Current technology for autonomous cars primarily focuses on getting the passenger from point A to B. Nevertheless, it has been shown that passengers are afraid of taking a ride in self-driving cars. One way to alleviate this problem is by allowing the passenger to give natural language commands to the car. However, the car can misunderstand the issued command or the visual surroundings which could lead to uncertain situations. It is desirable that the self-driving car detects these situations and interacts with the passenger to solve them. This paper proposes a model that detects uncertain situations when a command is given and finds the visual objects causing it. Optionally, a question generated by the system describing the uncertain objects is included. We argue that if the car could explain the objects in a human-like way, passengers could gain more confidence in the car's abilities. Thus, we investigate how to (1) detect uncertain situations and their underlying causes, and (2) how to generate clarifying questions for the passenger. When evaluating on the Talk2Car dataset, we show that the proposed model, \acrfull{pipeline}, improves \gls{m:ambiguous-absolute-increase} in terms of $IoU_{.5}$ compared to not using \gls{pipeline}. Furthermore, we designed a referring expression generator (REG) \acrfull{reg_model} tailored to a self-driving car setting which yields a relative improvement of \gls{m:meteor-relative} METEOR and \gls{m:rouge-relative} ROUGE-l compared with state-of-the-art REG models, and is three times faster.

The Emotion Cause Extraction (ECE)} task aims to identify clauses which contain emotion-evoking information for a particular emotion expressed in text. We observe that a widely-used ECE dataset exhibits a bias that the majority of annotated cause clauses are either directly before their associated emotion clauses or are the emotion clauses themselves. Existing models for ECE tend to explore such relative position information and suffer from the dataset bias. To investigate the degree of reliance of existing ECE models on clause relative positions, we propose a novel strategy to generate adversarial examples in which the relative position information is no longer the indicative feature of cause clauses. We test the performance of existing models on such adversarial examples and observe a significant performance drop. To address the dataset bias, we propose a novel graph-based method to explicitly model the emotion triggering paths by leveraging the commonsense knowledge to enhance the semantic dependencies between a candidate clause and an emotion clause. Experimental results show that our proposed approach performs on par with the existing state-of-the-art methods on the original ECE dataset, and is more robust against adversarial attacks compared to existing models.

I made my first trip to China in late 2008. I was able to speak to developers and entrepreneurs and to get a sense of the then-nascent market for cloud computing. With over 900 million Internet users as of 2020 (according to a recent report from China Internet Network Information Center), China now has the largest user base in the world. A limited preview of the China (Beijing) Region was launched in 2013 and brought to general availability in 2016. A year later the AWS China (Ningxia) Region launched.

NSW Police has "infused" its insights platform with Microsoft Azure-based artificial intelligence and machine learning services to fast-track video and audio evidence analysis. Microsoft recently worked with Australia's largest policing agency to containerise cognitive processing for the core investigation platform in Azure and feed the results back. The work comes ahead of a future migration of insights to Azure, which is expected to take place "shortly". As revealed by iTnews in April, NSW Police is working to stand up a protected-level Azure data centre under what it calls the'Azura Cloud Project' to support its broader transformation program. NSW Police expects to retire, re-architect or replace more than 200 legacy systems with cloud-based systems as part of the program.

Australia's Charles Sturt University (CSU) has announced plans to create a "hands-free" smart farm where robots will do all the work -- no human laborers required. The challenge: The majority of the food we eat comes from farms, and as the population grows, so does the amount of food needed to feed it. However, there's a lot of work that needs to be done around a farm, and many farmers are having trouble finding people to do it. Labor shortages have been a chronic problem in farms throughout the developed world. The idea: Robots and AI could help close the labor gap, literally doing the jobs people used to do.

Apple has let use your iPhone and Apple Watch as digital car key. Come iOS 15, a new tool called Home Keys will let you do the same with a compatible smart lock to your home. It's one of several smart home-related features Apple showed off during WWDC 2021. Once you're inside your home, tighter integration between HomePod and Apple TV devices will allow you to control tvOS by issuing voice commands through one of Apple's smart speakers. For those who own both an Apple TV 4K and one or more HomePod mini speakers, the company will let you pair those devices together for a better audio experience.

Artificial intelligence capabilities are expanding exponentially, with AI now being utilized in industries from advertising to medical research. The use of AI in more sensitive areas such as facial recognition software, hiring algorithms, and healthcare provision, have precipitated debate about bias and fairness. Bias is a well-researched facet of human psychology. Research regularly exposes our unconscious preferences and prejudices, and now we see AI reflect some of these biases in their algorithms. So, how does artificial intelligence become biased? And why does this matter?

There is a growing interest in cactus cultivation because of numerous cacti uses from houseplants to food and medicinal applications. Various diseases impact the growth of cacti. To develop an automated model for the analysis of cactus disease and to be able to quickly treat and prevent damage to the cactus. The Faster R-CNN and YOLO algorithm technique were used to analyze cactus diseases automatically distributed into six groups: 1) anthracnose, 2) canker, 3) lack of care, 4) aphid, 5) rusts and 6) normal group. Based on the experimental results the YOLOv5 algorithm was found to be more effective at detecting and identifying cactus disease than the Faster R-CNN algorithm. Data training and testing with YOLOv5S model resulted in a precision of 89.7% and an accuracy (recall) of 98.5%, which is effective enough for further use in a number of applications in cactus cultivation. Overall the YOLOv5 algorithm had a test time per image of only 26 milliseconds. Therefore, the YOLOv5 algorithm was found to suitable for mobile applications and this model could be further developed into a program for analyzing cactus disease.

In E-commerce, vouchers are important marketing tools to enhance users' engagement and boost sales and revenue. The likelihood that a user redeems a voucher is a key factor in voucher distribution decision. User-item Click-Through-Rate (CTR) models are often applied to predict the user-voucher redemption rate. However, the voucher scenario involves more complicated relations among users, items and vouchers. The users' historical behavior in a voucher collection activity reflects users' voucher usage patterns, which is nevertheless overlooked by the CTR-based solutions. In this paper, we propose a Deep Multi-behavior Graph Networks (DMBGN) to shed light on this field for the voucher redemption rate prediction. The complex structural user-voucher-item relationships are captured by a User-Behavior Voucher Graph (UVG). User behavior happening both before and after voucher collection is taken into consideration, and a high-level representation is extracted by Higher-order Graph Neural Networks. On top of a sequence of UVGs, an attention network is built which can help to learn users' long-term voucher redemption preference. Extensive experiments on three large-scale production datasets demonstrate the proposed DMBGN model is effective, with 10% to 16% relative AUC improvement over Deep Neural Networks (DNN), and 2% to 4% AUC improvement over Deep Interest Network (DIN). Source code and a sample dataset are made publicly available to facilitate future research.

We propose a simple post hoc calibration method to estimate the confidence/uncertainty that a model prediction is correct on data with covariate shift, as represented by the large-scale corrupted data benchmark [Ovadia et al., 2019]. We achieve this by synthesizing surrogate calibration sets by corrupting the calibration set with varying intensities of a known corruption. Our method demonstrates significant improvements on the benchmark on a wide range of covariate shifts.