|
Volkmar Frinken, Andreas Fischer, Markus Baumgartner, & Horst Bunke. (2014). Keyword spotting for self-training of BLSTM NN based handwriting recognition systems. PR - Pattern Recognition, 47(3), 1073–1082.
Abstract: The automatic transcription of unconstrained continuous handwritten text requires well trained recognition systems. The semi-supervised paradigm introduces the concept of not only using labeled data but also unlabeled data in the learning process. Unlabeled data can be gathered at little or not cost. Hence it has the potential to reduce the need for labeling training data, a tedious and costly process. Given a weak initial recognizer trained on labeled data, self-training can be used to recognize unlabeled data and add words that were recognized with high confidence to the training set for re-training. This process is not trivial and requires great care as far as selecting the elements that are to be added to the training set is concerned. In this paper, we propose to use a bidirectional long short-term memory neural network handwritten recognition system for keyword spotting in order to select new elements. A set of experiments shows the high potential of self-training for bootstrapping handwriting recognition systems, both for modern and historical handwritings, and demonstrate the benefits of using keyword spotting over previously published self-training schemes.
Keywords: Document retrieval; Keyword spotting; Handwriting recognition; Neural networks; Semi-supervised learning
|
|
|
Axel Barroso-Laguna, Edgar Riba, Daniel Ponsa, & Krystian Mikolajczyk. (2019). Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters. In 18th IEEE International Conference on Computer Vision (pp. 5835–5843).
Abstract: We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide anchor structures for learned filters, which localize, score and rank repeatable features. Scale-space representation is used within the network to extract keypoints at different levels. We design a loss function to detect robust features that exist across a range of scales and to maximize the repeatability score. Our Key.Net model is trained on data synthetically created from ImageNet and evaluated on HPatches benchmark. Results show that our approach outperforms state-of-the-art detectors in terms of repeatability, matching performance and complexity.
|
|
|
Hongxing Gao, Marçal Rusiñol, Dimosthenis Karatzas, Josep Llados, Tomokazu Sato, Masakazu Iwamura, et al. (2013). Key-region detection for document images -applications to administrative document retrieval. In 12th International Conference on Document Analysis and Recognition (pp. 230–234).
Abstract: In this paper we argue that a key-region detector designed to take into account the special characteristics of document images can result in the detection of less and more meaningful key-regions. We propose a fast key-region detector able to capture aspects of the structural information of the document, and demonstrate its efficiency by comparing against standard detectors in an administrative document retrieval scenario. We show that using the proposed detector results to a smaller number of detected key-regions and higher performance without any drop in speed compared to standard state of the art detectors.
|
|
|
Mohammad Ali Bagheri, Qigang Gao, Sergio Escalera, Albert Clapes, Kamal Nasrollahi, Michael Holte, et al. (2015). Keep it Accurate and Diverse: Enhancing Action Recognition Performance by Ensemble Learning. In IEEE Conference on Computer Vision and Pattern Recognition Worshops (CVPRW) (pp. 22–29).
Abstract: The performance of different action recognition techniques has recently been studied by several computer vision researchers. However, the potential improvement in classification through classifier fusion by ensemble-based methods has remained unattended. In this work, we evaluate the performance of an ensemble of action learning techniques, each performing the recognition task from a different perspective.
The underlying idea is that instead of aiming a very sophisticated and powerful representation/learning technique, we can learn action categories using a set of relatively simple and diverse classifiers, each trained with different feature set. In addition, combining the outputs of several learners can reduce the risk of an unfortunate selection of a learner on an unseen action recognition scenario.
This leads to having a more robust and general-applicable framework. In order to improve the recognition performance, a powerful combination strategy is utilized based on the Dempster-Shafer theory, which can effectively make use
of diversity of base learners trained on different sources of information. The recognition results of the individual classifiers are compared with those obtained from fusing the classifiers’ output, showing enhanced performance of the proposed methodology.
|
|
|
Ferran Diego, Joan Serrat, & Antonio Lopez. (2013). Joint spatio-temporal alignment of sequences. TMM - IEEE Transactions on Multimedia, 15(6), 1377–1387.
