|
Sergi Garcia Bordils and 6 others. 2022. Read While You Drive-Multilingual Text Tracking on the Road. 15th IAPR International workshop on document analysis systems.756–770. (LNCS.)
Abstract: Visual data obtained during driving scenarios usually contain large amounts of text that conveys semantic information necessary to analyse the urban environment and is integral to the traffic control plan. Yet, research on autonomous driving or driver assistance systems typically ignores this information. To advance research in this direction, we present RoadText-3K, a large driving video dataset with fully annotated text. RoadText-3K is three times bigger than its predecessor and contains data from varied geographical locations, unconstrained driving conditions and multiple languages and scripts. We offer a comprehensive analysis of tracking by detection and detection by tracking methods exploring the limits of state-of-the-art text detection. Finally, we propose a new end-to-end trainable tracking model that yields state-of-the-art results on this challenging dataset. Our experiments demonstrate the complexity and variability of RoadText-3K and establish a new, realistic benchmark for scene text tracking in the wild.
|
|
|
Ali Furkan Biten. 2022. A Bitter-Sweet Symphony on Vision and Language: Bias and World Knowledge. (Ph.D. thesis, IMPRIMA.)
Abstract: Vision and Language are broadly regarded as cornerstones of intelligence. Even though language and vision have different aims – language having the purpose of communication, transmission of information and vision having the purpose of constructing mental representations around us to navigate and interact with objects – they cooperate and depend on one another in many tasks we perform effortlessly. This reliance is actively being studied in various Computer Vision tasks, e.g. image captioning, visual question answering, image-sentence retrieval, phrase grounding, just to name a few. All of these tasks share the inherent difficulty of the aligning the two modalities, while being robust to language
priors and various biases existing in the datasets. One of the ultimate goal for vision and language research is to be able to inject world knowledge while getting rid of the biases that come with the datasets. In this thesis, we mainly focus on two vision and language tasks, namely Image Captioning and Scene-Text Visual Question Answering (STVQA).
In both domains, we start by defining a new task that requires the utilization of world knowledge and in both tasks, we find that the models commonly employed are prone to biases that exist in the data. Concretely, we introduce new tasks and discover several problems that impede performance at each level and provide remedies or possible solutions in each chapter: i) We define a new task to move beyond Image Captioning to Image Interpretation that can utilize Named Entities in the form of world knowledge. ii) We study the object hallucination problem in classic Image Captioning systems and develop an architecture-agnostic solution. iii) We define a sub-task of Visual Question Answering that requires reading the text in the image (STVQA), where we highlight the limitations of current models. iv) We propose an architecture for the STVQA task that can point to the answer in the image and show how to combine it with classic VQA models. v) We show how far language can get us in STVQA and discover yet another bias which causes the models to disregard the image while doing Visual Question Answering.
|
|
|
Soumya Jahagirdar, Minesh Mathew, Dimosthenis Karatzas and CV Jawahar. 2023. Watching the News: Towards VideoQA Models that can Read. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer.
Abstract: Video Question Answering methods focus on commonsense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA approaches ignore the textual information present in the video. Instead, we argue that textual information is complementary to the action and provides essential contextualisation cues to the reasoning process. To this end, we propose a novel VideoQA task that requires reading and understanding the text in the video. To explore this direction, we focus on news videos and require QA systems to comprehend and answer questions about the topics presented by combining visual and textual cues in the video. We introduce the ``NewsVideoQA'' dataset that comprises more than 8,600 QA pairs on 3,000+ news videos obtained from diverse news channels from around the world. We demonstrate the limitations of current Scene Text VQA and VideoQA methods and propose ways to incorporate scene text information into VideoQA methods.
|
|
|
Marçal Rusiñol. 2009. Geometric and Structural-based Symbol Spotting. Application to Focused Retrieval in Graphic Document Collections. (Ph.D. thesis, Ediciones Graficas Rey.)
