Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain. To address the large domain gap issue between the source and target domains, we propose a novel regularization method for domain adaptive object detection, BlenDA, by generating the pseudo samples of the intermediate domains and their corresponding soft domain labels for adaptation training. The intermediate samples are generated by dynamically blending the source images with their corresponding translated images using an off-the-shelf pre-trained text-to-image diffusion model which takes the text label of the target domain as input and has demonstrated superior image-to-image translation quality. Based on experimental results from two adaptation benchmarks, our proposed approach can significantly enhance the performance of the state-of-the-art domain adaptive object detector, Adversarial Query Transformer (AQT). Particularly, in the Cityscapes to Foggy Cityscapes adaptation, we achieve an impressive 53.4% mAP on the Foggy Cityscapes dataset, surpassing the previous state-of-the-art by 1.5%. It is worth noting that our proposed method is also applicable to various paradigms of domain adaptive object detection. The code is available at https://github.com/aiiu-lab/BlenDA

In this paper, we study a novel type of spatial queries, namely Nearest Window Cluster (NWC) queries. For a given query location q, NWC (q; l; w; n) retrieves n objects within a window of length l and width w, where the distance between the query location q to these n objects is the shortest. To facilitate efficient NWC query processing, we identify several properties and accordingly develop an NWC algorithm. Moreover, we propose several optimization techniques to further reduce the search cost. To validate our ideas, we conduct a comprehensive performance evaluation using both real and synthetic datasets. Experimental results show that the proposed NWC algorithm, along with the optimization techniques, is very efficient under various datasets and parameter settings.

In this paper, we propose a novel integrated API service system as well as a Web API script to enable mobile mashup application developers to invoke Web APIs in a consistent way, and provide a consistent format for the responses of Web APIs, thereby relieving developers of striving to study the usage of various Web APIs.

Caching valid regions of spatial queries at mobile clients is effective in reducing the number of queries submitted by mobile clients and query load on the server. However, mobile clients suffer from longer waiting time for the server to compute valid regions. We propose in this paper a proxy-based approach to continuous nearest-neighbor (NN) and window queries. The proxy creates estimated valid regions (EVRs) for mobile clients by exploiting spatial and temporal locality of spatial queries. For NN queries, we devise two new algorithms to accelerate EVR growth, leading the proxy to build effective EVRs even when the cache size is small. On the other hand, we propose to represent the EVRs of window queries in the form of vectors, called estimated window vectors (EWVs), to achieve larger estimated valid regions. This novel representation and the associated creation algorithm result in more effective EVRs of window queries. In addition, due to the distinct characteristics, we use separate index structures, namely EVR-tree and grid index, for NN queries and window queries, respectively. To further increase efficiency, we develop algorithms to exploit the results of NN queries to aid grid index growth, benefiting EWV creation of window queries. Similarly, the grid index is utilized to support NN query answering and EVR updating. We conduct several experiments for performance evaluation. The experimental results show that the proposed approach significantly outperforms the existing proxy-based approaches.

Traditional routing protocols in wireless mesh networks establish a single data path between a source and a destination. However, the performance suffers from degradation and instability due to variation of wireless links and interference. Opportunistic routing has been proposed to overcome the problem by exploiting the broadcast nature of wireless links and multiple forwarders. Current opportunistic routing protocols with network coding improve the system performance but suffer from redundant packet transmissions because a source stops transmitting packets in the same segment until it receives an ACK message from the destination. In this paper, we propose a pipelined opportunistic routing protocol with network coding (PipelineOR) in which segments are transmitted in a pipelined manner. A source is allowed to send packets in the next segment without waiting for the ACK message from the destination. In addition, we present two mechanisms, namely ETX-based mechanism and DCounter-based mechanism, to suppress forwarders to transmit redundant packets. The simulation results show that the proposed PipelineOR outperforms MORE [7] and CodeOR [8] in terms of transmission time.