Search

Does the stethoscope in the picture make the adjacent person a doctor or a patient? This, of course, depends on the contextual relationship of the two objects. If it is obvious, why don not explanation methods for vision models use contextual information? In this paper, we (1) review the most popular methods of explaining computer vision models by pointing out that they do not take into account context information, (2) provide examples of real-world use cases where spatial context plays a significant role, (3) propose new research directions that may lead to better use of context information in explaining computer vision models, (4) argue that a change in approach to explanations is needed from 'where' to 'how'.

Artificial Intelligence (AI) has witnessed rapid growth, especially in the subfields Natural Language Processing (NLP), Machine Learning (ML) and Computer Vision (CV). Keeping pace with this rapid progress poses a considerable challenge for researchers and professionals in the field. In this arXiv report, the second of its kind, which covers the period from January to September 2023, we aim to provide insights and analysis that help navigate these dynamic areas of AI. We accomplish this by 1) identifying the top-40 most cited papers from arXiv in the given period, comparing the current top-40 papers to the previous report, which covered the period January to June; 2) analyzing dataset characteristics and keyword popularity; 3) examining the global sectoral distribution of institutions to reveal differences in engagement across geographical areas. Our findings highlight the continued dominance of NLP: while only 16% of all submitted papers have NLP as primary category (more than 25% have CV and ML as primary category), 50% of the most cited papers have NLP as primary category, 90% of which target LLMs. Additionally, we show that i) the US dominates among both top-40 and top-9k papers, followed by China; ii) Europe clearly lags behind and is hardly represented in the top-40 most cited papers; iii) US industry is largely overrepresented in the top-40 most influential papers.

Tender notices are usually sought by most of the companies at regular intervals as a means for obtaining the contracts of various projects. These notices consist of all the required information like description of the work, period of construction, estimated amount of project, etc. In the context of Nepal, tender notices are usually published in national as well as local newspapers. The interested bidders should search all the related tender notices in newspapers. However, it is very tedious for these companies to manually search tender notices in every newspaper and figure out which bid is best suited for them. This project is built with the purpose of solving this tedious task of manually searching the tender notices. Initially, the newspapers are downloaded in PDF format using the selenium library of python. After downloading the newspapers, the e-papers are scanned and tender notices are automatically extracted using a neural network. For extraction purposes, different architectures of CNN namely ResNet, GoogleNet and Xception are used and a model with highest performance has been implemented. Finally, these extracted notices are then published on the website and are accessible to the users. This project is helpful for construction companies as well as contractors assuring quality and efficiency. This project has great application in the field of competitive bidding as well as managing them in a systematic manner.

Contrastive Language-Image Pretraining (CLIP) models are able to capture the semantic relationship of images and texts and have enabled a wide range of applications, from image retrieval to classification. These models are trained with datasets extracted from web crawls, which are of large quantity but limited quality. This paper explores whether limited amounts higher quality data in a specific domain improve the general performance of CLIP models. To this purpose, we extract text-image data from scientific papers hosted in the arXiv and PubMed Central repositories. Experiments on small-scale CLIP models (ViT B/32) show that model performance increases on average, but only moderately. This result indicates that using the data sources considered in the paper to train large-scale CLIP models is a worthwile research direction., Comment: ICCV 2023 Workshop

Generative deep learning models are able to create realistic audio and video. This technology has been used to impersonate the faces and voices of individuals. These ``deepfakes'' are being used to spread misinformation, enable scams, perform fraud, and blackmail the innocent. The technology continues to advance and today attackers have the ability to generate deepfakes in real-time. This new capability poses a significant threat to society as attackers begin to exploit the technology in advances social engineering attacks. In this paper, we discuss the implications of this emerging threat, identify the challenges with preventing these attacks and suggest a better direction for researching stronger defences.

We describe the development of a real-time smartphone app that allows the user to digitize paper receipts in a novel way by "waving" their phone over the receipts and letting the app automatically detect and rectify the receipts for subsequent text recognition. We show that traditional computer vision algorithms for edge and corner detection do not robustly detect the non-linear and discontinuous edges and corners of a typical paper receipt in real-world settings. This is particularly the case when the colors of the receipt and background are similar, or where other interfering rectangular objects are present. Inaccurate detection of a receipt's corner positions then results in distorted images when using an affine projective transformation to rectify the perspective. We propose an innovative solution to receipt corner detection by treating each of the four corners as a unique "object", and training a Single Shot Detection MobileNet object detection model. We use a small amount of real data and a large amount of automatically generated synthetic data that is designed to be similar to real-world imaging scenarios. We show that our proposed method robustly detects the four corners of a receipt, giving a receipt detection accuracy of 85.3% on real-world data, compared to only 36.9% with a traditional edge detection-based approach. Our method works even when the color of the receipt is virtually indistinguishable from the background. Moreover, our method is trained to detect only the corners of the central target receipt and implicitly learns to ignore other receipts, and other rectangular objects. Including synthetic data allows us to train an even better model. These factors are a major advantage over traditional edge detection-based approaches, allowing us to deliver a much better experience to the user.