Abstract: Usually, pattern recognition systems consist of two main parts. On the one hand, the data acquisition and, on the other hand, the classification of this data on a certain category. In order to recognize which category a certain query element belongs to, a set of pattern models must be provided beforehand. An off-line learning stage is needed to train the classifier and to offer a robust classification of the patterns. Within the pattern recognition field, we are interested in the recognition of graphics and, in particular, on the analysis of documents rich in graphical information. In this context, one of the main concerns is to see if the proposed systems remain scalable with respect to the data volume so as it can handle growing amounts of symbol models. In order to avoid to work with a database of reference symbols, symbol spotting and on-the-fly symbol recognition methods have been introduced in the past years.
Generally speaking, the symbol spotting problem can be defined as the identification of a set of regions of interest from a document image which are likely to contain an instance of a certain queriedn symbol without explicitly applying the whole pattern recognition scheme. Our application framework consists on indexing a collection of graphic-rich document images. This collection is
queried by example with a single instance of the symbol to look for and, by means of symbol spotting methods we retrieve the regions of interest where the symbol is likely to appear within the documents. This kind of applications are known as focused retrieval methods.
In order that the focused retrieval application can handle large collections of documents there is a need to provide an efficient access to the large volume of information that might be stored. We use indexing strategies in order to efficiently retrieve by similarity the locations where a certain part of the symbol appears. In that scenario, graphical patterns should be used as indices for accessing and navigating the collection of documents.
These indexing mechanism allow the user to search for similar elements using graphical information rather than textual queries.
Along this thesis we present a spotting architecture and different methods aiming to build a complete focused retrieval application dealing with a graphic-rich document collections. In addition, a protocol to evaluate the performance of symbol
spotting systems in terms of recognition abilities, location accuracy and scalability is proposed.
|
|
|
Andres Mafla. 2022. Leveraging Scene Text Information for Image Interpretation. (Ph.D. thesis, IMPRIMA.)
Abstract: Until recently, most computer vision models remained illiterate, largely ignoring the semantically rich and explicit information contained in scene text. Recent progress in scene text detection and recognition has recently allowed exploring its role in a diverse set of open computer vision problems, e.g. image classification, image-text retrieval, image captioning, and visual question answering to name a few. The explicit semantics of scene text closely requires specific modeling similar to language. However, scene text is a particular signal that has to be interpreted according to a comprehensive perspective that encapsulates all the visual cues in an image. Incorporating this information is a straightforward task for humans, but if we are unfamiliar with a language or scripture, achieving a complete world understanding is impossible (e.a. visiting a foreign country with a different alphabet). Despite the importance of scene text, modeling it requires considering the several ways in which scene text interacts with an image, processing and fusing an additional modality. In this thesis, we mainly focus
on two tasks, scene text-based fine-grained image classification, and cross-modal retrieval. In both studied tasks we identify existing limitations in current approaches and propose plausible solutions. Concretely, in each chapter: i) We define a compact way to embed scene text that generalizes to unseen words at training time while performing in real-time. ii) We incorporate the previously learned scene text embedding to create an image-level descriptor that overcomes optical character recognition (OCR) errors which is well-suited to the fine-grained image classification task. iii) We design a region-level reasoning network that learns the interaction through semantics among salient visual regions and scene text instances. iv) We employ scene text information in image-text matching and introduce the Scene Text Aware Cross-Modal retrieval StacMR task. We gather a dataset that incorporates scene text and design a model suited for the newly studied modality. v) We identify the drawbacks of current retrieval metrics in cross-modal retrieval. An image captioning metric is proposed as a way of better evaluating semantics in retrieved results. Ample experimentation shows that incorporating such semantics into a model yields better semantic results while
requiring significantly less data to converge.
|
|
|
Kaida Xiao, Chenyang Fu, D.Mylonas, Dimosthenis Karatzas and S. Wuerger. 2013. Unique Hue Data for Colour Appearance Models. Part ii: Chromatic Adaptation Transform. CRA, 38(1), 22–29.
