Optical Character Recognition (OCR) is an established task with the objective of identifying the text present in an image. While many off-the-shelf OCR models exist, they are often trained for either scientific (e.g., formulae) or generic printed English text. Extracting text from chemistry publications requires an OCR model that is capable in both realms. Nougat, a recent tool, exhibits strong ability to parse academic documents, but is unable to parse tables in PubMed articles, which comprises a significant part of the academic community and is the focus of this work. To mitigate this gap, we present the Printed English and Chemical Equations (PEaCE) dataset, containing both synthetic and real-world records, and evaluate the efficacy of transformer-based OCR models when trained on this resource. Given that real-world records contain artifacts not present in synthetic records, we propose transformations that mimic such qualities. We perform a suite of experiments to explore the impact of patch size, multi-domain training, and our proposed transformations, ultimately finding that models with a small patch size trained on multiple domains using the proposed transformations yield the best performance. Our dataset and code is available at https://github.com/ZN1010/PEaCE.

As the privacy risks posed by camera surveillance and facial recognition have grown, so has the research into privacy preservation algorithms. Among these, visual privacy preservation algorithms attempt to impart bodily privacy to subjects in visuals by obfuscating privacy-sensitive areas. While disparate performances of facial recognition systems across phenotypes are the subject of much study, its counterpart, privacy preservation, is not commonly analysed from a fairness perspective. In this paper, the fairness of commonly used visual privacy preservation algorithms is investigated through the performances of facial recognition models on obfuscated images. Experiments on the PubFig dataset clearly show that the privacy protection provided is unequal across groups.

To date, the privacy-protection intended pixelation tasks are still labor-intensive and yet to be studied. With the prevailing of video live streaming, establishing an online face pixelation mechanism during streaming is an urgency. In this paper, we develop a new method called Face Pixelation in Video Live Streaming (FPVLS) to generate automatic personal privacy filtering during unconstrained streaming activities. Simply applying multi-face trackers will encounter problems in target drifting, computing efficiency, and over-pixelation. Therefore, for fast and accurate pixelation of irrelevant people's faces, FPVLS is organized in a frame-to-video structure of two core stages. On individual frames, FPVLS utilizes image-based face detection and embedding networks to yield face vectors. In the raw trajectories generation stage, the proposed Positioned Incremental Affinity Propagation (PIAP) clustering algorithm leverages face vectors and positioned information to quickly associate the same person's faces across frames. Such frame-wise accumulated raw trajectories are likely to be intermittent and unreliable on video level. Hence, we further introduce the trajectory refinement stage that merges a proposal network with the two-sample test based on the Empirical Likelihood Ratio (ELR) statistic to refine the raw trajectories. A Gaussian filter is laid on the refined trajectories for final pixelation. On the video live streaming dataset we collected, FPVLS obtains satisfying accuracy, real-time efficiency, and contains the over-pixelation problems.

With the prevailing of live video streaming, establishing an online pixelation method for privacy-sensitive objects is an urgency. Caused by the inaccurate detection of privacy-sensitive objects, simply migrating the tracking-by-detection structure into the online form will incur problems in target initialization, drifting, and over-pixelation. To cope with the inevitable but impacting detection issue, we propose a novel Privacy-sensitive Objects Pixelation (PsOP) framework for automatic personal privacy filtering during live video streaming. Leveraging pre-trained detection networks, our PsOP is extendable to any potential privacy-sensitive objects pixelation. Employing the embedding networks and the proposed Positioned Incremental Affinity Propagation (PIAP) clustering algorithm as the backbone, our PsOP unifies the pixelation of discriminating and indiscriminating pixelation objects through trajectories generation. In addition to the pixelation accuracy boosting, experiments on the streaming video data we built show that the proposed PsOP can significantly reduce the over-pixelation ratio in privacy-sensitive object pixelation.

According to Massachusetts Institute of Technology (MIT), Artificial Intelligence could be the answer to reducing headaches for viewers and streaming services. Video buffering and pixelation continues to be problematic for those who rely a ton on video streaming services for catching up on the newest movies and the latest TV shows. Buffering and pixelation can make people to switch over to other content which can result in poor viewership and advertising. The way it works is that Streaming services use ABR (Adaptive BitRate) algorithms to ascertain what the resolution of the video playback is at that time which varies according to changing network conditions. Videos are typically chopped into smaller chunks and transmitted in a sequential manner to the device that viewers are watching it on.

Buffering and pixelation are the scourge of streaming video. It ruins the experience for viewers, robs advertisers of revenue as said viewers tune out, and causes technical headaches for streaming services which have to engineer solutions. But a new neural network AI from MIT CSAIL may be just what the internet needs for velvety smooth streaming services. That would take entirely too much bandwidth. So instead, that data is chopped up into smaller pieces and sent sequentially.

Ben Dickson is a software engineer and the founder of TechTalks. While machine learning is introducing innovation and change to many sectors, it also is bringing trouble and worries to others. One of the most worrying aspects of emerging machine learning technologies is their invasiveness on user privacy. From rooting out your intimate and embarrassing secrets to imitating you, machine learning is making it hard to not only hide your identity but also keep ownership of it and prevent from being attributed to you words you haven't uttered and actions you haven't taken. Here are some of the technologies that might have been created with good-natured intent, but can also be used for evil deeds when put into the wrong hands.

While machine learning is introducing innovation and change to many sectors, it also is bringing trouble and worries to others. One of the most worrying aspects of emerging machine learning technologies is their invasiveness on user privacy. From rooting out your intimate and embarrassing secrets to imitating you, machine learning is making it hard to not only hide your identity but also keep ownership of it and prevent from being attributed to you words you haven't uttered and actions you haven't taken. Here are some of the technologies that might have been created with good-natured intent, but can also be used for evil deeds when put into the wrong hands. This is a reminder that while we further delve into the seemingly countless possibilities of this exciting new technology, we should keep our eyes open for the repercussions and unwanted side-effects.

Ben Dickson is a software engineer and the founder of TechTalks. While machine learning is introducing innovation and change to many sectors, it also is bringing trouble and worries to others. One of the most worrying aspects of emerging machine learning technologies is their invasiveness on user privacy. From rooting out your intimate and embarrassing secrets to imitating you, machine learning is making it hard to not only hide your identity but also keep ownership of it and prevent from being attributed to you words you haven't uttered and actions you haven't taken. Here are some of the technologies that might have been created with good-natured intent, but can also be used for evil deeds when put into the wrong hands.

Pixelation is used heavily across the media to obscure faces, vehicle license plates and restricted pieces of text. The technique generally works well, preventing people from identifying what's beneath the blur without completely destroying the image with overlays or cut-outs. However, we may soon need to find an alternative to pixelation, according to researchers at the University of Texas. WIRED reports that a team has developed software that is able to see through a pixelated mask to determine the identity of a person beneath it. The technology is able to process images as if the pixelation simply didn't exist.