The purpose of the image quality assessment is to evaluate image quality consistently with human’s subjective evaluation. In image quality assessment, many structural features have been used to measure the quality degradation of an image. However, most of the existing image quality assessment methods are block-based, which ignores the features among neighboring blocks. In this paper, we argue that the human visual system perceives distortions not only depends on local structural (intra-block structure) distortions, but also relates to the structural distortions of their neighborhoods (inter-block texture). Based on this insight, we propose a novel image quality assessment method, called the diffusion speed structure similarity (DSSIM), by considering both intra-block structure and inter-block texture. Specifically, to characterize the inter-block texture, we devise a novel visual feature based on the image diffusion speed. To measure the changes of the intra-block structure, we adopt the image gradient magnitude. Furthermore, to differentiate the importance of a local region, we devise a weighting function based on the image diffusion speed. Extensive experimental results on six benchmark databases demonstrate that our proposed method yields a better performance than the state-of-the-art methods.

The alignment of Image Quality Assessment (IQA) models with diverse human preferences remains a challenge, owing to the variability in preferences for different types of visual content, including user-generated content and AI-Generated Content (AIGC), etc. Despite the significant success of existing IQA methods in assessing specific visual content by leveraging knowledge from pre-trained models, the intricate factors impacting final ratings and the specially designed network architecture of these methods result in gaps in their ability to accurately capture human preferences for novel visual content. To address this issue, we propose Align-IQA, a novel framework that aims to generate visual quality scores aligned with diverse human preferences for various types of visual content. Align-IQA contains two key designs: (1) A customizable quality-aware guidance injection module. By injecting specializable quality-aware prior knowledge into general-purpose pre-trained models, the proposed module guides the acquisition of quality-aware features and allows for various adjustments of features to be consistent with diverse human preferences for different types of visual content. (2) A multi-scale feature aggregation module. By simulating the multi-scale mechanism in the human visual system, the proposed module enables the extraction of a more comprehensive representation of quality-aware features from the human perception perspective. Extensive experimental results demonstrate that Align-IQA achieves better or comparable performance to State-Of-The-Art (SOTA) methods. Notably, Align-IQA outperforms the previous best results on AIGC datasets, achieving Pearson's Linear Correlation Coefficients (PLCCs) of 0.890 (+3.73%) on AGIQA-1K and 0.924 (+1.99%) on AGIQA-3K. Additionally, Align-IQA reduces training parameters by 72.26% and inference overhead by 78.12%, while maintaining SOTA performance.

The huge benefit of mobile application industry has attracted a large number of developers and attendant attackers. Application repackaging provides help for the distribution of most Android malware. It is a serious threat to the entire Android ecosystem, as it not only compromises the security and privacy of the app users but also plunders app developers’ income. Although massive approaches have been proposed to address this issue, plagiarists try to fight back through packing their malicious code with the help of commercial packers. Previous works either do not consider the packing issue or rely on time-consuming computations, which are not scalable for large-scale real-world scenario. In this paper, we propose FUIDroid, a novel two-phase app clones detection system that can detect the packed cloned app. FUIDroid includes a function-based fast selection phase to quickly select suspicious apps by analyzing apps’ description and a further UI-based accurate detection phase to refine the detection result. We evaluate our system on two sets of apps. The result from experiment on 320 packed samples demonstrates that FUIDroid is resilient to packed apps. The evaluation on more than 150,000 real-world apps shows the efficiency of FUIDroid in large-scale scenario.

With the increasing wide applications of wearable wireless networks, body-to-body networks (BBNs) have become significantly important to provide timely and reliable data delivery services. For a specific BBN, assessing its theoretically achievable Quality of Service (QoS) is necessary, especially on the key performance metrics of end-to-end delay distribution and packet loss ratio. The existing analysis models in the literature mainly focused on 1-D space scenarios. In this article, BBN in a 2-D area is considered, where mobile nodes freely and stochastically move along lanes. By introducing two new definitions: 1) node entrance probability and 2) network entrance probability, a systematically analytical framework for end-to-end delay distribution and packet loss ratio is presented. The proposed analytical framework is built on three critical techniques: 1) the Markov chain to model node behaviors; 2) the first passage theory to calculate node entrance probability and network entrance probability; and 3) the central limit theory to decrease the computation time for summing up per-hop delay. Simulation results demonstrate the effectiveness and accuracy of our proposed analysis model.