Abstract: Unique hue settings of 185 observers under three room-lighting conditions were used to evaluate the accuracy of full and mixed chromatic adaptation transform models of CIECAM02 in terms of unique hue reproduction. Perceptual hue shifts in CIECAM02 were evaluated for both models with no clear difference using the current Commission Internationale de l'Éclairage (CIE) recommendation for mixed chromatic adaptation ratio. Using our large dataset of unique hue data as a benchmark, an optimised parameter is proposed for chromatic adaptation under mixed illumination conditions that produces more accurate results in unique hue reproduction. © 2011 Wiley Periodicals, Inc. Col Res Appl, 2013
|
|
|
Volkmar Frinken, Francisco Zamora, Salvador España, Maria Jose Castro, Andreas Fischer and Horst Bunke. 2012. Long-Short Term Memory Neural Networks Language Modeling for Handwriting Recognition. 21st International Conference on Pattern Recognition.701–704.
Abstract: Unconstrained handwritten text recognition systems maximize the combination of two separate probability scores. The first one is the observation probability that indicates how well the returned word sequence matches the input image. The second score is the probability that reflects how likely a word sequence is according to a language model. Current state-of-the-art recognition systems use statistical language models in form of bigram word probabilities. This paper proposes to model the target language by means of a recurrent neural network with long-short term memory cells. Because the network is recurrent, the considered context is not limited to a fixed size especially as the memory cells are designed to deal with long-term dependencies. In a set of experiments conducted on the IAM off-line database we show the superiority of the proposed language model over statistical n-gram models.
|
|
|
Lluis Gomez and Dimosthenis Karatzas. 2016. A fast hierarchical method for multi‐script and arbitrary oriented scene text extraction. IJDAR, 19(4), 335–349.
Abstract: Typography and layout lead to the hierarchical organisation of text in words, text lines, paragraphs. This inherent structure is a key property of text in any script and language, which has nonetheless been minimally leveraged by existing text detection methods. This paper addresses the problem of text
segmentation in natural scenes from a hierarchical perspective.
Contrary to existing methods, we make explicit use of text structure, aiming directly to the detection of region groupings corresponding to text within a hierarchy produced by an agglomerative similarity clustering process over individual regions. We propose an optimal way to construct such an hierarchy introducing a feature space designed to produce text group hypotheses with
high recall and a novel stopping rule combining a discriminative classifier and a probabilistic measure of group meaningfulness based in perceptual organization. Results obtained over four standard datasets, covering text in variable orientations and different languages, demonstrate that our algorithm, while being trained in a single mixed dataset, outperforms state of the art
methods in unconstrained scenarios.
Keywords: scene text; segmentation; detection; hierarchical grouping; perceptual organisation
|
|
|
J.Kuhn and 10 others. 2015. Advancing Physics Learning Through Traversing a Multi-Modal Experimentation Space. Workshop Proceedings on the 11th International Conference on Intelligent Environments.373–380.
Abstract: Translating conceptual knowledge into real world experiences presents a significant educational challenge. This position paper presents an approach that supports learners in moving seamlessly between conceptual learning and their application in the real world by bringing physical and virtual experiments into everyday settings. Learners are empowered in conducting these situated experiments in a variety of physical settings by leveraging state of the art mobile, augmented reality, and virtual reality technology. A blend of mobile-based multi-sensory physical experiments, augmented reality and enabling virtual environments can allow learners to bridge their conceptual learning with tangible experiences in a completely novel manner. This approach focuses on the learner by applying self-regulated personalised learning techniques, underpinned by innovative pedagogical approaches and adaptation techniques, to ensure that the needs and preferences of each learner are catered for individually.
|
|
|
Andreas Fischer, Volkmar Frinken, Alicia Fornes and Horst Bunke. 2011. Transcription Alignment of Latin Manuscripts Using Hidden Markov Models. Proceedings of the 2011 Workshop on Historical Document Imaging and Processing. ACM, 29–36.
Abstract: Transcriptions of historical documents are a valuable source for extracting labeled handwriting images that can be used for training recognition systems. In this paper, we introduce the Saint Gall database that includes images as well as the transcription of a Latin manuscript from the 9th century written in Carolingian script. Although the available transcription is of high quality for a human reader, the spelling of the words is not accurate when compared with the handwriting image. Hence, the transcription poses several challenges for alignment regarding, e.g., line breaks, abbreviations, and capitalization. We propose an alignment system based on character Hidden Markov Models that can cope with these challenges and efficiently aligns complete document pages. On the Saint Gall database, we demonstrate that a considerable alignment accuracy can be achieved, even with weakly trained character models.
|
|