Explore the vast range of titles available.

A style transfer aims to produce synthesized images that retain the content of one image while adopting the artistic style of another. Traditional style transfer methods often require training separate transformation networks for each new style, limiting their adaptability and scalability. To address this challenge, we propose a flow-based image style transfer framework that integrates Randomized Hierarchy Flow (RH Flow) and a meta network for adaptive parameter generation. The meta network dynamically produces the RH Flow parameters conditioned on the style image, enabling efficient and flexible style adaptation without retraining for new styles. RH Flow enhances feature interaction by introducing a random permutation of the feature sub-blocks before hierarchical coupling, promoting diverse and expressive stylization while preserving the content structure. Our experimental results demonstrate that Meta FIST achieves superior content retention, style fidelity, and adaptability compared to existing approaches.

This paper introduces a novel unsupervised domain adaptation (UDA) method, MeTa Discriminative Class-Wise MMD (MCWMMD), which combines meta-learning with a Class-Wise Maximum Mean Discrepancy (MMD) approach to enhance domain adaptation. Traditional MMD methods align overall distributions but struggle with class-wise alignment, reducing feature distinguishability. MCWMMD incorporates a meta-module to dynamically learn a deep kernel for MMD, improving alignment accuracy and model adaptability. This meta-learning technique enhances the model’s ability to generalize across tasks by ensuring domain-invariant and class-discriminative feature representations. Despite the complexity of the method, including the need for meta-module training, it presents a significant advancement in UDA. Future work will explore scalability in diverse real-world scenarios and further optimize the meta-learning framework. MCWMMD offers a promising solution to the persistent challenge of domain adaptation, paving the way for more adaptable and generalizable deep learning models.

It is an interesting and challenging problem to synthesise vivid facial expression images. In this paper, we propose a facial expression synthesis system which imitates a reference facial expression image according to the difference between shape feature vectors of the neutral image and expression image. To improve the result, two stages of postprocessing are involved. We focus on the facial expressions of happiness, sadness, and surprise. Experimental results show vivid and flexible results.

Music representation with pitch interval and duration ratio can achieve invariance to transposition and tempo. However, altering the pitch or duration of a single music note will cause an antisymmetry effect. This paper proposes an algorithm for computing a geometric measure between two music fragments represented with pitch interval and duration ratio, with the capability of detecting and reducing these effects to improve search effectiveness. Index Terms-content-based music retrieval, geometric matching, pitch interval, duration ratio, antisymmetry effect

Batch normalization (BN) has become a foundational component in modern deep neural networks. However, one of its disadvantages is its reliance on batch statistics that may be unreliable or unavailable during inference, particularly under test-time domain shifts. While batch-statistics-free affine transformation methods alleviate this by learning per-sample scale and shift parameters, most treat samples independently, overlooking temporal or sequential correlations in streaming or episodic test-time settings. We propose LSTM-Affine, a memory-based normalization module that replaces BN with a recurrent parameter generator. By leveraging an LSTM, the module produces channel-wise affine parameters conditioned on both the current input and its historical context, enabling gradual adaptation to evolving feature distributions. Unlike conventional batch-statistics-free designs, LSTM-Affine captures dependencies across consecutive samples, improving stability and convergence in scenarios with gradual distribution shifts. Extensive experiments on few-shot learning and source-free domain adaptation benchmarks demonstrate that LSTM-Affine consistently outperforms BN and prior batch-statistics-free baselines, particularly when adaptation data are scarce or non-stationary.

For the subject of arbitrary image style transfer, there have been some proposed architectures that directly compute the transformation matrix of the whitening and coloring transformation (WCT) to obtain more satisfactory transformation results. However, calculating the transformation matrix of WCT is time-consuming. Li et al. trained a linear transformation module to generate a WCT transformation matrix for any pair of images, i.e., content image and style image, to avoid complex calculations and improves time efficiency. In this work, we introduce a flexible arbitrary image style transfer framework based on the LST, which uses deep neural networks to train a linear transformation matrix as the standard matrix for WCT. For the first part, inverse relationship between the Whitening matrix and the Coloring matrix w.r.t. the same image is enforced during the training of the linear transformation matrix, so that the resulting matrix will be more accurate and ​​closer to the standard matrix of WCT. For the second part, a split-and-transform scheme is proposed. Unlike LST, which transforms the block of feature maps as a whole, the split-and-transform scheme divides the feature block into several smaller blocks and transforms them individually, so that the transformation is more localized, and the more the number of divided blocks, the more localized. In addition, the proposed split-and-transform scheme allows users to determine the number of divided blocks to flexibly control the locality of the transformations. Experimental results demonstrate the effectiveness and flexibility of the proposed framework by the high-quality stylized images and adjustable balance between globality and locality of transformations. The use of the split-and-transform scheme can reduce the computational time while preserving or even improving the stylization results.

In this study, we would like to improve the existing seam carving methods by using an more appropriate edge map and with the aid of Hough transform to select more appropriate seams for removal. This would allow seam carving to adapt to a variety of environments, providing desired results for users.

A flexible video colorization system is proposed that propagates color from one frame to its adjacent frames based on acquiring color from neighboring pixels, color interpolation, connected component analysis, and post processing to accomplish the work of video colorization. Users can obtain a preliminary result by setting some proper thresholds, and then get a finer result in the post processing stage. The experimental results show that our approach can provide satisfactory colorization results.

Both the annotation and identification of genes in pathogenic parasites are still challenging. Although, as a survival factor, nitric oxide (NO) has been proven to be synthesized in Trichomonas vaginalis (TV), nitric oxide synthase (NOS) has not yet been annotated in the TV genome. We developed a witness-to-suspect strategy to identify incorrectly annotated genes in TV via the Smith–Waterman and Needleman–Wunsch algorithms through in-depth and repeated alignment of whole coding sequences of TV against thousands of sequences of known proteins from other organisms. A novel NOS of TV (TV NOS), which was annotated as hydrogenase in the NCBI database, was successfully identified; this TV NOS had a high witness-to-suspect ratio and contained all the NOS cofactor-binding motifs (NADPH, tetrahydrobiopterin (BH4), heme and flavin adenine dinucleotide (FAD) motifs). To confirm this identification, we performed in silico modeling of the protein structure and cofactor docking, cloned the gene, expressed and purified the protein, performed mass spectrometry analysis, and ultimately performed an assay to measure enzymatic activity. Our data showed that although the predicted structure of the TV NOS protein was not similar to the structure of NOSs of other species, all cofactor-binding motifs could interact with their ligands with high affinities. We clearly showed that the purified protein had high enzymatic activity for generating NO in vitro. This study provides an innovative approach to identify incorrectly annotated genes in TV and highlights a novel NOS that might serve as a virulence factor of TV.