With the rapid development of autonomous driving technology, autonomous vehicles have become a critical direction for the future of transportation. Ensuring efficient and safe autonomous driving relies heavily on the accuracy of perception systems. However, traditional vision-based perception systems often face significant challenges in adverse visual conditions and complex road environments. To address these issues, this study proposes a multi-modal object detection method based on pixel-level fusion and a multi-scale feature focus diffusion mechanism. A multi-modal fusion module is designed at the entry point of the backbone network to integrate infrared and visible light images, significantly enhancing the model’s detection capability under poor visual conditions. Additionally, a novel multi-scale feature diffusion network is developed using a self-designed multi-scale focus module to iteratively fuse and diffuse features across three different scales, improving the model’s adaptive receptive field for features of varying scales and enhancing detection efficiency in complex road scenarios. A multi-modal dataset is also constructed to support further research in this field. Comparative experiments on three public datasets and a self-constructed dataset show that the proposed model, DAF-MFNet (Diffusion and Focus Multimodal Fusion Network), achieves state-of-the-art detection performance. On the self-constructed dataset, our model outperforms the strong baseline YOLOv8, with [email protected] and [email protected] improvements of 6.9% and 3.5%, respectively, demonstrating its strong adaptability to object detection in the autonomous driving domain.

We operate one of the largest short video streaming platforms in the world, serving billions of global users every day. Similar to other platforms, we employ Adaptive Bitrate (ABR) streaming, which adaptively selects an appropriate representation from a group of video representations forming a bitrate ladder. In this paper, instead of developing yet another ABR algorithm, we optimize the bitrate ladder configuration, which constitutes the decision space of ABR, by developing a system called TLadder.

Despite years of research attention, localization-based indoor navigation has not found wide-spread practical use, largely due to the high burden on deployment and bootstrapping. Lightweight peer-to-peer navigation systems that use a leader-follower model have recently been proposed to alleviate these burdens. However, typical peer-to-peer navigation suffers from poor scalability and flexibility as navigation is only possible over pre-collected leader paths. In this paper, we present FollowUs, an easily-deployable (bootstrap-free) and scalable indoor navigation system. In addition to robust navigation through real-time trace-following, FollowUs integrates cloud services to process and combine traces at large scale. Optionally, it can also leverage floor plans to further enhance navigation efficiency. We design and implement FollowUs, including mobile app and cloud services. Experimental results from a company-internal beta release show that 91% of FollowUs' spatial errors on reaching destinations to be 3m or less, and 95% of navigation instructions are shown to users within a 4-step error margin during navigation.

Bootstrapping efforts and scalability issues hinder large-scale deployment of indoor navigation systems. We present FollowUs, an easily-deployable (bootstrap-free) and scalable indoor navigation system. In addition to robust navigation through real-time trace-following, FollowUs integrates cloud services to process and combine traces at large scale. It can also leverage optional floor plans to further enhance navigation performance. We designed and implemented FollowUs, including a mobile app and cloud services on Azure, and validate its real-world usability.

WeChat is a mobile messaging application that has 549 million active users as of Q1 2015, and “WeChat Moments” (WM) serves its social-networking function that allows users to post/share links of web pages. WM differs from the other social networks as it imposes many restrictions on the information diffusion process to mitigate the information overload. In this paper, we conduct a measurement study on information diffusion in the WM network by crawling and analyzing the spreading statistics of more than 160,000 pages that involve approximately 40 million users. Specifically, we identify the relationship of the number of posted pages and the number of views, the diffusion path length, the similarity and distribution of users' locations as well as their connections with the GDP of the users' province. For each individual WM page, we measure its temporal characteristics (e.g., the life time, the popularity within a time period); for each individual user, we evaluate how many of, or how likely, one's friends will view his posted pages. Our results will help the business to decide when and how to release the marketing pages over WM for better publicity.

The detection of face-screen distance on smartphone (i.e., the distance between the user face and the smartphone screen) is of paramount importance for many mobile applications, including dynamic adjustment of screen on-off, screen resolution, screen luminance, font size, with the purposes of power saving, protection of human eyesight, etc. Existing detection techniques for face-screen distance depend on external or internal hardware, e.g., an accessory plug-in sensor (e.g., infrared or ultrasonic sensors) to measure the face-screen distance, a built-in proximity sensor that usually outputs a coarse-grained, two-valued, proximity index (for the purpose of powering on/off the screen), etc. In this paper, we present a fine-grained detection method, called "Look Into My Eyes (LIME)", that utilizes the front camera and inertial accelerometer of the smartphone to estimate the face-screen distance. Specifically, LIME captures the photo of the user's face only when the accelerometer detects certain motion patterns of mobile phones, and then estimates the face-screen distance by looking at the distance between the user's eyes. Besides, LIME is able to take care of the user experience when multiple users are facing the phone screen. The experimental results show that LIME can achieve a mean squared error smaller than 2.4 cm in all of experimented scenarios, and it incurs a small cost on battery life when integrated into an SMS application for enabling dynamic font size by detecting the face-screen distance.