Transparent object segmentation from a single image has been investigated for several years. However, detecting transparent areas from video has not been well explored, especially for different kinds of transparent categories besides glass, due to the scarcity of such a dataset. Therefore, in this paper, we propose the video-based transparent object segmentation task and introduce the first-of-its-kind corresponding dataset named TransVid, which contains nearly 400 videos with a total of 18,523 frames. Based on TranVid, we further propose a new method called TranSeg, in which we innovatively introduce Graph Neural Networks into the temporal segmentation task and combined with a novel Diffusion Model to make the model's segmentation results more accurate. Experimental results show that TranSeg achieves higher accuracy with fewer parameters than previous state-of-the-art models, demonstrating the effectiveness of our method. Moreover, comprehensive ablation analysis reveal several fascinating insights and suggest viable paths for further research.

Actively engaging learners with learning materials has been shown to be very important in the Search as Learning (SAL) setting. One active reading strategy relies on asking so-called adjunct questions, i.e., manually curated questions geared towards essential concepts of the target material. However, manual question creation is impractical given the vast online content. Recent research has explored the effects of Automatic Question Generation (AQG) on aiding human learning. These studies have primarily focused on user studies in controlled online reading scenarios with limited documents. However, the impacts of adjunct questions on learning in the SAL setting, which involves learning through web searching, are not yet well understood. This paper addresses this gap by conducting a user study with automatically generated adjunct questions integrated into the reading interface built on top of a search system. We conducted a between-subjects user study (N = 144) to investigate the incorporation of automatically generated adjunct questions on participants’ learning. We employed three different question generation strategies as well as a control condition: (i) synthesis questions; (ii) factoid questions targeting random text spans; and (iii) factoid questions targeting terms and phrases relevant to the information need at hand. We present four major findings: (i) participants who received adjunct questions exhibited significantly more fine-grained reading behaviour, such as longer document dwell time and more scrolls, than those without adjunct questions. However, adjunct questions’ influence on learning outcomes depends on the AQG strategy. (ii) Question types significantly influence participants’ reading behaviour. (iii) The adjunct questions’ target spans significantly influence learning outcomes. Lastly, (iv) participants’ prior knowledge levels affect adjunct questions’ effects on their learning outcomes and their reaction to different AQG strategies. Our findings have significant design implications for learning-oriented search systems. The data and code is available at https://github.com/zpeide/AQG-AdjunctQuestions.

Controversy is widespread online. Previous studies mainly define controversy based on vague assumptions of its relation to sentiment such as hate speech and offensive words. This paper introduces the first question-answering dataset that defines content controversy by user perception, i.e., votes from plenty of users. It contains nearly 10K questions, and each question has a best answer and a most controversial answer. Experimental results reveal that controversy detection in question answering is essential and challenging, and there is no strong correlation between controversy and sentiment tasks. We also show that controversial answers and most acceptable answers cannot be distinguished by retrieval-based QA models, which may cause controversy issues. With these insights, we believe ControversialQA can inspire future research on controversy in QA systems.

Wireless power transfer (WPT) systems using magnetic resonant coupling (MRC) have made significant progress recently, leading to various optimization methods in scenarios involving multiple-input multiple-output (MIMO) to improve charging performance. Adjusting the coil orientation of the power transmitter (TX) is a simple but effective method due to the directional nature of magnetic field distribution, but existing approaches often require unnecessary coil rotations. In this study, we introduce a Location-Aware Orientation Adjustment algorithm, known as LAORA, to address these inefficiencies. LAORA focuses on solving the problems of charging devices (RX) localization and location-based optimization. We begin by introducing the concept of Equivalent Impedance Distribution Image (EIDI) and transform the RX localization problem into a combined matching process involving EIDI. In addition, we establish a dynamic simulation framework to predict charging performance using RX-related knowledge, enabling us to obtain optimal TX orientations through reinforcement learning without needing to rotate on mechanical devices physically. We then implement the prototype and conduct extensive experiments. The results show that, compared to other existing orientation adjustment methods, LAORA achieves an average improvement of 186 % while reducing the mechanical rotations by 83.3 %.

Sign language is a natural and fully-formed communication method for deaf or hearing-impaired people. Unfortunately, most of the state-of-the-art sign recognition technologies are limited by either high energy consumption or expensive device costs and have a difficult time providing a real-time service in a daily-life environment. Inspired by previous works on motion detection with wearable devices, we propose Sign Speaker - a real-time, robust, and user-friendly American sign language recognition (ASLR) system with affordable and portable commodity mobile devices. SignSpeaker is deployed on a smartwatch along with a smartphone; the smartwatch collects the sign signals and the smartphone outputs translation through an inbuilt loudspeaker. We implement a prototype system and run a series of experiments that demonstrate the promising performance of our system. For example, the average translation time is approximately $1.1$ seconds for a sentence with eleven words. The average detection ratio and reliability of sign recognition are 99.2% and 99.5%, respectively. The average word error rate of continuous sentence recognition is 1.04% on average.

Finger gesture input is emerged as an increasingly popular means of human-computer interactions. In this paper, we propose iPand, an acoustic sensing system that enables finger gesture input on the skin, which is more convenient, user-friendly and always accessible. Unlike previous works, which implement gesture input with dedicated devices, our system exploits passive acoustic sensing to identify the gestures, e.g. swipe left, swipe right, pinch and spread. The insight of our system is that specific gesture emits unique friction sound, which can be captured by the microphone embedded in wearable devices. We capture these acoustic signals and extract the features by using bandpass filters and short-time Fourier Transform. The offline convolutional neural network is adopted to recognize the gestures. iPand is implemented and evaluated using COTS smartphones and smartwatches. Experiment results show that iPand can achieve the recognition accuracy of 89%, 83% and 78% in three daily scenarios (i.e., library, lab and cafe), respectively. Particularly, our system supports multi-touch function where 2-4 fingers are enabled for more efficient and expressive gesture input, and its average accuracy for individual finger gesture reaches up to 83% within 12 gestures.

Finger gesture input is emerged as an increasingly popular means of human-computer interactions. In this demo, we propose iPand, an acoustic sensing system that enables finger gesture input on the skin, which is more convenient, user-friendly and always accessible. Unlike past works, which implement gesture input with dedicated devices, our system exploits passive acoustic sensing to identify the gestures, e.g. swipe left, swipe right, pinch and spread. The intuition underlying our system is that specific gesture emits unique friction sound, which can be captured by the microphone embedded in wearable devices. We then adopt convolutional neural network to recognize the gestures. We implement and evaluate iPand using COTS smartphones and smartwatches. Results from three daily scenarios (i.e., library, lab and cafe) of 10 volunteers show that iPand can achieve the recognition accuracy of 87%, 81% and 77% respectively.