Video salient object ranking aims to simulate the human attention mechanism by dynamically prioritizing the visual attraction of objects in a scene over time. Despite its numerous practical applications, this area remains underexplored. In this work, we propose a graph model for video salient object ranking. This graph simultaneously explores multi-scale spatial contrasts and intra-/inter-instance temporal correlations across frames to extract diverse spatio-temporal saliency cues. It has two advantages: 1. Unlike previous methods that only perform global inter-frame contrast or compare all proposals across frames globally, we explicitly model the motion of each instance by comparing its features with those in the same spatial region in adjacent frames, thus obtaining more accurate motion saliency cues.

In this paper, we revisit the problem of smoothed online learning, in which the online learner suffers both a hitting cost and a switching cost, and target two performance metrics: competitive ratio and dynamic regret with switching cost. To bound the competitive ratio, we assume the hitting cost is known to the learner in each round, and investigate the simple idea of balancing the two costs by an optimization problem.

In this paper, we investigate an online prediction strategy named as Discounted-Normal-Predictor [Kapralov and Panigrahy, 2010] for smoothed online convex optimization (SOCO), in which the learner needs to minimize not only the hitting cost but also the switching cost. In the setting of learning with expert advice, Daniely and Mansour [2019] demonstrate that Discounted-Normal-Predictor can be utilized to yield nearly optimal regret bounds over any interval, even in the presence of switching costs. Inspired by their results, we develop a simple algorithm for SOCO: Combining online gradient descent (OGD) with different step sizes sequentially by Discounted-Normal-Predictor. Despite its simplicity, we prove that it is able to minimize the adaptive regret with switching cost, i.e., attaining nearly optimal regret with switching cost on every interval. By exploiting the theoretical guarantee of OGD for dynamic regret, we further show that the proposed algorithm can minimize the dynamic regret with switching cost in every interval.

NANJING: China has been invited to test its artificial intelligence (AI) solutions in Singapore and work together to help the region tackle everyday problems in areas such as healthcare and banking. Minister for Finance Heng Swee Keat made this invitation at the first Sino-Singapore Artificial Intelligence Forum in Nanjing on Friday (Jun 1), which was attended by about 350 AI experts from both countries. During his speech, which was partly delivered in Chinese, Mr Heng said that there was big potential for both countries to develop AI. "For example, the Monetary Authority of Singapore has a financial technology (Fintech) sandbox for companies to develop new financial solutions before launching them in the market," said Mr Heng, who is also in China for a series of meetings. Sandboxes are platforms that allow software to be securely tested in an environment where legal and regulatory requirements are relaxed. The Land Transport Authority is also testing driverless vehicle systems in such sandboxes in Singapore, Mr Heng said.

On the morning of December 13th, 1937, Japanese troops pounded on the door of Xia Shuqin's family home in Nanjing, China. Thirteen people had taken shelter under this particular roof: Eight-year-old Xia, her mother and father, two grandparents, four sisters (one, four, 13 and 15 years old), and four neighbors. The Japanese army had ridden into the city on horseback that morning and faced little resistance; the Chinese army had made a full, chaotic retreat the prior evening, December 12th.