Abstract: Video alignment is important in different areas of computer vision such as wide baseline matching, action recognition, change detection, video copy detection and frame dropping prevention. Current video alignment methods usually deal with a relatively simple case of fixed or rigidly attached cameras or simultaneous acquisition. Therefore, in this paper we propose a joint video alignment for bringing two video sequences into a spatio-temporal alignment. Specifically, the novelty of the paper is to formulate the video alignment to fold the spatial and temporal alignment into a single alignment framework. This simultaneously satisfies a frame-correspondence and frame-alignment similarity; exploiting the knowledge among neighbor frames by a standard pairwise Markov random field (MRF). This new formulation is able to handle the alignment of sequences recorded at different times by independent moving cameras that follows a similar trajectory, and also generalizes the particular cases that of fixed geometric transformation and/or linear temporal mapping. We conduct experiments on different scenarios such as sequences recorded simultaneously or by moving cameras to validate the robustness of the proposed approach. The proposed method provides the highest video alignment accuracy compared to the state-of-the-art methods on sequences recorded from vehicles driving along the same track at different times.
Keywords: video alignment
|
|
|
Manuel Carbonell, Mauricio Villegas, Alicia Fornes, & Josep Llados. (2018). Joint Recognition of Handwritten Text and Named Entities with a Neural End-to-end Model. In 13th IAPR International Workshop on Document Analysis Systems (pp. 399–404).
Abstract: When extracting information from handwritten documents, text transcription and named entity recognition are usually faced as separate subsequent tasks. This has the disadvantage that errors in the first module affect heavily the
performance of the second module. In this work we propose to do both tasks jointly, using a single neural network with a common architecture used for plain text recognition. Experimentally, the work has been tested on a collection of historical marriage records. Results of experiments are presented to show the effect on the performance for different
configurations: different ways of encoding the information, doing or not transfer learning and processing at text line or multi-line region level. The results are comparable to state of the art reported in the ICDAR 2017 Information Extraction competition, even though the proposed technique does not use any dictionaries, language modeling or post processing.
Keywords: Named entity recognition; Handwritten Text Recognition; neural networks
|
|
|
David Guillamet, & B. Moghaddam. (2002). Joint Distribution of Local Image Features for Appearance Moldeling..
|
|
|
Victor Vaquero, German Ros, Francesc Moreno-Noguer, Antonio Lopez, & Alberto Sanfeliu. (2017). Joint coarse-and-fine reasoning for deep optical flow. In 24th International Conference on Image Processing (pp. 2558–2562).
Abstract: We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning. The coarse reasoning is performed over a discrete classification space to obtain a general rough solution, while the fine details of the solution are obtained over a continuous regression space. In our approach both components are jointly estimated, which proved to be beneficial for improving estimation accuracy. Additionally, we propose a new network architecture, which combines coarse and fine components by treating the fine estimation as a refinement built on top of the coarse solution, and therefore adding details to the general prediction. We apply our approach to the challenging problem of optical flow estimation and empirically validate it against state-of-the-art CNN-based solutions trained from scratch and tested on large optical flow datasets.
|
|
|
Iiris Lusi, Julio C. S. Jacques Junior, Jelena Gorbova, Xavier Baro, Sergio Escalera, Hasan Demirel, et al. (2017). Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation: Databases. In 12th IEEE International Conference on Automatic Face and Gesture Recognition.
Abstract: In this work two databases for the Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation1 are introduced. Head pose estimation paired with and detailed emotion recognition have become very important in relation to human-computer interaction. The 3D head pose database, SASE, is a 3D database acquired with Microsoft Kinect 2 camera, including RGB and depth information of different head poses which is composed by a total of 30000 frames with annotated markers, including 32 male and 18 female subjects. For the dominant and complementary emotion database, iCVMEFED, includes 31250 images with different emotions of 115 subjects whose gender distribution is almost uniform. For each subject there are 5 samples. The emotions are composed by 7 basic emotions plus neutral, being defined as complementary and dominant pairs. The emotion associated to the images were labeled with the support of psychologists.
|
|
|
Zeynep Yucel, Albert Ali Salah, Çetin Meriçli, Tekin Meriçli, Roberto Valenti, & Theo Gevers. (2013). Joint Attention by Gaze Interpolation and Saliency. T-CIBER - IEEE Transactions on cybernetics, 829–842.
