Publicacions CVC -- Query Results

	Publicacions CVC Home \| Show All \| Simple Search \| Advanced Search \| Add Record \| Import	Login Quick Search: Field: contains: ...
	2596–2610 of 3413 records found matching your query (RSS \| history):

Search & Display Options

Select All Deselect All

[161–170] << 171 172 173 174 175 176 177 178 179 180 >> [181–190]

List View

Citations

Details

	Records
	Author	Sangheeta Roy; Palaiahnakote Shivakumara; Namita Jain; Vijeta Khare; Anjan Dutta; Umapada Pal; Tong Lu
	Title	Rough-Fuzzy based Scene Categorization for Text Detection and Recognition in Video			Type	Journal Article
	Year	2018	Publication	Pattern Recognition	Abbreviated Journal	PR
	Volume	80	Issue		Pages	64-82
	Keywords	Rough set; Fuzzy set; Video categorization; Scene image classification; Video text detection; Video text recognition
	Abstract	Scene image or video understanding is a challenging task especially when number of video types increases drastically with high variations in background and foreground. This paper proposes a new method for categorizing scene videos into different classes, namely, Animation, Outlet, Sports, e-Learning, Medical, Weather, Defense, Economics, Animal Planet and Technology, for the performance improvement of text detection and recognition, which is an effective approach for scene image or video understanding. For this purpose, at first, we present a new combination of rough and fuzzy concept to study irregular shapes of edge components in input scene videos, which helps to classify edge components into several groups. Next, the proposed method explores gradient direction information of each pixel in each edge component group to extract stroke based features by dividing each group into several intra and inter planes. We further extract correlation and covariance features to encode semantic features located inside planes or between planes. Features of intra and inter planes of groups are then concatenated to get a feature matrix. Finally, the feature matrix is verified with temporal frames and fed to a neural network for categorization. Experimental results show that the proposed method outperforms the existing state-of-the-art methods, at the same time, the performances of text detection and recognition methods are also improved significantly due to categorization.
	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; 600.097; 600.121			Approved	no
	Call Number	Admin @ si @ RSJ2018			Serial	3096
Permanent link to this record



	Author	Xinhang Song; Luis Herranz; Shuqiang Jiang
	Title	Depth CNNs for RGB-D Scene Recognition: Learning from Scratch Better than Transferring from RGB-CNNs			Type	Conference Article
	Year	2017	Publication	31st AAAI Conference on Artificial Intelligence	Abbreviated Journal
	Volume		Issue		Pages
	Keywords	RGB-D scene recognition; weakly supervised; fine tune; CNN
	Abstract	Scene recognition with RGB images has been extensively studied and has reached very remarkable recognition levels, thanks to convolutional neural networks (CNN) and large scene datasets. In contrast, current RGB-D scene data is much more limited, so often leverages RGB large datasets, by transferring pretrained RGB CNN models and fine-tuning with the target RGB-D dataset. However, we show that this approach has the limitation of hardly reaching bottom layers, which is key to learn modality-specific features. In contrast, we focus on the bottom layers, and propose an alternative strategy to learn depth features combining local weakly supervised training from patches followed by global fine tuning with images. This strategy is capable of learning very discriminative depth-specific features with limited depth images, without resorting to Places-CNN. In addition we propose a modified CNN architecture to further match the complexity of the model and the amount of data available. For RGB-D scene recognition, depth and RGB features are combined by projecting them in a common space and further leaning a multilayer classifier, which is jointly optimized in an end-to-end network. Our framework achieves state-of-the-art accuracy on NYU2 and SUN RGB-D in both depth only and combined RGB-D data.
	Address	San Francisco CA; 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	AAAI
	Notes	LAMP; 600.120			Approved	no
	Call Number	Admin @ si @ SHJ2017			Serial	2967
Permanent link to this record



