No abstract

Hashing has been proved as an attractive solution to approximate nearest neighbor search, owing to its theoretical guarantee and computational efficiency. Though most of prior hashing algorithms can achieve low memory and computation consumption by pursuing compact hash codes, however, they are still far beyond the capability of learning discriminative hash functions from the data with complex inherent structure among them. To address this issue, in this paper, we propose a structure sensitive hashing based on cluster prototypes, which explicitly exploits both global and local structures. An alternating optimization algorithm, respectively, minimizing the quantization loss and spectral embedding loss, is presented to simultaneously discover the cluster prototypes for each hash function, and optimally assign unique binary codes to them satisfying the affinity alignment between them. For hash codes of a desired length, an adaptive bit assignment is further appended to the product quantization of the subspaces, approximating the Hamming distances and meanwhile balancing the variance among hash functions. Experimental results on four large-scale benchmarks CIFAR-10, NUS-WIDE, SIFT1M, and GIST1M demonstrate that our approach significantly outperforms state-of-the-art hashing methods in terms of semantic and metric neighbor search.

With the development of cities, especially in developing countries, public transport is a major choice for millions city dwellers, which can ease the traffic pressure, such as crowdedness. However, for cities, in particular cities of developing countries, the continuous development of urban construction leads to the function of regions are changed, and then the collective that travel to specific locations in the city are redistributed, such as a new shopping mall in operation or a newbuilt community comes into service to meet travel demands of citizens. Currently, Automated Fare Collection Systems (AFCS) are widely used in cities around the world and large amounts of data from AFCS have been acquired.In this paper, we present a new framework to use the data through AFCS to discovering regions with high passenger gathering intensity and classify points in these regions with similar passenger gathering feature varying with time in dynamic way, which is called spark region. Furthermore, the novel definition group mobility pattern (GMP) is proposed to mine the regular group behavior among these spark regions. A series of analysis is employed by using large-scale and real-world data, which consists of nearly 17million people's daily public transit records, bus trajectories generated by over 14,854 buses organizations in Beijing at 20seconds interval. The actual application indicates group mobility pattern is helpful for diagnosis and understanding residence of each region with their demand for public transportation in a significant way.

In this paper, we present a novel approach to machine reading comprehension for the MS-MARCO dataset. Unlike the SQuAD dataset that aims to answer a question with exact text spans in a passage, the MS-MARCO dataset defines the task as answering a question from multiple passages and the words in the answer are not necessary in the passages. We therefore develop an extraction-then-synthesis framework to synthesize answers from extraction results. Specifically, the answer extraction model is first employed to predict the most important sub-spans from the passage as evidence, and the answer synthesis model takes the evidence as additional features along with the question and passage to further elaborate the final answers. We build the answer extraction model with state-of-the-art neural networks for single passage reading comprehension, and propose an additional task of passage ranking to help answer extraction in multiple passages. The answer synthesis model is based on the sequence-to-sequence neural networks with extracted evidences as features. Experiments show that our extraction-then-synthesis method outperforms state-of-the-art methods.

So far COVID-19 has resulted in mass deaths and huge economic losses across the world. Various measures such as quarantine and social distancing have been taken to prevent the spread of this disease. These prevention measures have changed the transmission dynamics of COVID-19 and introduced new challenges for epidemic modelling and prediction. In this paper, we study a novel disease spreading model with two important aspects. First, the proposed model takes the quarantine effect of confirmed cases on transmission dynamics into account, which can better resemble the real-world scenario. Second, our model incorporates two types of human mobility, where the intra-region human mobility is related to the internal transmission speed of the disease in the focal area and the inter-region human mobility reflects the scale of external infectious sources to a focal area. With the proposed model, we use the human mobility data from 24 cities in China and 8 states in the USA to analyse the disease spreading patterns. The results show that our model could well fit/predict the reported cases in both countries. The predictions and findings shed light on how to effectively control COVID-19 by managing human mobility behaviours.