Souhail Bakkali, Zuheng Ming, Mickael Coustaty, Marçal Rusiñol, & Oriol Ramos Terrades. (2023). VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification. PR - Pattern Recognition, 139, 109419.
Abstract: Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream approach. In this paper, we approach the document classification problem by learning cross-modal representations through language and vision cues, considering intra- and inter-modality relationships. Instead of merging features from different modalities into a common representation space, the proposed method exploits high-level interactions and learns relevant semantic information from effective attention flows within and across modalities. The proposed learning objective is devised between intra- and inter-modality alignment tasks, where the similarity distribution per task is computed by contracting positive sample pairs while simultaneously contrasting negative ones in the common feature representation space}. Extensive experiments on public document classification datasets demonstrate the effectiveness and the generalization capacity of our model on both low-scale and large-scale datasets.
|
Raul Gomez, Lluis Gomez, Jaume Gibert, & Dimosthenis Karatzas. (2019). Self-Supervised Learning from Web Data for Multimodal Retrieval. In Multi-Modal Scene Understanding Book (pp. 279–306).
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.
Keywords: self-supervised learning; webly supervised learning; text embeddings; multimodal retrieval; multimodal embedding
|
Ali Furkan Biten, Ruben Tito, Andres Mafla, Lluis Gomez, Marçal Rusiñol, M. Mathew, et al. (2019). ICDAR 2019 Competition on Scene Text Visual Question Answering. In 3rd Workshop on Closing the Loop Between Vision and Language, in conjunction with ICCV2019.
Abstract: This paper presents final results of ICDAR 2019 Scene Text Visual Question Answering competition (ST-VQA). ST-VQA introduces an important aspect that is not addressed
by any Visual Question Answering system up to date, namely the incorporation of scene text to answer questions asked about an image. The competition introduces a new dataset comprising 23, 038 images annotated with 31, 791 question / answer pairs where the answer is always grounded on text instances present in the image. The images are taken from 7 different public computer vision datasets, covering a wide range of scenarios.
The competition was structured in three tasks of increasing difficulty, that require reading the text in a scene and understanding it in the context of the scene, to correctly answer a given question. A novel evaluation metric is presented, which elegantly assesses both key capabilities expected from an optimal model: text recognition and image understanding. A detailed analysis of results from different participants is showcased, which provides insight into the current capabilities of VQA systems that can read. We firmly believe the dataset proposed in this challenge will be an important milestone to consider towards a path of more robust and general models that
can exploit scene text to achieve holistic image understanding.
|
Raul Gomez, Lluis Gomez, Jaume Gibert, & Dimosthenis Karatzas. (2018). Learning to Learn from Web Data through Deep Semantic Embeddings. In 15th European Conference on Computer Vision Workshops (Vol. 11134, pp. 514–529). LNCS.
Abstract: In this paper we propose to learn a multimodal image and text embedding from Web and Social Media data, 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 pipeline can learn from images with associated text without supervision and perform a thourough analysis of five different 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 based image retrieval task, and we clearly outperform state of the art in the MIRFlickr dataset when 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.
|
Raul Gomez, Lluis Gomez, Jaume Gibert, & Dimosthenis Karatzas. (2018). Learning from# Barcelona Instagram data what Locals and Tourists post about its Neighbourhoods. In 15th European Conference on Computer Vision Workshops (Vol. 11134, pp. 530–544). LNCS.
Abstract: Massive tourism is becoming a big problem for some cities, such as Barcelona, due to its concentration in some neighborhoods. In this work we gather Instagram data related to Barcelona consisting on images-captions pairs and, using the text as a supervisory signal, we learn relations between images, words and neighborhoods. Our goal is to learn which visual elements appear in photos when people is posting about each neighborhood. We perform a language separate treatment of the data and show that it can be extrapolated to a tourists and locals separate analysis, and that tourism is reflected in Social Media at a neighborhood level. The presented pipeline allows analyzing the differences between the images that tourists and locals associate to the different neighborhoods. The proposed method, which can be extended to other cities or subjects, proves that Instagram data can be used to train multi-modal (image and text) machine learning models that are useful to analyze publications about a city at a neighborhood level. We publish the collected dataset, InstaBarcelona and the code used in the analysis.
|
Ali Furkan Biten, Ruben Tito, Andres Mafla, Lluis Gomez, Marçal Rusiñol, M. Mathew, et al. (2019). ICDAR 2019 Competition on Scene Text Visual Question Answering. In 15th International Conference on Document Analysis and Recognition (pp. 1563–1570).