	Author	Sergi Garcia Bordils; Dimosthenis Karatzas; Marçal Rusiñol
	Title	Accelerating Transformer-Based Scene Text Detection and Recognition via Token Pruning			Type	Conference Article
	Year	2023	Publication	17th International Conference on Document Analysis and Recognition	Abbreviated Journal
	Volume	14192	Issue		Pages	106-121
	Keywords	Scene Text Detection; Scene Text Recognition; Transformer Acceleration
	Abstract	Scene text detection and recognition is a crucial task in computer vision with numerous real-world applications. Transformer-based approaches are behind all current state-of-the-art models and have achieved excellent performance. However, the computational requirements of the transformer architecture makes training these methods slow and resource heavy. In this paper, we introduce a new token pruning strategy that significantly decreases training and inference times without sacrificing performance, striking a balance between accuracy and speed. We have applied this pruning technique to our own end-to-end transformer-based scene text understanding architecture. Our method uses a separate detection branch to guide the pruning of uninformative image features, which significantly reduces the number of tokens at the input of the transformer. Experimental results show how our network is able to obtain competitive results on multiple public benchmarks while running at significantly higher speeds.
	Address	San Jose; CA; USA; August 2023
	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	ICDAR
	Notes	DAG			Approved	no
	Call Number	Admin @ si @ GKR2023a			Serial	3907
Permanent link to this record



	Author	Lluis Gomez; Dimosthenis Karatzas
	Title	Multi-script Text Extraction from Natural Scenes			Type	Conference Article
	Year	2013	Publication	12th International Conference on Document Analysis and Recognition	Abbreviated Journal
	Volume		Issue		Pages	467-471
	Keywords
	Abstract	Scene text extraction methodologies are usually based in classification of individual regions or patches, using a priori knowledge for a given script or language. Human perception of text, on the other hand, is based on perceptual organisation through which text emerges as a perceptually significant group of atomic objects. Therefore humans are able to detect text even in languages and scripts never seen before. In this paper, we argue that the text extraction problem could be posed as the detection of meaningful groups of regions. We present a method built around a perceptual organisation framework that exploits collaboration of proximity and similarity laws to create text-group hypotheses. Experiments demonstrate that our algorithm is competitive with state of the art approaches on a standard dataset covering text in variable orientations and two languages.
	Address	Washington; USA; August 2013
	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	1520-5363	ISBN		Medium
	Area		Expedition		Conference	ICDAR
	Notes	DAG; 600.056; 601.158; 601.197			Approved	no
	Call Number	Admin @ si @ GoK2013			Serial	2310
Permanent link to this record



	Author	Josep Brugues Pujolras; Lluis Gomez; Dimosthenis Karatzas
	Title	A Multilingual Approach to Scene Text Visual Question Answering			Type	Conference Article
	Year	2022	Publication	Document Analysis Systems.15th IAPR International Workshop, (DAS2022)	Abbreviated Journal
	Volume		Issue		Pages	65-79
	Keywords	Scene text; Visual question answering; Multilingual word embeddings; Vision and language; Deep learning
	Abstract	Scene Text Visual Question Answering (ST-VQA) has recently emerged as a hot research topic in Computer Vision. Current ST-VQA models have a big potential for many types of applications but lack the ability to perform well on more than one language at a time due to the lack of multilingual data, as well as the use of monolingual word embeddings for training. In this work, we explore the possibility to obtain bilingual and multilingual VQA models. In that regard, we use an already established VQA model that uses monolingual word embeddings as part of its pipeline and substitute them by FastText and BPEmb multilingual word embeddings that have been aligned to English. Our experiments demonstrate that it is possible to obtain bilingual and multilingual VQA models with a minimal loss in performance in languages not used during training, as well as a multilingual model trained in multiple languages that match the performance of the respective monolingual baselines.
	Address	La Rochelle, France; May 22–25, 2022
	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	DAS
	Notes	DAG; 611.004; 600.155; 601.002			Approved	no
	Call Number	Admin @ si @ BGK2022b			Serial	3695
Permanent link to this record



