17 accepted papers
Unsupervised domain adaptive pose estimation is a fundamental yet challenging task due to the need to transfer from labeled synthetic data to unlabeled real data. Nevertheless, the underlying pose semantics, which are governed by spatial structure, remain largely consistent across domains. This obse
Unsupervised domain adaptation (UDA) for pose estimation promises transfer from synthetic to real domains but often suffers instability under domain shift. Prior work attributes this deterioration to gradient interference between source supervision and target consistency. This conflict is distinct i
The limited capacity for fine-grained visual perception presents a critical bottleneck for Vision-Language Models (VLMs) in real-world applications. Addressing this is challenging due to the scarcity of high-quality data and the limitations of existing methods: supervised fine-tuning (SFT) often com…
Evaluating and iterating upon recommender systems is crucial, yet traditional A/B testing is resource-intensive, and offline methods struggle with dynamic user-platform interactions. While agent-based simulation is promising, existing platforms often lack a mechanism for user actions to dynamically
The Kalman filter has been adopted in acoustic echo cancellation due to its robustness to double-talk, fast convergence, and good steady-state performance. The performance of Kalman filter is closely related to the estimation accuracy of the state noise covariance and the observation noise covarianc…
Each student matters, but it is hardly for instructors to observe all the students during the courses and provide helps to the needed ones immediately. In this paper, we present StuArt, a novel automatic system designed for the individualized classroom observation, which empowers instructors to conc…
Graph similarity learning refers to calculating the similarity score between two graphs, which is required in many realistic applications, such as visual tracking, graph classification, and collaborative filtering. As most of the existing graph neural networks yield effective graph representations o…
Snapshot Compressive Imaging (SCI) systems, including hyperspectral compressive imaging and video compressive imaging, are designed to depict high-dimensional signals with limited data by mapping multiple images into one. One key module of SCI systems is a high quality reconstruction algorithm for o…
Students’ gestures, hand-raising, stand-up, and sleeping, indicates the engagement of students in classrooms and partially reflects teaching quality. Therefore, fast and automatically recognizing these gestures are of great importance. Due to limited computational resources in primary and secondary…
In this paper, we design an intelligent student behavior analysis system for recorded classrooms, which automatically detects hand-raising, standing, and sleeping behaviors of students. Detecting these behaviors is quite challenging mainly due to various scale behaviors, low resolution, and imbalanc…
In this paper, we focus on dealing with problems of large-pose face alignment. Recently proposed heatmap-based algorithms have made promising performance on this problem. However, the traditional heatmap is constructed based on Gaussian model with fixed variance, which is inconsistent with the local…
Most existing methods for person re-identification (re-id) only utilize last layer features of deep convolution neural networks (CNNs), which may lose the useful lower level information and decreases the performance. To alleviate this problem, we propose a novel multi-level feature learning framewor…
This paper proposes a novel method to detect sleep persons in real classroom scenes, which is useful for detecting the attention of students. There are several challenges for sleep gesture detection, including occlusion, various sleep gestures, interference terms with similar features like writing,…
In this paper, we propose a novel low-rank tensor completion (LRTC) model under the circulant algebra for color image inpainting, which simultaneously preserves the low-rank structures of images, and also explore the local smooth and piecewise priors of the images in the spatial domain. First, color…
Based on non-local prior distributions, we propose a Bayesian model selection (BMS) procedure for boundary detection in a sequence of data with multiple systematic mean changes. The BMS method can effectively suppress the non-boundary spike points with large instantaneous changes. We speed up the al…
This paper proposes a novel method for hand-raising detection in the real classroom environment. Different from traditional motion detection, the hand-raising detection is quite challenging in the real classroom due to complex scenarios, various gestures, and low resolutions. To solve these challeng…
Many small insects such as water striders can leap from water surface. Inspired by their jumping capability, we present the design of a novel, miniature, water surface jumping robot in this paper. Jumping from water surface is more challenging than jumping from ground due to the liquid water surface