Abstract: This paper presents final results of ICDAR 2019 Scene Text Visual Question Answering competition (ST-VQA). ST-VQA introduces an important aspect that is not addressed by any Visual Question Answering system up to date, namely the incorporation of scene text to answer questions asked about an image. The competition introduces a new dataset comprising 23,038 images annotated with 31,791 question / answer pairs where the answer is always grounded on text instances present in the image. The images are taken from 7 different public computer vision datasets, covering a wide range of scenarios. The competition was structured in three tasks of increasing difficulty, that require reading the text in a scene and understanding it in the context of the scene, to correctly answer a given question. A novel evaluation metric is presented, which elegantly assesses both key capabilities expected from an optimal model: text recognition and image understanding. A detailed analysis of results from different participants is showcased, which provides insight into the current capabilities of VQA systems that can read. We firmly believe the dataset proposed in this challenge will be an important milestone to consider towards a path of more robust and general models that can exploit scene text to achieve holistic image understanding.
|
Lei Kang, Marçal Rusiñol, Alicia Fornes, Pau Riba, & Mauricio Villegas. (2020). Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition. In IEEE Winter Conference on Applications of Computer Vision.
Abstract: Handwritten Text Recognition (HTR) is still a challenging problem because it must deal with two important difficulties: the variability among writing styles, and the scarcity of labelled data. To alleviate such problems, synthetic data generation and data augmentation are typically used to train HTR systems. However, training with such data produces encouraging but still inaccurate transcriptions in real words. In this paper, we propose an unsupervised writer adaptation approach that is able to automatically adjust a generic handwritten word recognizer, fully trained with synthetic fonts, towards a new incoming writer. We have experimentally validated our proposal using five different datasets, covering several challenges (i) the document source: modern and historic samples, which may involve paper degradation problems; (ii) different handwriting styles: single and multiple writer collections; and (iii) language, which involves different character combinations. Across these challenging collections, we show that our system is able to maintain its performance, thus, it provides a practical and generic approach to deal with new document collections without requiring any expensive and tedious manual annotation step.
|
Lei Kang, Pau Riba, Marçal Rusiñol, Alicia Fornes, & Mauricio Villegas. (2020). Distilling Content from Style for Handwritten Word Recognition. In 17th International Conference on Frontiers in Handwriting Recognition.
Abstract: Despite the latest transcription accuracies reached using deep neural network architectures, handwritten text recognition still remains a challenging problem, mainly because of the large inter-writer style variability. Both augmenting the training set with artificial samples using synthetic fonts, and writer adaptation techniques have been proposed to yield more generic approaches aimed at dodging style unevenness. In this work, we take a step closer to learn style independent features from handwritten word images. We propose a novel method that is able to disentangle the content and style aspects of input images by jointly optimizing a generative process and a handwritten
word recognizer. The generator is aimed at transferring writing style features from one sample to another in an image-to-image translation approach, thus leading to a learned content-centric features that shall be independent to writing style attributes.
Our proposed recognition model is able then to leverage such writer-agnostic features to reach better recognition performances. We advance over prior training strategies and demonstrate with qualitative and quantitative evaluations the performance of both
the generative process and the recognition efficiency in the IAM dataset.
|
Raul Gomez, Ali Furkan Biten, Lluis Gomez, Jaume Gibert, Marçal Rusiñol, & Dimosthenis Karatzas. (2019). Selective Style Transfer for Text. In 15th International Conference on Document Analysis and Recognition (pp. 805–812).
Abstract: This paper explores the possibilities of image style transfer applied to text maintaining the original transcriptions. Results on different text domains (scene text, machine printed text and handwritten text) and cross-modal results demonstrate that this is feasible, and open different research lines. Furthermore, two architectures for selective style transfer, which means
transferring style to only desired image pixels, are proposed. Finally, scene text selective style transfer is evaluated as a data augmentation technique to expand scene text detection datasets, resulting in a boost of text detectors performance. Our implementation of the described models is publicly available.
Keywords: transfer; text style transfer; data augmentation; scene text detection
|
Ali Furkan Biten, Ruben Tito, Andres Mafla, Lluis Gomez, Marçal Rusiñol, C.V. Jawahar, et al. (2019). Scene Text Visual Question Answering. In 18th IEEE International Conference on Computer Vision (pp. 4291–4301).
Abstract: Current visual question answering datasets do not consider the rich semantic information conveyed by text within an image. In this work, we present a new dataset, ST-VQA, that aims to highlight the importance of exploiting highlevel semantic information present in images as textual cues in the Visual Question Answering process. We use this dataset to define a series of tasks of increasing difficulty for which reading the scene text in the context provided by the visual information is necessary to reason and generate an appropriate answer. We propose a new evaluation metric for these tasks to account both for reasoning errors as well as shortcomings of the text recognition module. In addition we put forward a series of baseline methods, which provide further insight to the newly released dataset, and set the scene for further research.
|
Ali Furkan Biten, Lluis Gomez, Marçal Rusiñol, & Dimosthenis Karatzas. (2019). Good News, Everyone! Context driven entity-aware captioning for news images. In 32nd IEEE Conference on Computer Vision and Pattern Recognition (pp. 12458–12467).
