Abstract: Pretraining has proven successful in Document Intelligence tasks where deluge of documents are used to pretrain the models only later to be finetuned on downstream tasks. One of the problems of the pretraining approaches is the inconsistent usage of pretraining data with different OCR engines leading to incomparable results between models. In other words, it is not obvious whether the performance gain is coming from diverse usage of amount of data and distinct OCR engines or from the proposed models. To remedy the problem, we make public the OCR annotations for IDL documents using commercial OCR engine given their superior performance over open source OCR models. The contributed dataset (OCR-IDL) has an estimated monetary value over 20K US$. It is our hope that OCR-IDL can be a starting point for future works on Document Intelligence. All of our data and its collection process with the annotations can be found in this https URL.

Abstract: In this paper we present our image preprocessing methods as a key part of our automatic polyp localization scheme. These methods are used to assess the impact of different endoluminal scene elements when characterizing polyps. More precisely we tackle the influence of specular highlights, blood vessels and black mask surrounding the scene. Experimental results prove that the appropriate handling of these elements leads to a great improvement in polyp localization results.

Abstract: One of the first usual steps in pattern recognition schemas is image segmentation, in order to reduce the dimensionality of the problem and manage smaller quantity of data. In our case as we are pursuing real-time colon cancer polyp detection, this step is crucial. In this paper we present a non-informative region estimation algorithm that will let us discard some parts of the image where we will not expect to find colon cancer polyps. The performance of our approach will be measured in terms of both non-informative areas elimination and polyps’ areas preserving. The results obtained show the importance of having correct non- informative region estimation in order to fasten the whole recognition process.

Abstract: Aesthetic image analysis is essential for improving the performance of multimedia image retrieval systems, especially from a repository of social media and multimedia content stored on mobile devices. This paper presents a novel method for classifying aesthetic natural scene images by studying the naturalness of image content using statistical features, and reading text in the images using semantic features. Unlike existing methods that focus only on image quality with human information, the proposed approach focuses on image features as well as text-based semantic features without human intervention to reduce the gap between subjectivity and objectivity in the classification. The aesthetic classes considered in this work are (i) Very Pleasant, (ii) Pleasant, (iii) Normal and (iv) Unpleasant. The naturalness is represented by features of focus, defocus, perceived brightness, perceived contrast, blurriness and noisiness, while semantics are represented by text recognition, description of the images and labels of images, profile pictures, and banner images. Furthermore, a deep learning model is proposed in a novel way to fuse statistical and semantic features for the classification of aesthetic natural scene images. Experiments on our own dataset and the standard datasets demonstrate that the proposed approach achieves 92.74%, 88.67% and 83.22% average classification rates on our own dataset, AVA dataset and CUHKPQ dataset, respectively. Furthermore, a comparative study of the proposed model with the existing methods shows that the proposed method is effective for the classification of aesthetic social media images.

Abstract: Vision-based bronchoscopy (VB) models require the registration of the virtual lung model with the frames from the video bronchoscopy to provide effective guidance during the biopsy. The registration can be achieved by either tracking the position and orientation of the bronchoscopy camera or by calibrating its deviation from the pose (position and orientation) simulated in the virtual lung model. Recent advances in neural networks and temporal image processing have provided new opportunities for guided bronchoscopy. However, such progress has been hindered by the lack of comparative experimental conditions.
In the present paper, we share a novel synthetic dataset allowing for a fair comparison of methods. Moreover, this paper investigates several neural network architectures for the learning of temporal information at different levels of subject personalization. In order to improve orientation measurement, we also present a standardized comparison framework and a novel metric for camera orientation learning. Results on the dataset show that the proposed metric and architectures, as well as the standardized conditions, provide notable improvements to current state-of-the-art camera pose estimation in video bronchoscopy.

Abstract: In this paper we describe a system for automatic people counting in crowded environments. The approach we propose is a counting-by-detection method based on depth imagery. It is designed to be deployed as an autonomous appliance for crowd analysis in video surveillance application scenarios. Our system performs foreground/background segmentation on depth image streams in order to coarsely segment persons, then depth information is used to localize head candidates which are then tracked in time on an automatically estimated ground plane. The system runs in real-time, at a frame-rate of about 20 fps. We collected a dataset of RGB-D sequences representing three typical and challenging surveillance scenarios, including crowds, queuing and groups. An extensive comparative evaluation is given between our system and more complex, Latent SVM-based head localization for person counting applications.

Abstract: Most existing color constancy algorithms assume uniform illumination. However, in real-world scenes, this is not often the case. Thus, we propose a novel framework for estimating the colors of multiple illuminants and their spatial distribution in the scene. We formulate this problem as an energy minimization task within a conditional random field over a set of local illuminant estimates. In order to quantitatively evaluate the proposed method, we created a novel data set of two-dominant-illuminant images comprised of laboratory, indoor, and outdoor scenes. Unlike prior work, our database includes accurate pixel-wise ground truth illuminant information. The performance of our method is evaluated on multiple data sets. Experimental results show that our framework clearly outperforms single illuminant estimators as well as a recently proposed multi-illuminant estimation approach.