The generation of attractive sentences for consumers is an important issue. In this paper, we propose a new method to generate title sentences that are more popular on YouTube, which is gaining large ...popularity in recent years. In the proposed method, the automatic generation of titles is regarded as a sentence style transfer task; The title sentence generated by the video creator is transformed into a more attractive one. Specifically, first, the latent variable is obtained by the back translation method. In the back translation method, it translates the original title into another language and retranslates it into Japanese. Then, style transfer is performed based on this latent variable to generate a more attractive title sentence. In addition, transfer learning is employed to address the problem of scarce training data. Subjective evaluation experiments have been conducted to show the effectiveness of the proposed method.
Recent work within neuroimaging consortia have aimed to identify reproducible, and often subtle, brain signatures of psychiatric or neurological conditions. To allow for high‐powered brain imaging ...analyses, it is often necessary to pool MR images that were acquired with different protocols across multiple scanners. Current retrospective harmonization techniques have shown promise in removing site‐related image variation. However, most statistical approaches may over‐correct for technical, scanning‐related, variation as they cannot distinguish between confounded image‐acquisition based variability and site‐related population variability. Such statistical methods often require that datasets contain subjects or patient groups with similar clinical or demographic information to isolate the acquisition‐based variability. To overcome this limitation, we consider site‐related magnetic resonance (MR) imaging harmonization as a style transfer problem rather than a domain transfer problem. Using a fully unsupervised deep‐learning framework based on a generative adversarial network (GAN), we show that MR images can be harmonized by inserting the style information encoded from a single reference image, without knowing their site/scanner labels a priori. We trained our model using data from five large‐scale multisite datasets with varied demographics. Results demonstrated that our style‐encoding model can harmonize MR images, and match intensity profiles, without relying on traveling subjects. This model also avoids the need to control for clinical, diagnostic, or demographic information. We highlight the effectiveness of our method for clinical research by comparing extracted cortical and subcortical features, brain‐age estimates, and case–control effect sizes before and after the harmonization. We showed that our harmonization removed the site‐related variances, while preserving the anatomical information and clinical meaningful patterns. We further demonstrated that with a diverse training set, our method successfully harmonized MR images collected from unseen scanners and protocols, suggesting a promising tool for ongoing collaborative studies. Source code is released in USC‐IGC/style_transfer_harmonization (github.com).
We develop a novel harmonization approach for T1‐weighted magnetic resonance imaging using a style‐encoding generative adversarial network that can be used to harmonize entire images for a variety of international, multi‐cohort, neuroimaging collaborations. Results demonstrated that this model avoids the need to control for clinical or demographic information. We showed that our harmonization removed the cross‐site variances, while preserving the anatomical information and clinical meaningful patterns.
With the continuous improvement of the level of science and technology, the design method of cloud brocade pattern has gradually changed from the traditional process of color halo, white, and gold ...stranding to the modern design process, such as the synthesis of cloud brocade line pattern based on the transfer of image style. But back to reality, this method still has problems such as blurred outline and mixed colors, which is not conducive to the transfer of cloud brocade style pictures. Based on this, the paper will use the cloud brocade pattern style transfer color optimization model to analyze the color of the cloud brocade pattern in order to get a better cloud brocade style effect map. The results show that the average similarity of the local migration algorithm is 0.348, while the average similarity of the local migration algorithm based on color optimization is 0.378, which is 8.62% higher than that of the local migration algorithm. After 1600 iterations, the average running time of the local migration algorithm is 13.65s, and the running time of the local migration algorithm for color optimization is 12.46s. It can be seen that the local migration algorithm based on color optimization has obvious advantages in both comprehensive similarity and running time and can provide new ideas and references for the current design of Yunjin pictures. Doi: 10.28991/HIJ-2023-04-04-07 Full Text: PDF
Neural Style Transfer (NST) has been a widely researched topic as of late enabling new forms of image manipulation. Here we perform an extensive study on NST algorithms and extend the existing ...methods with custom modifications for application to Indian art styles. In this paper, we aim to provide a comprehensive analysis of various methods ranging from the seminal work of Gatys et al which demonstrated the power of Convolutional Neural Networks (CNNs) in creating artistic imagery by separating and recombining image content and style, to the state of the art image-to-image translation models which use Generative Adversarial Networks (GANs) to learn the mapping between two domain of images. We observe and infer based on the results produced by the models on which one could be a more suitable approach for Indian art styles, especially Tanjore paintings which are unique compared to the Western art styles. We then propose the method which is more suitable for the domain of Indian Art style along with custom architecture which includes an enhancement and evaluation module. We then present evaluation methods, both qualitative and quantitative which includes our proposed metric, to evaluate the results produced by the model.
