Recently, object detection has continued to evolve from its current state, and due to its technology, it can be found across almost every technological platform. Whether it is through image classification, recognition, or localization, these are all based on object detection. Convolutional neural networks (CNNs) can bring together many object recognition and classification techniques together by incorporating deep learning and computer vision methods. In computer vision, convolutional neural networks, as the name suggests, apply a convolution layer in each pixel image in a dataset. Due to computer vision and deep learning fundamentals in its primary structure, CNNs obtain a different output layer step-by-step by moving the filter we specify onto an image.

Kate Crawford, one of the world's pre-eminent scholars on the social and political implications of artificial intelligence, is being watched. She has arrived at our meeting point outside an anonymous inner-Sydney building before me and, while she waits on the footpath, is twice questioned by people who seem to be security staff. A woman is the first to come out of the building. Are you meeting someone here, she asks, do you have an appointment? He asks Crawford if there's anything she needs.

Background and aim: Surgical telepresence using augmented perception has been applied, but mixed reality is still being researched and is only theoretical. The aim of this work is to propose a solution to improve the visualization in the final merged video by producing globally consistent videos when the intensity of illumination in the input source and target video varies. Methodology: The proposed system uses an enhanced multi-layer visualization with illumination-aware gradient mixing using Illumination Aware Video Composition algorithm. Particle Swarm Optimization Algorithm is used to find the best sample pair from foreground and background region and image pixel correlation to estimate the alpha matte. Particle Swarm Optimization algorithm helps to get the original colour and depth of the unknown pixel in the unknown region. Result: Our results showed improved accuracy caused by reducing the Mean squared Error for selecting the best sample pair for unknown region in 10 each sample for bowel, jaw and breast. The amount of this reduction is 16.48% from the state of art system. As a result, the visibility accuracy is improved from 89.4 to 97.7% which helped to clear the hand vision even in the difference of light. Conclusion: Illumination effect and alpha pixel correlation improves the visualization accuracy and produces a globally consistent composition results and maintains the temporal coherency when compositing two videos with high and inverse illumination effect. In addition, this paper provides a solution for selecting the best sampling pair for the unknown region to obtain the original colour and depth.

Convolutional Neural Networks (CNNs) are widely used in deep learning applications, e.g. visual systems, robotics etc. However, existing software solutions are not efficient. Therefore, many hardware accelerators have been proposed optimizing performance, power and resource utilization of the implementation. Amongst existing solutions, Field Programmable Gate Array (FPGA) based architecture provides better cost-energy-performance trade-offs as well as scalability and minimizing development time. In this paper, we present a model-independent reconfigurable co-processing architecture to accelerate CNNs. Our architecture consists of parallel Multiply and Accumulate (MAC) units with caching techniques and interconnection networks to exploit maximum data parallelism. In contrast to existing solutions, we introduce limited precision 32 bit Q-format fixed point quantization for arithmetic representations and operations. As a result, our architecture achieved significant reduction in resource utilization with competitive accuracy. Furthermore, we developed an assembly-type microinstructions to access the co-processing fabric to manage layer-wise parallelism, thereby making re-use of limited resources. Finally, we have tested our architecture up to 9x9 kernel size on Xilinx Virtex 7 FPGA, achieving a throughput of up to 226.2 GOp/S for 3x3 kernel size.

As machine learning is applied more widely, it is necessary to have a machine learning platform for both infrastructure administrators and users including expert data scientists and citizen data scientists to improve their productivity. However, existing machine learning platforms are ill-equipped to address the "Machine Learning tech debts" such as glue code, reproducibility, and portability. Furthermore, existing platforms only take expert data scientists into consideration, and thus they are inflexible for infrastructure administrators and non-user-friendly for citizen data scientists. We propose Submarine, a unified machine learning platform, to address the challenges.

Every day we are surrounded by spoken dialog. This medium delivers rich diverse streams of information auditorily; however, systematically understanding dialog can often be non-trivial. Despite the pervasiveness of spoken dialog, automated speech understanding and quality information extraction remains markedly poor, especially when compared to written prose. Furthermore, compared to understanding text, auditory communication poses many additional challenges such as speaker disfluencies, informal prose styles, and lack of structure. These concerns all demonstrate the need for a distinctly speech tailored interactive system to help users understand and navigate the spoken language domain. While individual automatic speech recognition (ASR) and text summarization methods already exist, they are imperfect technologies; neither consider user purpose and intent nor address spoken language induced complications. Consequently, we design a two stage ASR and text summarization pipeline and propose a set of semantic segmentation and merging algorithms to resolve these speech modeling challenges. Our system enables users to easily browse and navigate content as well as recover from errors in these underlying technologies. Finally, we present an evaluation of the system which highlights user preference for hierarchical summarization as a tool to quickly skim audio and identify content of interest to the user.