Abstract: Current image captioning systems perform at a merely descriptive level, essentially enumerating the objects in the scene and their relations. Humans, on the contrary, interpret images by integrating several sources of prior knowledge of the world. In this work, we aim to take a step closer to producing captions that offer a plausible interpretation of the scene, by integrating such contextual information into the captioning pipeline. For this we focus on the captioning of images used to illustrate news articles. We propose a novel captioning method that is able to leverage contextual information provided by the text of news articles associated with an image. Our model is able to selectively draw information from the article guided by visual cues, and to dynamically extend the output dictionary to out-of-vocabulary named entities that appear in the context source. Furthermore we introduce“ GoodNews”, the largest news image captioning dataset in the literature and demonstrate state-of-the-art results.
|
Dena Bazazian, Dimosthenis Karatzas, & Andrew Bagdanov. (2018). Soft-PHOC Descriptor for End-to-End Word Spotting in Egocentric Scene Images. In International Workshop on Egocentric Perception, Interaction and Computing at ECCV.
Abstract: Word spotting in natural scene images has many applications in scene understanding and visual assistance. We propose Soft-PHOC, an intermediate representation of images based on character probability maps. Our representation extends the concept of the Pyramidal Histogram Of Characters (PHOC) by exploiting Fully Convolutional Networks to derive a pixel-wise mapping of the character distribution within candidate word regions. We show how to use our descriptors for word spotting tasks in egocentric camera streams through an efficient text line proposal algorithm. This is based on the Hough Transform over character attribute maps followed by scoring using Dynamic Time Warping (DTW). We evaluate our results on ICDAR 2015 Challenge 4 dataset of incidental scene text captured by an egocentric camera.
|
Dena Bazazian, Dimosthenis Karatzas, & Andrew Bagdanov. (2018). Word Spotting in Scene Images based on Character Recognition. In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (pp. 1872–1874).
Abstract: In this paper we address the problem of unconstrained Word Spotting in scene images. We train a Fully Convolutional Network to produce heatmaps of all the character classes. Then, we employ the Text Proposals approach and, via a rectangle classifier, detect the most likely rectangle for each query word based on the character attribute maps. We evaluate the proposed method on ICDAR2015 and show that it is capable of identifying and recognizing query words in natural scene images.
|
Rui Zhang, Yongsheng Zhou, Qianyi Jiang, Qi Song, Nan Li, Kai Zhou, et al. (2019). ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard. In 15th International Conference on Document Analysis and Recognition (pp. 1577–1581).
Abstract: Chinese scene text reading is one of the most challenging problems in computer vision and has attracted great interest. Different from English text, Chinese has more than 6000 commonly used characters and Chinesecharacters can be arranged in various layouts with numerous fonts. The Chinese signboards in street view are a good choice for Chinese scene text images since they have different backgrounds, fonts and layouts. We organized a competition called ICDAR2019-ReCTS, which mainly focuses on reading Chinese text on signboard. This report presents the final results of the competition. A large-scale dataset of 25,000 annotated signboard images, in which all the text lines and characters are annotated with locations and transcriptions, were released. Four tasks, namely character recognition, text line recognition, text line detection and end-to-end recognition were set up. Besides, considering the Chinese text ambiguity issue, we proposed a multi ground truth (multi-GT) evaluation method to make evaluation fairer. The competition started on March 1, 2019 and ended on April 30, 2019. 262 submissions from 46 teams are received. Most of the participants come from universities, research institutes, and tech companies in China. There are also some participants from the United States, Australia, Singapore, and Korea. 21 teams submit results for Task 1, 23 teams submit results for Task 2, 24 teams submit results for Task 3, and 13 teams submit results for Task 4.
|
Mohammed Al Rawi, Ernest Valveny, & Dimosthenis Karatzas. (2019). Can One Deep Learning Model Learn Script-Independent Multilingual Word-Spotting? In 15th International Conference on Document Analysis and Recognition (pp. 260–267).
Abstract: Word spotting has gained increased attention lately as it can be used to extract textual information from handwritten documents and scene-text images. Current word spotting approaches are designed to work on a single language and/or script. Building intelligent models that learn script-independent multilingual word-spotting is challenging due to the large variability of multilingual alphabets and symbols. We used ResNet-152 and the Pyramidal Histogram of Characters (PHOC) embedding to build a one-model script-independent multilingual word-spotting and we tested it on Latin, Arabic, and Bangla (Indian) languages. The one-model we propose performs on par with the multi-model language-specific word-spotting system, and thus, reduces the number of models needed for each script and/or language.
|
