Jia Chen

Jingtao Zhan, Qingyao Ai, Yiqun Liu et al. · tsinghua

Text-to-image generation systems have emerged as revolutionary tools in the realm of artistic creation, offering unprecedented ease in transforming textual prompts into visual art. However, the efficacy of these systems is intricately linked to the quality of user-provided prompts, which often poses a challenge to users unfamiliar with prompt crafting. This paper addresses this challenge by leveraging user reformulation data from interaction logs to develop an automatic prompt reformulation model. Our in-depth analysis of these logs reveals that user prompt reformulation is heavily dependent on the individual user's capability, resulting in significant variance in the quality of reformulation pairs. To effectively use this data for training, we introduce the Capability-aware Prompt Reformulation (CAPR) framework. CAPR innovatively integrates user capability into the reformulation process through two key components: the Conditional Reformulation Model (CRM) and Configurable Capability Features (CCF). CRM reformulates prompts according to a specified user capability, as represented by CCF. The CCF, in turn, offers the flexibility to tune and guide the CRM's behavior. This enables CAPR to effectively learn diverse reformulation strategies across various user capacities and to simulate high-capability user reformulation during inference. Extensive experiments on standard text-to-image generation benchmarks showcase CAPR's superior performance over existing baselines and its remarkable robustness on unseen systems. Furthermore, comprehensive analyses validate the effectiveness of different components. CAPR can facilitate user-friendly interaction with text-to-image systems and make advanced artistic creation more achievable for a broader range of users.

Jia Wei Chen

We present a comprehensive video-based analytics framework for tennis doubles that addresses the lack of automated analysis tools for this strategically complex sport. Our approach introduces a standardised annotation methodology encompassing player positioning, shot types, court formations, and match outcomes, coupled with a specialised annotation tool designed to meet the unique requirements of tennis video labelling. The framework integrates advanced machine learning techniques including GroundingDINO for precise player localisation through natural language grounding and YOLO-Pose for robust pose estimation. This combination significantly reduces manual annotation effort whilst improving data consistency and quality. We evaluate our approach on doubles tennis match data and demonstrate that CNN-based models with transfer learning substantially outperform pose-based methods for predicting shot types, player positioning, and formations. The CNN models effectively capture complex visual and contextual features essential for doubles tennis analysis. Our integrated system bridges advanced analytical capabilities with the strategic complexities of tennis doubles, providing a foundation for automated tactical analysis, performance evaluation, and strategic modelling in professional tennis.

Zhengqin Yang, Di Wu, Jia Chen et al.

Concept Factorization (CF) models have attracted widespread attention due to their excellent performance in data clustering. In recent years, many variant models based on CF have achieved great success in clustering by taking into account the internal geometric manifold structure of the dataset and using graph regularization techniques. However, their clustering performance depends greatly on the construction of the initial graph structure. In order to enable adaptive learning of the graph structure of the data, we propose a Concept Factorization Based on Self-Representation and Adaptive Graph Structure Learning (CFSRAG) Model. CFSRAG learns the affinity relationship between data through a self-representation method, and uses the learned affinity matrix to implement dynamic graph regularization constraints, thereby ensuring dynamic learning of the internal geometric structure of the data. Finally, we give the CFSRAG update rule and convergence analysis, and conduct comparative experiments on four real datasets. The results show that our model outperforms other state-of-the-art models.

Weize Yu, Jia Chen

In this letter, a physical unclonable function (PUF)-advanced encryption standard (AES)-PUF is proposed as a new PUF architecture by embedding an AES cryptographic circuit between two conventional PUF circuits to conceal their challenge-to-response pairs (CRPs) against machine learning attacks. Moreover, an internal confidential data is added to the secret key of the AES cryptographic circuit in the new PUF architecture to update the secret key in real-time against side-channel attacks. As shown in the results, even if 1 million number of data are enabled by the adversary to implement machine learning or side-channel attacks, the proposed PUF can not be cracked. By contrast, only 5,000 (1,000) number of data are sufficient to leak the confidential information of a conventional PUF via machine learning (side-channel) attacks.