	Author	Marçal Rusiñol
	Title	Classificació semàntica i visual de documents digitals			Type	Journal
	Year	2019	Publication	Revista de biblioteconomia i documentacio	Abbreviated Journal
	Volume		Issue		Pages	75-86
	Keywords
	Abstract	Se analizan los sistemas de procesamiento automático que trabajan sobre documentos digitalizados con el objetivo de describir los contenidos. De esta forma contribuyen a facilitar el acceso, permitir la indización automática y hacer accesibles los documentos a los motores de búsqueda. El objetivo de estas tecnologías es poder entrenar modelos computacionales que sean capaces de clasificar, agrupar o realizar búsquedas sobre documentos digitales. Así, se describen las tareas de clasificación, agrupamiento y búsqueda. Cuando utilizamos tecnologías de inteligencia artificial en los sistemas de clasificación esperamos que la herramienta nos devuelva etiquetas semánticas; en sistemas de agrupamiento que nos devuelva documentos agrupados en clusters significativos; y en sistemas de búsqueda esperamos que dada una consulta, nos devuelva una lista ordenada de documentos en función de la relevancia. A continuación se da una visión de conjunto de los métodos que nos permiten describir los documentos digitales, tanto de manera visual (cuál es su apariencia), como a partir de sus contenidos semánticos (de qué hablan). En cuanto a la descripción visual de documentos se aborda el estado de la cuestión de las representaciones numéricas de documentos digitalizados tanto por métodos clásicos como por métodos basados en el aprendizaje profundo (deep learning). Respecto de la descripción semántica de los contenidos se analizan técnicas como el reconocimiento óptico de caracteres (OCR); el cálculo de estadísticas básicas sobre la aparición de las diferentes palabras en un texto (bag-of-words model); y los métodos basados en aprendizaje profundo como el método word2vec, basado en una red neuronal que, dadas unas cuantas palabras de un texto, debe predecir cuál será la siguiente palabra. Desde el campo de las ingenierías se están transfiriendo conocimientos que se han integrado en productos o servicios en los ámbitos de la archivística, la biblioteconomía, la documentación y las plataformas de gran consumo, sin embargo los algoritmos deben ser lo suficientemente eficientes no sólo para el reconocimiento y transcripción literal sino también para la capacidad de interpretación de los contenidos.
	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; 600.135; 600.121; 600.129			Approved	no
	Call Number	Admin @ si @ Rus2019			Serial	3282
Permanent link to this record



	Author	Antonio Clavelli
	Title	A computational model of eye guidance, searching for text in real scene images			Type	Book Whole
	Year	2014	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Searching for text objects in real scene images is an open problem and a very active computer vision research area. A large number of methods have been proposed tackling the text search as extension of the ones from the document analysis field or inspired by general purpose object detection methods. However the general problem of object search in real scene images remains an extremely challenging problem due to the huge variability in object appearance. This thesis builds on top of the most recent findings in the visual attention literature presenting a novel computational model of eye guidance aiming to better describe text object search in real scene images. First are presented the relevant state-of-the-art results from the visual attention literature regarding eye movements and visual search. Relevant models of attention are discussed and integrated with recent observations on the role of top-down constraints and the emerging need for a layered model of attention in which saliency is not the only factor guiding attention. Visual attention is then explained by the interaction of several modulating factors, such as objects, value, plans and saliency. Then we introduce our probabilistic formulation of attention deployment in real scene. The model is based on the rationale that oculomotor control depends on two interacting but distinct processes: an attentional process that assigns value to the sources of information and motor process that flexibly links information with action. In such framework, the choice of where to look next is task-dependent and oriented to classes of objects embedded within pictures of complex scenes. The dependence on task is taken into account by exploiting the value and the reward of gazing at certain image patches or proto-objects that provide a sparse representation of the scene objects. In the experimental section the model is tested in laboratory condition, comparing model simulations with data from eye tracking experiments. The comparison is qualitative in terms of observable scan paths and quantitative in terms of statistical similarity of gaze shift amplitude. Experiments are performed using eye tracking data from both a publicly available dataset of face and text and from newly performed eye-tracking experiments on a dataset of street view pictures containing text. The last part of this thesis is dedicated to study the extent to which the proposed model can account for human eye movements in a low constrained setting. We used a mobile eye tracking device and an ad-hoc developed methodology to compare model simulated eye data with the human eye data from mobile eye tracking recordings. Such setting allow to test the model in an incomplete visual information condition, reproducing a close to real-life search task.
	Address
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	Place of Publication		Editor	Dimosthenis Karatzas;Giuseppe Boccignone;Josep Llados
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-940902-6-4	Medium
	Area		Expedition		Conference
	Notes	DAG; 600.077			Approved	no
	Call Number	Admin @ si @ Cla2014			Serial	2571
Permanent link to this record



