Semantic segmentation is a fundamental task in multimedia processing, which can be used for analyzing, understanding, editing contents of images and videos, among others. To accelerate the analysis of multimedia data, existing segmentation researches tend to extract semantic information by progressively reducing the spatial resolutions of feature maps. However, this approach introduces a misalignment problem when restoring the resolution of high-level feature maps. In this paper, we design a Semantic Refinement Module (SRM) to address this issue within the segmentation network. Specifically, SRM is designed to learn a transformation offset for each pixel in the upsampled feature maps, guided by high-resolution feature maps and neighboring offsets. By applying these offsets to the upsampled feature maps, SRM enhances the semantic representation of the segmentation network, particularly for pixels around object boundaries. Furthermore, a Contextual Refinement Module (CRM) is presented to capture global context information across both spatial and channel dimensions. To balance dimensions between channel and space, we aggregate the semantic maps from all four stages of the backbone to enrich channel context information. The efficacy of these proposed modules is validated on three widely used datasets-Cityscapes, Bdd100K, and ADE20K-demonstrating superior performance compared to state-of-the-art methods. Additionally, this paper extends these modules to a lightweight segmentation network, achieving an mIoU of 82.5% on the Cityscapes validation set with only 137.9 GFLOPs.

Semi-supervised learning (SSL) utilizes limited labeled data and plenty of unlabeled data, and it has attracted attentions for its improved learning performance. However, recent studies have indicated that using unlabeled data, in some cases, could deteriorate the performance. Therefore, there’s an imminent need to develop safe semi-supervised learning methods to determine whether SSL should be applied for a given scenario. This paper proposes a safe version of multi-class graph-based semi-supervised support vector machine (SVM). At first, in order to eliminate the impact of bad label assignments, a criterion based on the cost function of semi-supervised SVM (S3VM) is introduced to evaluate the predicted label assignments. Then, m candidate optimal label assignments are picked up by the criterion. After that, a multi-class safe strategy is designed to generate the final label assignment whose performance is never worse than that of the methods using only labeled samples. Experimental results on several benchmark datasets validate the effectiveness of the proposed technique.

Local feature descriptor learning aims to represent distinctive images or patches with the same local features, where their representation is invariant under different types of deformation. Recent studies have demonstrated that descriptor learning based on Convolutional Neural Network (CNN) is able to improve the matching performance significantly. However, they tend to ignore the importance of sample selection during the training process, leading to unstable quality of descriptors and learning efficiency. In this paper, a dual hard batch construction method is proposed to sample the hard matching and non-matching examples for training, improving the performance of the descriptor learning on different tasks. To construct the dual hard training batches, the matching examples with the minimum similarity are selected as the hard positive pairs. For each positive pair, the most similar non-matching example is then sampled from the generated hard positive pairs in the same batch as the corresponding negative. By sampling the hard positive pairs and the corresponding hard negatives, the hard batches are produced to force the CNN model to learn the descriptors with more efforts. In addition, based on the above dual hard batch construction, an ℓ22 triplet loss function is built for optimizing the training model. Specifically, we analyze the superiority of the ℓ22 loss function when dealing with hard examples, and also demonstrate it in the experiments. With the benefits of the proposed sampling strategy and the ℓ22 triplet loss function, our method achieves better performance compared to state-of-the-art on the reference benchmarks for different matching tasks.

Many sewage treatment facilities in China have been developed and operated using the Public-Private Partnerships (PPP) model. However, a big challenge faced by these PPP projects is that the subsidy requested from the government during the operation is normally higher than what was estimated originally, thus often exceeding the budget that the government can afford. This leads to a high risk of project failure or insufficient operation. This problem is largely caused by the uncertainties exhibited in the existing models, such as the Black-Scholes (BS) model. While being used in the budget estimation, these models cannot sufficiently account for the short-term uncertainty that may be incurred during the operation of projects. In this study, a method to account for this short-term uncertainty has been proposed to improve the BS model. This allows for investigations to address issues related to how the real option value of a government subsidy is affected. A Monte Carlo simulation was performed to take into account the noise in the estimation. A sensitivity analysis further revealed that this discrepancy is largely affected by the values of the relevant parameters in the short-term uncertainty model. We found that the short-term uncertainty has a significant effect on private revenue and government subsidy and that the changes of the latter are more sensitive to the change of short-term uncertainty. The value of the relevant variables of short-term uncertainty determined the fluctuation of the revenue. The mean value and revenue had a positive correlation. The reverting speed and revenue showed a negative correlation. The short-term volatility had a positive correlation toward the fluctuation range of the revenue. The simulation results indicate that this enhanced method can produce more accurate information for a better assessment of the PPP project under a wide range of uncertainty scenarios, allowing for the best decision making by the government.

An efficient and accurate point matching algorithm named advanced weight graph transformation matching (AWGTM) is proposed in this study. Instead of relying only on the elimination of dubious matches, the method iteratively reserve correspondences which have a small angular distance between two nearest‐neighbour graphs. The proposed algorithm is compared against weight graph transformation matching (WGTM) and graph transformation matching (GTM). Experimental results demonstrate the superior performance in eliminating outliers and reserving inliers of AWGTM algorithm under various conditions for images, such as duplication of patterns and non‐rigid deformation of objects. An execution time comparison is also presented, where AWGTM shows the best results for high outlier rates.