Interestingness recognition is crucial for decision making in autonomous exploration for mobile robots. Previous methods proposed an unsupervised online learning approach that can adapt to environments and detect interesting scenes quickly, but lack the ability to adapt to human-informed interesting objects. To solve this problem, we introduce a human-interactive framework, AirInteraction, that can detect human-informed objects via few-shot online learning. To reduce the communication bandwidth, we first apply an online unsupervised learning algorithm on the unmanned vehicle for interestingness recognition and then only send the potential interesting scenes to a base-station for human inspection. The human operator is able to draw and provide bounding box annotations for particular interesting objects, which are sent back to the robot to detect similar objects via few-shot learning. Only using few human-labeled examples, the robot can learn novel interesting object categories during the mission and detect interesting scenes that contain the objects. We evaluate our method on various interesting scene recognition datasets. To the best of our knowledge, it is the first human-informed few-shot object detection framework for autonomous exploration.

A convolutional network is an alternating sequence of linear filtering and nonlinear transformation operations. The input and output layers include one or more images, while intermediate layers contain "hidden" units with images called feature maps that are the internal computations of the algorithm. A convolutional network is an alternating sequence of linear filtering and nonlinear transformation operations. The input and output layers include one or more images, while intermediate layers contain "hidden" units with images called feature maps that are the internal computations of the algorithm. The border of the image is explicitly encoded by padding an area surrounding the image with values of -1.

The study provides an overview of how business professionals in the Global Machine Learning Artificial intelligence Market report have established a globally unique model to strategize the policies to contain the deleterious impact of the COVID-19 pandemic. The report highlights those market sectors that present a positive growth trend and a positive future outlook for the market participants by 2022-2027. The segments that have witnessed increase in the annual sales, market share because of the significant factors like trade and other. The Machine Learning Artificial intelligence report outlines business models and marketing strategies incorporated by market players to sustain the competition and accelerate business growth in market. Through various market scenarios, it recommends some solutions to implement in future to stay ahead of the competition and gives detailed insights about the covid-19 impact on the market.

Emerging with the support of computing and communications technologies, Metaverse is expected to bring users unprecedented service experiences. However, the increase in the number of Metaverse users places a heavy demand on network resources, especially for Metaverse services that are based on graphical extended reality and require rendering a plethora of virtual objects. To make efficient use of network resources and improve the Quality-of-Experience (QoE), we design an attention-aware network resource allocation scheme to achieve customized Metaverse services. The aim is to allocate more network resources to virtual objects in which users are more interested. We first discuss several key techniques related to Metaverse services, including QoE analysis, eye-tracking, and remote rendering. We then review existing datasets and propose the user-object-attention level (UOAL) dataset that contains the ground truth attention of 30 users to 96 objects in 1,000 images. A tutorial on how to use UOAL is presented. With the help of UOAL, we propose an attention-aware network resource allocation algorithm that has two steps, i.e., attention prediction and QoE maximization. Specially, we provide an overview of the designs of two types of attention prediction methods, i.e., interest-aware and time-aware prediction. By using the predicted user-object-attention values, network resources such as the rendering capacity of edge devices can be allocated optimally to maximize the QoE. Finally, we propose promising research directions related to Metaverse services.

Neural networks have been rapidly expanding in recent years, with novel strategies and applications. However, challenges such as interpretability, explainability, robustness, safety, trust, and sensibility remain unsolved in neural network technologies, despite the fact that they will unavoidably be addressed for critical applications. Attempts have been made to overcome the challenges in neural network computing by representing and embedding domain knowledge in terms of symbolic representations. Thus, the neuro-symbolic learning (NeSyL) notion emerged, which incorporates aspects of symbolic representation and bringing common sense into neural networks (NeSyL). In domains where interpretability, reasoning, and explainability are crucial, such as video and image captioning, question-answering and reasoning, health informatics, and genomics, NeSyL has shown promising outcomes. This review presents a comprehensive survey on the state-of-the-art NeSyL approaches, their principles, advances in machine and deep learning algorithms, applications such as opthalmology, and most importantly, future perspectives of this emerging field.