	Author	Manuel Carbonell
	Title	Neural Information Extraction from Semi-structured Documents A			Type	Book Whole
	Year	2020	Publication	PhD Thesis, Universitat Autonoma de Barcelona-CVC	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Sectors as fintech, legaltech or insurance process an inflow of millions of forms, invoices, id documents, claims or similar every day. Together with these, historical archives provide gigantic amounts of digitized documents containing useful information that needs to be stored in machine encoded text with a meaningful structure. This procedure, known as information extraction (IE) comprises the steps of localizing and recognizing text, identifying named entities contained in it and optionally finding relationships among its elements. In this work we explore multi-task neural models at image and graph level to solve all steps in a unified way. While doing so we find benefits and limitations of these end-to-end approaches in comparison with sequential separate methods. More specifically, we first propose a method to produce textual as well as semantic labels with a unified model from handwritten text line images. We do so with the use of a convolutional recurrent neural model trained with connectionist temporal classification to predict the textual as well as semantic information encoded in the images. Secondly, motivated by the success of this approach we investigate the unification of the localization and recognition tasks of handwritten text in full pages with an end-to-end model, observing benefits in doing so. Having two models that tackle information extraction subsequent task pairs in an end-to-end to end manner, we lastly contribute with a method to put them all together in a single neural network to solve the whole information extraction pipeline in a unified way. Doing so we observe some benefits and some limitations in the approach, suggesting that in certain cases it is beneficial to train specialized models that excel at a single challenging task of the information extraction process, as it can be the recognition of named entities or the extraction of relationships between them. For this reason we lastly study the use of the recently arrived graph neural network architectures for the semantic tasks of the information extraction process, which are recognition of named entities and relation extraction, achieving promising results on the relation extraction part.
	Address
	Corporate Author				Thesis	Ph.D. thesis
	Publisher	Ediciones Graficas Rey	Place of Publication		Editor	Alicia Fornes;Mauricio Villegas;Josep Llados
	Language		Summary Language		Original Title
	Series Editor		Series Title		Abbreviated Series Title
	Series Volume		Series Issue		Edition
	ISSN		ISBN	978-84-122714-1-6	Medium
	Area		Expedition		Conference
	Notes	DAG; 600.121			Approved	no
	Call Number	Admin @ si @ Car20			Serial	3483
Permanent link to this record



	Author	Ivan Huerta; Michael Holte; Thomas B. Moeslund; Jordi Gonzalez
	Title	Detection and Removal of Chromatic Moving Shadows in Surveillance Scenarios			Type	Conference Article
	Year	2009	Publication	12th International Conference on Computer Vision	Abbreviated Journal
	Volume		Issue		Pages	1499 - 1506
	Keywords
	Abstract	Segmentation in the surveillance domain has to deal with shadows to avoid distortions when detecting moving objects. Most segmentation approaches dealing with shadow detection are typically restricted to penumbra shadows. Therefore, such techniques cannot cope well with umbra shadows. Consequently, umbra shadows are usually detected as part of moving objects. In this paper we present a novel technique based on gradient and colour models for separating chromatic moving cast shadows from detected moving objects. Firstly, both a chromatic invariant colour cone model and an invariant gradient model are built to perform automatic segmentation while detecting potential shadows. In a second step, regions corresponding to potential shadows are grouped by considering “a bluish effect” and an edge partitioning. Lastly, (i) temporal similarities between textures and (ii) spatial similarities between chrominance angle and brightness distortions are analysed for all potential shadow regions in order to finally identify umbra shadows. Unlike other approaches, our method does not make any a-priori assumptions about camera location, surface geometries, surface textures, shapes and types of shadows, objects, and background. Experimental results show the performance and accuracy of our approach in different shadowed materials and illumination conditions.
	Address	Kyoto, Japan
	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	1550-5499	ISBN	978-1-4244-4420-5	Medium
	Area		Expedition		Conference	ICCV
	Notes				Approved	no
	Call Number	ISE @ ise @ HHM2009			Serial	1213
Permanent link to this record



