Salient object detection of surface defects is one of the surface defect detection tasks, which aims at highlighting the defect regions from the surface of strip steel, magnetic tale, road, and so on. However, the performance of existing methods degrades dramatically when dealing with complex scenarios, such as low contrast of defect regions and various defect shapes. Therefore, in this article, we propose a novel saliency model, namely, localizing, focus, and refinement network (LFRNet), which consists of the semantic-guided localizing module, the context-driven focus module, and the edge-aware refinement (ER) module. First, the semantic-guided localizing module deploys the graph reasoning (GR) unit and the global attention (GA) unit to localize the potential defect regions from a global view. Second, the context-driven focus module employs the split context (SC) unit and the mutual attention (MA) unit to perform the identification process via the introduction of spatial detail features. Finally, to further improve the accuracy of the detection results, we deploy the ER module, which introduces the boundary cues via the edge generation (EG) unit and aggregates the localizing result, the focus results, and the edge information into the high-quality detection map. Extensive experiments on four public defect datasets clearly show the effectiveness and superiority of the proposed LFRNet, where the LFRNet obtains an improvement of 4.1%, 5.7%, 1.0%, and 0.8% on F-measure (FM), weighted FM (WF), E-measure (EM), and structure-measure (SM), respectively, compared with the top-level method: AEP.

The human visual system (HVS) is a hierarchical system, in which visual signals are processed hierarchically. In this paper, the HVS is modeled as a three-level communication system and visual perception is divided into three stages according to the hierarchical predictive coding theory. Then, a novel just noticeable distortion (JND) estimation scheme is proposed. In visual perception, the input signals are predicted constantly and spontaneously in each hierarchy, and neural response is evoked by the central residue and inhibited by surrounding residues. These two types’ residues are regarded as the positive and negative visual incentives which cause positive and negative perception effects, respectively. In neuroscience, the effect of incentive on observer is measured by the surprise of this incentive. Thus, we propose a surprise-based measurement method to measure both perception effects. Specifically, considering the biased competition of visual attention, we define the product of the residue self-information (i.e., surprise) and the competition biases as the perceptual surprise to measure the positive perception effect. As for the negative perception effect, it is measured by the average surprise (i.e., the local Shannon entropy). The JND threshold of each stage is estimated individually by considering both perception effects. The total JND threshold is finally obtained by non-linear superposition of three stage thresholds. Furthermore, the proposed JND estimation scheme is incorporated into the codec of Versatile Video Coding for image compression. Experimental results show that the proposed JND model outperforms the relevant existing ones, and over 16% of bit rate can be reduced without jeopardizing the perceptual quality.

Due to the limited storage capacity and network bandwidth, an efficient rate control (RC) algorithm becomes more and more critical for multi-view video coding (MVC). Based on inter-view dependency and spatio-temporal correlation, a novel bit allocation method for multi-view texture video coding is proposed in this article. Firstly, considering that the distortion in the base view (BV) is directly transmitted to the dependent view (DV) by inter-view skip mode, a joint multi-view RD model is built based on the inter-view dependency. Based on the proposed joint multi-view RD model, a precise power model is derived to represent the target bitrates relationship between the BV and the DV. Secondly, since the P frame in the DV (P-DV) is mainly predicted from the corresponding I frame in the BV (I-BV) by disparity compensated prediction (DCP), the constant proportional relationship between the ratio of the average bitrates of the P-DV to the corresponding I-BV and the ratio of the total bitrates of the DV to the BV is discovered. Based on this discovery, a novel linear model is developed to assign the target bitrates of the P-DV. Finally, considering the spatio-temporal correlation, a new parameter prediction method is proposed for the R-$\lambda $ model in coding tree unit (CTU) level. Extensive experimental results show that the proposed overall method outperforms other state-of-the-art algorithms in terms of RD performance.

Change captioning aims to describe the differences between two similar images using natural language, significantly aiding in understanding and monitoring changes. This challenging task requires a fine-grained understanding of subtle changes while resisting disturbances like viewpoint shifts and illumination variations. Existing methods often rely solely on global difference features and lack comprehensive alignment of linguistic and visual information, leading to overlooking fine-grained details and generating semantic hallucinated sentences. To address these limitations, we propose the region-aware difference distilling (RDD) network with attribute-guided contrastive regularization (ACR). The RDD uses global difference features to progressively distill regional difference features using learnable vectors, allowing for more precise identification of changed regions. The ACR enhances comprehensive alignment between linguistic and visual information by formulating Nouns-to-Objects (N2O) and Verbs-to-Actions (V2A) alignment losses to regularize the regional difference features. Promising results on three datasets demonstrate that our method outperforms the state-of-the-art change captioning methods.