Medieval paper, a handmade product, is made with a mould which leaves an indelible imprint on the sheet of paper. This imprint includes chain lines, laid lines and watermarks which are often visible on the sheet. Extracting these features allows the identification of paper stock and gives information about chronology, localisation and movement of books and people. Most computational work for feature extraction of paper analysis has so far focused on radiography or transmitted light images. While these imaging methods provide clear visualisation for the features of interest, they are expensive and time consuming in their acquisition and not feasible for smaller institutions. However, reflected light images of medieval paper manuscripts are abundant and possibly cheaper in their acquisition. In this paper, we propose algorithms to detect and extract the laid and chain lines from reflected light images. We tackle the main drawback of reflected light images, that is, the low contrast attenuation of lines and intensity jumps due to noise and degradation, by employing the spectral total variation decomposition and develop methods for subsequent line extraction. Our results clearly demonstrate the feasibility of using reflected light images in paper analysis. This work enables the feature extraction for paper manuscripts that have otherwise not been analysed due to a lack of appropriate images. We also open the door for paper stock identification at scale.

The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. The goal of domain adaptation (DA) is to mitigate this domain shift problem by searching for an optimal feature transformation to learn a domain-invariant representation. Such a domain shift can appear in handwriting recognition (HWR) applications where the motion pattern of the hand and with that the motion pattern of the pen is different for writing on paper and on tablet. This becomes visible in the sensor data for online handwriting (OnHW) from pens with integrated inertial measurement units. This paper proposes a supervised DA approach to enhance learning for OnHW recognition between tablet and paper data. Our method exploits loss functions such as maximum mean discrepancy and correlation alignment to learn a domain-invariant feature representation (i.e., similar covariances between tablet and paper features). We use a triplet loss that takes negative samples of the auxiliary domain (i.e., paper samples) to increase the amount of samples of the tablet dataset. We conduct an evaluation on novel sequence-based OnHW datasets (i.e., words) and show an improvement on the paper domain with an early fusion strategy by using pairwise learning., Comment: Accepted at IAPR Intl. Workshop on Multimodal Pattern Recognition of Social Signals in Human Computer Interaction (MPRSS), Montreal, Canada, August 2022

Image denoising (removal of additive white Gaussian noise from an image) is one of the oldest and most studied problems in image processing. An extensive work over several decades has led to thousands of papers on this subject, and to many well-performing algorithms for this task. Indeed, 10 years ago, these achievements have led some researchers to suspect that "Denoising is Dead", in the sense that all that can be achieved in this domain has already been obtained. However, this turned out to be far from the truth, with the penetration of deep learning (DL) into image processing. The era of DL brought a revolution to image denoising, both by taking the lead in today's ability for noise removal in images, and by broadening the scope of denoising problems being treated. Our paper starts by describing this evolution, highlighting in particular the tension and synergy that exist between classical approaches and modern DL-based alternatives in design of image denoisers. The recent transitions in the field of image denoising go far beyond the ability to design better denoisers. In the 2nd part of this paper we focus on recently discovered abilities and prospects of image denoisers. We expose the possibility of using denoisers to serve other problems, such as regularizing general inverse problems and serving as the prime engine in diffusion-based image synthesis. We also unveil the idea that denoising and other inverse problems might not have a unique solution as common algorithms would have us believe. Instead, we describe constructive ways to produce randomized and diverse high quality results for inverse problems, all fueled by the progress that DL brought to image denoising. This survey paper aims to provide a broad view of the history of image denoising and closely related topics. Our aim is to give a better context to recent discoveries, and to the influence of DL in our domain.

To date, a large number of research papers have been written on the classification of malware, its identification, classification into different families and the distinction between malware and goodware. These works have been based on captured malware samples and have attempted to analyse malware and goodware using various techniques, including techniques from the field of artificial intelligence. For example, neural networks have played a significant role in these classification methods. Some of this work also deals with analysing malware using its visualisation. These works usually convert malware samples capturing the structure of malware into image structures, which are then the object of image processing. In this paper, we propose a very unconventional and novel approach to malware visualisation based on dynamic behaviour analysis, with the idea that the images, which are visually very interesting, are then used to classify malware concerning goodware. Our approach opens an extensive topic for future discussion and provides many new directions for research in malware analysis and classification, as discussed in conclusion. The results of the presented experiments are based on a database of 6 589 997 goodware, 827 853 potentially unwanted applications and 4 174 203 malware samples provided by ESET and selected experimental data (images, generating polynomial formulas and software generating images) are available on GitHub for interested readers. Thus, this paper is not a comprehensive compact study that reports the results obtained from comparative experiments but rather attempts to show a new direction in the field of visualisation with possible applications in malware analysis., Comment: This paper is under review; the section describing conversion from malware structure to fractal figure is temporarily erased here to protect our idea. It will be replaced by a full version when accepted