Stress during public speaking is common and adversely affects performance and self-confidence. Extensive research has been carried out to develop various models to recognize emotional states. However, minimal research has been conducted to detect stress during public speaking in real time using voice analysis. In this context, the current review showed that the application of algorithms was not properly explored and helped identify the main obstacles in creating a suitable testing environment while accounting for current complexities and limitations. In this paper, we present our main idea and propose a stress detection computational algorithmic model that could be integrated into a Virtual Reality (VR) application to create an intelligent virtual audience for improving public speaking skills. The developed model, when integrated with VR, will be able to detect excessive stress in real time by analysing voice features correlated to physiological parameters indicative of stress and help users gradually control excessive stress and improve public speaking performance

The development of compact and energy-efficient wearable sensors has led to an increase in the availability of biosignals. To analyze these continuously recorded, and often multidimensional, time series at scale, being able to conduct meaningful unsupervised data segmentation is an auspicious target. A common way to achieve this is to identify change-points within the time series as the segmentation basis. However, traditional change-point detection algorithms often come with drawbacks, limiting their real-world applicability. Notably, they generally rely on the complete time series to be available and thus cannot be used for real-time applications. Another common limitation is that they poorly (or cannot) handle the segmentation of multidimensional time series. Consequently, the main contribution of this work is to propose a novel unsupervised segmentation algorithm for multidimensional time series named Latent Space Unsupervised Semantic Segmentation (LS-USS), which was designed to work easily with both online and batch data. When comparing LS-USS against other state-of-the-art change-point detection algorithms on a variety of real-world datasets, in both the offline and real-time setting, LS-USS systematically achieves on par or better performances.

This paper considers a setting where embedded devices are used to acquire and classify images. Because of limited computing capacity, embedded devices rely on a parsimonious classification model with uneven accuracy. When local classification is deemed inaccurate, devices can decide to offload the image to an edge server with a more accurate but resource-intensive model. Resource constraints, e.g., network bandwidth, however, require regulating such transmissions to avoid congestion and high latency. The paper investigates this offloading problem when transmissions regulation is through a token bucket, a mechanism commonly used for such purposes. The goal is to devise a lightweight, online offloading policy that optimizes an application-specific metric (e.g., classification accuracy) under the constraints of the token bucket. The paper develops a policy based on a Deep Q-Network (DQN), and demonstrates both its efficacy and the feasibility of its deployment on embedded devices. Of note is the fact that the policy can handle complex input patterns, including correlation in image arrivals and classification accuracy. The evaluation is carried out by performing image classification over a local testbed using synthetic traces generated from the ImageNet image classification benchmark. Implementation of this work is available at https://github.com/qiujiaming315/edgeml-dqn.

Masked autoencoders are scalable vision learners, as the title of MAE \cite{he2022masked}, which suggests that self-supervised learning (SSL) in vision might undertake a similar trajectory as in NLP. Specifically, generative pretext tasks with the masked prediction (e.g., BERT) have become a de facto standard SSL practice in NLP. By contrast, early attempts at generative methods in vision have been buried by their discriminative counterparts (like contrastive learning); however, the success of mask image modeling has revived the masking autoencoder (often termed denoising autoencoder in the past). As a milestone to bridge the gap with BERT in NLP, masked autoencoder has attracted unprecedented attention for SSL in vision and beyond. This work conducts a comprehensive survey of masked autoencoders to shed insight on a promising direction of SSL. As the first to review SSL with masked autoencoders, this work focuses on its application in vision by discussing its historical developments, recent progress, and implications for diverse applications.

A fundamental goal of scientific research is to learn about causal relationships. However, despite its critical role in the life and social sciences, causality has not had the same importance in Natural Language Processing (NLP), which has traditionally placed more emphasis on predictive tasks. This distinction is beginning to fade, with an emerging area of interdisciplinary research at the convergence of causal inference and language processing. Still, research on causality in NLP remains scattered across domains without unified definitions, benchmark datasets and clear articulations of the challenges and opportunities in the application of causal inference to the textual domain, with its unique properties. In this survey, we consolidate research across academic areas and situate it in the broader NLP landscape. We introduce the statistical challenge of estimating causal effects with text, encompassing settings where text is used as an outcome, treatment, or to address confounding. In addition, we explore potential uses of causal inference to improve the robustness, fairness, and interpretability of NLP models. We thus provide a unified overview of causal inference for the NLP community.