Current construction object detection models are vulnerable in complex conditions, as they are trained on conventional data and lack robustness in extreme situations. The lack of extreme data with ...relevant annotations worsens this situation. A new end-to-end unified image adaptation You-Only-Look-Once-v5 (UIA-YOLOv5) model is presented for robust object detection in five extreme conditions: low/intense light, fog, dust, and rain. The UIA-YOLOv5 adaptively enhances the input image to make image content visually clear and then feeds the enhanced image to the YOLOv5 for object detection. Sufficient extreme images are synthesized via the neural style transfer (NST) and mixed with conventional data for model training to reduce domain shift. An extreme construction dataset (ExtCon) containing 506 images labeled with 13 objects is constructed for real-world evaluation. Results show that the UIA-YOLOv5 keeps the same performance as the YOLOv5 on conventional data but is more robust to extreme data with an 8.21% mAP05 improvement.
•UIA-YOLOv5 is presented for robust object detection in extreme conditions.•It is validated in low/intense light, fog, dust, and rain.•An extreme condition test set (ExtCon) with 506 images is created and released.•Using a shallow network enhances accuracy and inference speed.•UIA-YOLOv5 achieves an 8.21% mAP05 improvement on the ExtCon set.
Real-world paintings are made, by artists, using brush strokes as the rendering primitive to depict semantic content. The bulk of the Neural Style Transfer (NST) is known transferring style using ...texture patches, not strokes. The output looks like the content image, but some are traced over using the style texture: it does not look painterly. We adopt a very different approach that uses strokes. Our contribution is to analyse paintings to learn stroke families -that is, distributions of strokes based on their shape (a dot, straight lines, curved arcs, etc. ). When synthesising a new output, these distributions are sampled to ensure the output is painted with the correct style of stroke. Consequently, our output looks more "painterly" than NST output based on texture. Furthermore, where strokes are placed is an important contributing factor in determining output quality, and we have also addressed this aspect. Humans place strokes to emphasize salient semantically meaningful image content. Conventional NST uses a content loss premised on filter responses that is agnostic to salience. We show that replacing that loss with one based on the language-image model benefits the output through greater emphasis of salient content.
Dynamic artistic text style transfer aims to migrate the style in terms of both the appearance and motion patterns from a reference style video to the target text to create artistic text animation. ...Recent researches have improved the usability of transfer models by introducing texture control. However, it remains an important open challenge to investigate the control of the stylistic degree with respect to shape deformation. In this paper, we explore a new problem of dynamic artistic text style transfer with glyph stylistic degree control. The key idea is to build multi-scale glyph-style shape mappings through a novel bidirectional shape matching framework. Following this idea, we first introduce a scale-ware Shape-Matching GAN to learn such mappings to simultaneously model the style shape features at multiple scales and transfer them onto the target glyph. Furthermore, an advanced Shape-Matching GAN++ is proposed to animate a static text image based on the reference style video. Our Shape-Matching GAN++ characterizes the short-term consistency of motion patterns via shape matchings within consecutive frames, which are propagated to achieve effective long-term consistency. Experiments show that the proposed method outperforms previous state-of-the-arts both qualitatively and quantitatively, and generate high-quality and controllable artistic text.