Jiarun Song

Jiarun Song, Ninghao Wan, Fuzheng Yang et al.

Remote Collaborative Augmented Reality (RCAR) enables geographically distributed users to collaborate by integrating virtual and physical environments. However, because RCAR relies on real-time transmission, it is susceptible to delay and stalling impairments under constrained network conditions. Perceptual interaction fluency (PIF), defined as the perceived pace and responsiveness of collaboration, is influenced not only by physical network impairments but also by intrinsic task characteristics. These characteristics can be interpreted as the task-specific just-noticeable difference (JND), i.e., the maximal tolerable temporal responsiveness before PIF degrades. When the average response time (ART), measured as the mean time per operation from receiving collaborator feedback to initiating the next action, falls within the JND, PIF is generally sustained, whereas values exceeding it indicate disruption. Tasks differ in their JNDs, reflecting distinct temporal responsiveness demands and sensitivities to impairments. From the perspective of the Free Energy Principle (FEP), tasks with lower JNDs impose stricter temporal prediction demands, making PIF more vulnerable to impairments, whereas higher JNDs allow greater tolerance. On this basis, we classify RCAR tasks by JND and evaluate their PIF through controlled subjective experiments under delay, stalling, and hybrid conditions. Building on these findings, we propose the Task-Aware Perceptual Interaction Fluency Model (TPIFM). Experimental results show that TPIFM accurately assesses PIF under network impairments, providing guidance for adaptive RCAR design and user experience optimization under network constraints.

Jiarun Song, Ninghao Wan, FuZheng Yang et al.

Virtual reality (VR) conferencing has the potential to provide geographically dispersed users with an immersive environment, enabling rich social interactions and user experience using avatars. However, remote communication in VR inevitably introduces end-to-end (E2E) latency, which can significantly impact user experience. To clarify the impact of latency, we conducted subjective experiments to analyze how it influences interaction fluency from the perspective of quality perception and social presence from the perspective of social cognition, comparing VR conferencing with traditional video conferencing (VC). Specifically, interaction fluency emphasizes user perception of interaction pace and responsiveness and is assessed using Absolute Category Rating (ACR) method. In contrast, social presence focuses on the cognitive understanding of interaction, specifically whether individuals can comprehend the intentions, emotions, and behaviors expressed by others. It is primarily measured using the Networked Minds Social Presence Inventory (NMSPI). Building on this analysis, we further investigate the relationship between interaction fluency and social presence under different latency conditions to clarify the underlying perceptual and cognitive mechanisms. The findings from these subjective tests provide meaningful insights for optimizing the related systems, helping to improve interaction fluency and enhancing social presence in immersive virtual environments.

Ninghao Wan, Jiarun Song, Fuzheng Yang

In virtual reality (VR) educational scenarios, Pedagogical agents (PAs) enhance immersive learning through realistic appearances and interactive behaviors. However, most existing PAs rely on static speech and simple gestures. This limitation reduces their ability to dynamically adapt to the semantic context of instructional content. As a result, interactions often lack naturalness and effectiveness in the teaching process. To address this challenge, this study proposes a large language model (LLM)-driven multimodal expression generation method that constructs semantically sensitive prompts to generate coordinated speech and gesture instructions, enabling dynamic alignment between instructional semantics and multimodal expressive behaviors. A VR-based PA prototype was developed and evaluated through user experience-oriented subjective experiments. Results indicate that dynamically generated multimodal expressions significantly enhance learners' perceived learning effectiveness, engagement, and intention to use, while effectively alleviating feelings of fatigue and boredom during the learning process. Furthermore, the combined dynamic expression of speech and gestures notably enhances learners' perceptions of human-likeness and social presence. The findings provide new insights and design guidelines for building more immersive and naturally expressive intelligent PAs.

Jiarun Song, Yongkang Hou, Fuzheng Yang

Networked virtual reality (NVR) whiteboards are increasingly important for enabling geographically dispersed users to engage in real-time idea sharing, collaborative design, and discussion. However, latency caused by network limitations, rendering delays, or synchronization issues can significantly degrade the Quality of Experience (QoE) in whiteboard collaboration. To systematically investigate the impact of latency, this study classified QoE into pragmatic and hedonic aspects, each comprising multiple sub-dimensions. Controlled experiments were conducted to identify the sub-dimensions most affected by latency, which were then adopted as the primary QoE indicators, with the aim of uncovering the processes and mechanisms through which latency shapes QoE. Building on this, we further examined how these impacts vary across different collaboration modes, namely sequential collaboration (SC) for structured design workflows and free collaboration (FC) for open discussion. We also compared two VR whiteboard types, one with avatars (VR+) and the other without avatars (VR), and included a traditional PC-based whiteboard as a baseline. This multi-dimensional design enables a comprehensive evaluation of latency's impact on QoE across collaboration modes and platforms, providing practical guidance for optimizing NVR whiteboard systems under real-world network and system constraints.

Linghe Meng, Jiarun Song

The quality assessment of AI-generated content (AIGC) faces multi-dimensional challenges, that span from low-level visual perception to high-level semantic understanding. Existing methods generally rely on single-level visual features, limiting their ability to capture complex distortions in AIGC images. To address this limitation, a multi-level visual representation paradigm is proposed with three stages, namely multi-level feature extraction, hierarchical fusion, and joint aggregation. Based on this paradigm, two networks are developed. Specifically, the Multi-Level Global-Local Fusion Network (MGLF-Net) is designed for the perceptual quality assessment, extracting complementary local and global features via dual CNN and Transformer visual backbones. The Multi-Level Prompt-Embedded Fusion Network (MPEF-Net) targets Text-to-Image correspondence by embedding prompt semantics into the visual feature fusion process at each feature level. The fused multi-level features are then aggregated for final evaluation. Experiments on benchmarks demonstrate outstanding performance on both tasks, validating the effectiveness of the proposed multi-level visual assessment paradigm.

Yongkang Hou, Jiarun Song

Image Quality Assessment (IQA) is a core task in computer vision. Multimodal methods based on vision-language models, such as CLIP, have demonstrated exceptional generalization capabilities in IQA tasks. To address the issues of excessive parameter burden and insufficient ability to identify local distorted features in CLIP for IQA, this study proposes a visual-language model knowledge distillation method aimed at guiding the training of models with architectural advantages using CLIP's IQA knowledge. First, quality-graded prompt templates were designed to guide CLIP to output quality scores. Then, CLIP is fine-tuned to enhance its capabilities in IQA tasks. Finally, a modality-adaptive knowledge distillation strategy is proposed to achieve guidance from the CLIP teacher model to the student model. Our experiments were conducted on multiple IQA datasets, and the results show that the proposed method significantly reduces model complexity while outperforming existing IQA methods, demonstrating strong potential for practical deployment.