	Author	Jose Carlos Rubio; Joan Serrat; Antonio Lopez
	Title	Video Co-segmentation			Type	Conference Article
	Year	2012	Publication	11th Asian Conference on Computer Vision	Abbreviated Journal
	Volume	7725	Issue		Pages	13-24
	Keywords
	Abstract	Segmentation of a single image is in general a highly underconstrained problem. A frequent approach to solve it is to somehow provide prior knowledge or constraints on how the objects of interest look like (in terms of their shape, size, color, location or structure). Image co-segmentation trades the need for such knowledge for something much easier to obtain, namely, additional images showing the object from other viewpoints. Now the segmentation problem is posed as one of differentiating the similar object regions in all the images from the more varying background. In this paper, for the first time, we extend this approach to video segmentation: given two or more video sequences showing the same object (or objects belonging to the same class) moving in a similar manner, we aim to outline its region in all the frames. In addition, the method works in an unsupervised manner, by learning to segment at testing time. We compare favorably with two state-of-the-art methods on video segmentation and report results on benchmark videos.
	Address	Daejeon, Korea
	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	978-3-642-37443-2	Medium
	Area		Expedition		Conference	ACCV
	Notes	ADAS			Approved	no
	Call Number	Admin @ si @ RSL2012d			Serial	2153
Permanent link to this record



	Author	Debora Gil; Carles Sanchez; Agnes Borras; Marta Diez-Ferrer; Antoni Rosell
	Title	Segmentation of Distal Airways using Structural Analysis			Type	Journal Article
	Year	2019	Publication	PloS one	Abbreviated Journal	Plos
	Volume	14	Issue	12	Pages
	Keywords
	Abstract	Segmentation of airways in Computed Tomography (CT) scans is a must for accurate support of diagnosis and intervention of many pulmonary disorders. In particular, lung cancer diagnosis would benefit from segmentations reaching most distal airways. We present a method that combines descriptors of bronchi local appearance and graph global structural analysis to fine-tune thresholds on the descriptors adapted for each bronchial level. We have compared our method to the top performers of the EXACT09 challenge and to a commercial software for biopsy planning evaluated in an own-collected data-base of high resolution CT scans acquired under different breathing conditions. Results on EXACT09 data show that our method provides a high leakage reduction with minimum loss in airway detection. Results on our data-base show the reliability across varying breathing conditions and a competitive performance for biopsy planning compared to a commercial solution.
	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	IAM; 600.139; 600.145			Approved	no
	Call Number	Admin @ si @ GSB2019			Serial	3357
Permanent link to this record



	Author	Lluis Pere de las Heras; Joan Mas; Gemma Sanchez; Ernest Valveny
	Title	Wall Patch-Based Segmentation in Architectural Floorplans			Type	Conference Article
	Year	2011	Publication	11th International Conference on Document Analysis and Recognition	Abbreviated Journal
	Volume		Issue		Pages	1270-1274
	Keywords
	Abstract	Segmentation of architectural floor plans is a challenging task, mainly because of the large variability in the notation between different plans. In general, traditional techniques, usually based on analyzing and grouping structural primitives obtained by vectorization, are only able to handle a reduced range of similar notations. In this paper we propose an alternative patch-based segmentation approach working at pixel level, without need of vectorization. The image is divided into a set of patches and a set of features is extracted for every patch. Then, each patch is assigned to a visual word of a previously learned vocabulary and given a probability of belonging to each class of objects. Finally, a post-process assigns the final label for every pixel. This approach has been applied to the detection of walls on two datasets of architectural floor plans with different notations, achieving high accuracy rates.
	Address	Beiging, China
	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	1520-5363	ISBN	978-0-7695-4520-2	Medium
	Area		Expedition		Conference	ICDAR
	Notes	DAG			Approved	no
	Call Number	Admin @ si @ HMS2011a			Serial	1792
Permanent link to this record