The ubiquitous availability of computing devices and the widespread use of the internet have generated a large amount of data continuously. Therefore, the amount of available information on any given topic is far beyond humans' processing capacity to properly process, causing what is known as information overload. To efficiently cope with large amounts of information and generate content with significant value to users, we require identifying, merging and summarising information. Data summaries can help gather related information and collect it into a shorter format that enables answering complicated questions, gaining new insight and discovering conceptual boundaries. This thesis focuses on three main challenges to alleviate information overload using novel summarisation techniques. It further intends to facilitate the analysis of documents to support personalised information extraction. This thesis separates the research issues into four areas, covering (i) feature engineering in document summarisation, (ii) traditional static and inflexible summaries, (iii) traditional generic summarisation approaches, and (iv) the need for reference summaries. We propose novel approaches to tackle these challenges, by: i)enabling automatic intelligent feature engineering, ii) enabling flexible and interactive summarisation, iii) utilising intelligent and personalised summarisation approaches. The experimental results prove the efficiency of the proposed approaches compared to other state-of-the-art models. We further propose solutions to the information overload problem in different domains through summarisation, covering network traffic data, health data and business process data.

As Artificial Intelligence (AI) is used in more applications, the need to consider and mitigate biases from the learned models has followed. Most works in developing fair learning algorithms focus on the offline setting. However, in many real-world applications data comes in an online fashion and needs to be processed on the fly. Moreover, in practical application, there is a trade-off between accuracy and fairness that needs to be accounted for, but current methods often have multiple hyperparameters with non-trivial interaction to achieve fairness. In this paper, we propose a flexible ensemble algorithm for fair decision-making in the more challenging context of evolving online settings. This algorithm, called FARF (Fair and Adaptive Random Forests), is based on using online component classifiers and updating them according to the current distribution, that also accounts for fairness and a single hyperparameters that alters fairness-accuracy balance. Experiments on real-world discriminated data streams demonstrate the utility of FARF.

Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boosted performance on various tasks using visual cues, deep cognition to reason intentions, motivation, or causality remains challenging. Existing datasets that aim to examine video reasoning capability focus on visual signals such as actions, objects, relations, or could be answered utilizing text bias. Observing this, we propose a novel task, along with a new dataset: Trope Understanding in Movies and Animations (TrUMAn), with 2423 videos associated with 132 tropes, intending to evaluate and develop learning systems beyond visual signals. Tropes are frequently used storytelling devices for creative works. By coping with the trope understanding task and enabling the deep cognition skills of machines, data mining applications and algorithms could be taken to the next level. To tackle the challenging TrUMAn dataset, we present a Trope Understanding and Storytelling (TrUSt) with a new Conceptual Storyteller module, which guides the video encoder by performing video storytelling on a latent space. Experimental results demonstrate that state-of-the-art learning systems on existing tasks reach only 12.01% of accuracy with raw input signals. Also, even in the oracle case with human-annotated descriptions, BERT contextual embedding achieves at most 28% of accuracy. Our proposed TrUSt boosts the model performance and reaches 13.94% performance. We also provide detailed analysis to pave the way for future research. TrUMAn is publicly available at:https://www.cmlab.csie.ntu.edu.tw/project/trope

More than 90 policy groups from the US and around the world signed an open letter urging Apple to drop its plan to have Apple devices scan photos for child sexual abuse material (CSAM). This story originally appeared on Ars Technica, a trusted source for technology news, tech policy analysis, reviews, and more. Ars is owned by WIRED's parent company, Condé Nast. "The undersigned organizations committed to civil rights, human rights, and digital rights around the world are writing to urge Apple to abandon the plans it announced on 5 August 2021 to build surveillance capabilities into iPhones, iPads, and other Apple products," the letter to Apple CEO Tim Cook said. "Though these capabilities are intended to protect children and to reduce the spread of child sexual abuse material (CSAM), we are concerned that they will be used to censor protected speech, threaten the privacy and security of people around the world, and have disastrous consequences for many children." The Center for Democracy and Technology (CDT) announced the letter, with CDT Security and Surveillance Project codirector Sharon Bradford Franklin saying, "We can expect governments will take advantage of the surveillance capability Apple is building into iPhones, iPads, and computers.