Recent deep learning-based multi-view people detection (MVD) methods have shown promising results on existing datasets. However, current methods are mainly trained and evaluated on small, single scenes with a limited number of multi-view frames and fixed camera views. As a result, these methods may not be practical for detecting people in larger, more complex scenes with severe occlusions and camera calibration errors. This paper focuses on improving multi-view people detection by developing a supervised view-wise contribution weighting approach that better fuses multi-camera information under large scenes. Besides, a large synthetic dataset is adopted to enhance the model's generalization ability and enable more practical evaluation and comparison. The model's performance on new testing scenes is further improved with a simple domain adaptation technique. Experimental results demonstrate the effectiveness of our approach in achieving promising cross-scene multi-view people detection performance.

Real-time streaming data is generated in high volumes and consumed for statistical and analytical purposes, requiring efficient and effective management by Message Queuing Systems (MQS) that ensure high throughput and low latency. ByteDance relies extensively on MQS to handle its massive streaming data across various applications. However, existing MQS solutions often fall short of meeting ByteDance's high-volume, diverse requirements. To address these challenges, we propose ByteMQ (BMQ), a cloud-native streaming data layer designed to manage ByteDance's extensive streaming data needs efficiently in the cloud. BMQ features three key designs: 1) separation of messaging and storage, utilizing ByteDance's Federated Distributed File System (DFS) for high-performance data storage; 2) adaptive resource scheduling to balance workloads and redistribute resources across multiple availability zones; and 3) historical data restructuring to support offline applications with efficient structured data management. ByteDance has migrated 99.76% of its Kafka clusters to BMQ infrastructure, achieving about a 70% reduction in resource costs. This paper shares our journey of designing and implementing BMQ, providing insights that may benefit other organizations facing similar challenges.

With the rapid development of Internet, Web pages have been more and more complex. Useful information is mixed with a lot of redundant information. In the current Web information extraction systems, manual or semi-manual methods are the majority. To improve the efficiency of information extraction, it requires us to further research the automatic method of Web information extraction. Firstly, we analyze the Web page's basic object according to the Functional-based Object Model. Then we give an automatic method to segment the Web page into semantic blocks using conditional random fields (CRFs). In order to further improve the effect of the semantic block segmentation, combining DOM structure and tree edit distance, the optimization algorithm of the semantic block is given. Finally, we give an automatic Web information extraction tool. Based on this tool, relevant experiments are carried out to evaluate the efficiency of information extraction. Compared to DOM-based Web information extraction systems, the experimental results show the increase in accuracy and recall rate.