISE; 600.098; 600.119 Approved no  
  Call Number Admin @ si @ ORL2018 Serial 3140  
Permanent link to this record
 
 
Author Lluis Gomez; Andres Mafla; Marçal Rusiñol; Dimosthenis Karatzas edit   pdf
url  openurl
  Title Single Shot Scene Text Retrieval Type Conference Article
  Year 2018 Publication 15th European Conference on Computer Vision Abbreviated Journal (up)  
  Volume 11218 Issue Pages 728-744  
  Keywords Image retrieval; Scene text; Word spotting; Convolutional Neural Networks; Region Proposals Networks; PHOC  
  Abstract Textual information found in scene images provides high level semantic information about the image and its context and it can be leveraged for better scene understanding. In this paper we address the problem of scene text retrieval: given a text query, the system must return all images containing the queried text. The novelty of the proposed model consists in the usage of a single shot CNN architecture that predicts at the same time bounding boxes and a compact text representation of the words in them. In this way, the text based image retrieval task can be casted as a simple nearest neighbor search of the query text representation over the outputs of the CNN over the entire image
database. Our experiments demonstrate that the proposed architecture
outperforms previous state-of-the-art while it offers a significant increase
in processing speed.		  
  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 DAG; 600.084; 601.338; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ GMR2018 Serial 3143  
Permanent link to this record
 
 
Author Mohammed Al Rawi; Dimosthenis Karatzas edit   pdf
openurl 
  Title On the Labeling Correctness in Computer Vision Datasets Type Conference Article
  Year 2018 Publication Proceedings of the Workshop on Interactive Adaptive Learning, co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases Abbreviated Journal (up)  
  Volume Issue Pages  
  Keywords  
  Abstract Image datasets have heavily been used to build computer vision systems.
These datasets are either manually or automatically labeled, which is a
problem as both labeling methods are prone to errors. To investigate this problem, we use a majority voting ensemble that combines the results from several Convolutional Neural Networks (CNNs). Majority voting ensembles not only enhance the overall performance, but can also be used to estimate the confidence level of each sample. We also examined Softmax as another form to estimate posterior probability. We have designed various experiments with a range of different ensembles built from one or different, or temporal/snapshot CNNs, which have been trained multiple times stochastically. We analyzed CIFAR10, CIFAR100, EMNIST, and SVHN datasets and we found quite a few incorrect
labels, both in the training and testing sets. We also present detailed confidence analysis on these datasets and we found that the ensemble is better than the Softmax when used estimate the per-sample confidence. This work thus proposes an approach that can be used to scrutinize and verify the labeling of computer vision datasets, which can later be applied to weakly/semi-supervised learning. We propose a measure, based on the Odds-Ratio, to quantify how many of these incorrectly classified labels are actually incorrectly labeled and how many of these are confusing. The proposed methods are easily scalable to larger datasets, like ImageNet, LSUN and SUN, as each CNN instance is trained for 60 epochs; or even faster, by implementing a temporal (snapshot) ensemble.		  
  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 ECML-PKDDW  
  Notes DAG; 600.121; 600.129 Approved no  
  Call Number Admin @ si @ RaK2018 Serial 3144  
Permanent link to this record
Select All    Deselect All [121–130] << 131 132 133 134 135 136 137 138 139 140 >> [141–150]
List View
 | 
Citations
 | 
Details
   print
toggle visibility
Save Citations:
Export Records:
Home SQL Search  |  Library Search  |  Show Record  |  Extract Citations Help