	Author	Antonio Hernandez; Carlo Gatta; Sergio Escalera; Laura Igual; Victoria Martin-Yuste; Manel Sabate; Petia Radeva
	Title	Accurate coronary centerline extraction, caliber estimation and catheter detection in angiographies			Type	Journal Article
	Year	2012	Publication	IEEE Transactions on Information Technology in Biomedicine	Abbreviated Journal	TITB
	Volume	16	Issue	6	Pages	1332-1340
	Keywords
	Abstract	Segmentation of coronary arteries in X-Ray angiography is a fundamental tool to evaluate arterial diseases and choose proper coronary treatment. The accurate segmentation of coronary arteries has become an important topic for the registration of different modalities which allows physicians rapid access to different medical imaging information from Computed Tomography (CT) scans or Magnetic Resonance Imaging (MRI). In this paper, we propose an accurate fully automatic algorithm based on Graph-cuts for vessel centerline extraction, caliber estimation, and catheter detection. Vesselness, geodesic paths, and a new multi-scale edgeness map are combined to customize the Graph-cuts approach to the segmentation of tubular structures, by means of a global optimization of the Graph-cuts energy function. Moreover, a novel supervised learning methodology that integrates local and contextual information is proposed for automatic catheter detection. We evaluate the method performance on three datasets coming from different imaging systems. The method performs as good as the expert observer w.r.t. centerline detection and caliber estimation. Moreover, the method discriminates between arteries and catheter with an accuracy of 96.5%, sensitivity of 72%, and precision of 97.4%.
	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	1089-7771	ISBN		Medium
	Area		Expedition		Conference
	Notes	MILAB;HuPBA			Approved	no
	Call Number	Admin @ si @ HGE2012			Serial	2141
Permanent link to this record



	Author	Marcin Przewiezlikowski; Mateusz Pyla; Bartosz Zielinski; Bartłomiej Twardowski; Jacek Tabor; Marek Smieja
	Title	Augmentation-aware Self-supervised Learning with Guided Projector			Type	Miscellaneous
	Year	2023	Publication	arxiv	Abbreviated Journal
	Volume		Issue		Pages
	Keywords
	Abstract	Self-supervised learning (SSL) is a powerful technique for learning robust representations from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo are able to reach quality on par with supervised approaches. However, this invariance may be harmful to solving some downstream tasks which depend on traits affected by augmentations used during pretraining, such as color. In this paper, we propose to foster sensitivity to such characteristics in the representation space by modifying the projector network, a common component of self-supervised architectures. Specifically, we supplement the projector with information about augmentations applied to images. In order for the projector to take advantage of this auxiliary conditioning when solving the SSL task, the feature extractor learns to preserve the augmentation information in its representations. Our approach, coined Conditional Augmentation-aware Self-supervised Learning (CASSLE), is directly applicable to typical joint-embedding SSL methods regardless of their objective functions. Moreover, it does not require major changes in the network architecture or prior knowledge of downstream tasks. In addition to an analysis of sensitivity towards different data augmentations, we conduct a series of experiments, which show that CASSLE improves over various SSL methods, reaching state-of-the-art performance in multiple downstream tasks.
	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			Approved	no
	Call Number	Admin @ si @ PPZ2023			Serial	3971
Permanent link to this record



	Author	Raul Gomez; Lluis Gomez; Jaume Gibert; Dimosthenis Karatzas
	Title	Self-Supervised Learning from Web Data for Multimodal Retrieval			Type	Book Chapter
	Year	2019	Publication	Multi-Modal Scene Understanding Book	Abbreviated Journal
	Volume		Issue		Pages	279-306
	Keywords	self-supervised learning; webly supervised learning; text embeddings; multimodal retrieval; multimodal embedding
	Abstract	Self-Supervised learning from multimodal image and text data allows deep neural networks to learn powerful features with no need of human annotated data. Web and Social Media platforms provide a virtually unlimited amount of this multimodal data. In this work we propose to exploit this free available data to learn a multimodal image and text embedding, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the proposed pipeline can learn from images with associated text without supervision and analyze the semantic structure of the learnt joint image and text embeddingspace. Weperformathoroughanalysisandperformancecomparisonofﬁvedifferentstateof the art text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text basedimageretrievaltask,andweclearlyoutperformstateoftheartintheMIRFlickrdatasetwhen training in the target data. Further, we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.
	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; 600.129; 601.338; 601.310			Approved	no
	Call Number	Admin @ si @ GGG2019			Serial	3266
Permanent link to this record