Abstract: Joint attention, which is the ability of coordination of a common point of reference with the communicating party, emerges as a key factor in various interaction scenarios. This paper presents an image-based method for establishing joint attention between an experimenter and a robot. The precise analysis of the experimenter's eye region requires stability and high-resolution image acquisition, which is not always available. We investigate regression-based interpolation of the gaze direction from the head pose of the experimenter, which is easier to track. Gaussian process regression and neural networks are contrasted to interpolate the gaze direction. Then, we combine gaze interpolation with image-based saliency to improve the target point estimates and test three different saliency schemes. We demonstrate the proposed method on a human-robot interaction scenario. Cross-subject evaluations, as well as experiments under adverse conditions (such as dimmed or artificial illumination or motion blur), show that our method generalizes well and achieves rapid gaze estimation for establishing joint attention.
|
|
|
Maya Dimitrova, I. Terziev, Petia Radeva, & Juan J. Villanueva. (2004). Java-Servlet Technology for Building New Web Document Classifiers.
|
|
|
Sergio Escalera, Oriol Pujol, J. Mauri, & Petia Radeva. (2008). IVUS Tissue Characterization with Sub-class Error-correcting Output Codes. In Computer Vision and Pattern Recognition Workshops, 2008. CVPR Workshops 2008. IEEE Computer Society Conference on, pp. 1–8, 23–28 juny 2008..
Abstract: Intravascular ultrasound (IVUS) represents a powerful imaging technique to explore coronary vessels and to study their morphology and histologic properties. In this paper, we characterize different tissues based on Radio Frequency, texture-based, slope-based, and combined features. To deal with the classification of multiple tissues, we require the use of robust multi-class learning techniques. In this context, we propose a strategy to model multi-class classification tasks using sub-classes information in the ECOC framework. The new strategy splits the classes into different subsets according to the applied base classifier. Complex IVUS data sets containing overlapping data are learnt by splitting the original set of classes into sub-classes, and embedding the binary problems in a problem-dependent ECOC design. The method automatically characterizes different tissues, showing performance improvements over the state-of-the-art ECOC techniques for different base classifiers and feature sets.
|
|
|
Debora Gil, Petia Radeva, & J. Mauri. (2002). Ivus Segmentation Via a Regularized Curvature Flow. In X Congreso Anual de la Sociedad Española de Ingeniería Biomédica CASEIB 2002 (pp. 133–136). Saragossa, Espanya.
Abstract: Cardiac diseases are diagnosed and treated through a study of the morphology and dynamics of cardiac arteries. In- travascular Ultrasound (IVUS) imaging is of high interest to physicians since it provides both information. At the current state-of-the-art in image segmentation, a robust detection of the arterial lumen in IVUS demands manual intervention or ECG-gating. Manual intervention is a tedious and time consuming task that requires experienced observers, meanwhile ECG-gating is an acquisition technique not available in all clinical centers. We introduce a parametric algorithm that detects the arterial luminal border in in vivo sequences. The method consist in smoothing the sequences’ level surfaces under a regularized mean curvature flow that admits non-trivial steady states. The flow is based on a measure of the surface local smoothness that takes into account regularity of the surface curvature.
|
|
|
Javier Varona, Jordi Gonzalez, Xavier Roca, & Juan J. Villanueva. (2000). iTrack: Image-based Probabilistic Tracking of People. In 15 th International Conference on Pattern Recognition (Vol. 3, pp. 1122–1125).
|
|
|
ChuanMing Fang, Kai Wang, & Joost Van de Weijer. (2023). IterInv: Iterative Inversion for Pixel-Level T2I Models. In 37th Annual Conference on Neural Information Processing Systems.
Abstract: Large-scale text-to-image diffusion models have been a ground-breaking development in generating convincing images following an input text prompt. The goal of image editing research is to give users control over the generated images by modifying the text prompt. Current image editing techniques are relying on DDIM inversion as a common practice based on the Latent Diffusion Models (LDM). However, the large pretrained T2I models working on the latent space as LDM suffer from losing details due to the first compression stage with an autoencoder mechanism. Instead, another mainstream T2I pipeline working on the pixel level, such as Imagen and DeepFloyd-IF, avoids this problem. They are commonly composed of several stages, normally with a text-to-image stage followed by several super-resolution stages. In this case, the DDIM inversion is unable to find the initial noise to generate the original image given that the super-resolution diffusion models are not compatible with the DDIM technique. According to our experimental findings, iteratively concatenating the noisy image as the condition is the root of this problem. Based on this observation, we develop an iterative inversion (IterInv) technique for this stream of T2I models and verify IterInv with the open-source DeepFloyd-IF model. By combining our method IterInv with a popular image editing method, we prove the application prospects of IterInv. The code will be released at \url{this https URL}.
|
|