Spatiotemporal forecasting (STF) is pivotal in urban computing, yet data scarcity in developing cities hampers robust model training. Addressing this, recent studies leverage transfer learning to migrate knowledge from data-rich (source) to data-poor (target) cities. This strategy, while effective, faces challenges as pre-trained models risk absorbing noise and harmful information due to data distribution disparities, potentially undermining the accuracy of forecasts for target cities. To address this issue, we propose a one-stage STF framework named Target-Skewed Joint Training (TSJT). Central to TSJT is a novel Target-Skewed Backward training strategy that selectively refines gradients from source city data, preserving only the elements that positively impact the target city. To further enhance the quality of these gradients, we have designed a Node Prompting Module (NPM). TSJT is crafted for seamless integration with existing STF models, endowing them with the capability to efficiently tackle challenges stemming from data scarcity. Experimental results on several real-world datasets from multiple cities substantiate the efficacy of TSJT in the realm of cross-city transfer learning.

Massive open online courses (MOOCs) recommendation provides online courses tailored to learners' individual preferences. Existing literature is limited by: 1) Ignoring the interrelations among courses, knowledge concepts, and videos, which leads to suboptimal recommendation performance; 2) Neglecting the hierarchical interactions between learners and components like courses, knowledge concepts, and videos, which makes it difficult to capture learners' intentions accurately. To address them, we propose a novel multi-type MOOCs recommendation framework, which enables multi-type educational content recommendations. This framework includes two important components: multi-relational representation and hierarchical reasoning. Regarding multi-relational representation, we first create two static course-relational and knowledge concept-relational graphs based on domain knowledge and construct a dynamic video-relational graph using learners' browsing historical sequences. Then, we capture the interactions among different components by learning the corresponding embeddings via graph neural networks. Regarding hierarchical reasoning, we implement a hierarchical beam search strategy to narrow down the candidate courses, knowledge concepts, and videos by calculating joint probability. Finally, we introduce an optional layer to increase the diversity and reasonableness of video recommendations by estimating learners' intentions. Extensive experiments are conducted to show the effectiveness, robustness, and interpretability of our method.

Recently, the success of text-to-image synthesis has greatly advanced the development of identity customization techniques, whose main goal is to produce realistic identity-specific photographs based on text prompts and reference face images. However, it is difficult for existing identity customization methods to simultaneously meet the various requirements of different real-world applications, including the identity fidelity of small face, the control of face location, pose and expression, as well as the customization of multiple persons. To this end, we propose a scale-robust and fine-controllable method, namely RealisID, which learns different control capabilities through the cooperation between a pair of local and global branches. Specifically, by using cropping and up-sampling operations to filter out face-irrelevant information, the local branch concentrates the fine control of facial details and the scale-robust identity fidelity within the face region. Meanwhile, the global branch manages the overall harmony of the entire image. It also controls the face location by taking the location guidance as input. As a result, RealisID can benefit from the complementarity of these two branches. Finally, by implementing our branches with two different variants of ControlNet, our method can be easily extended to handle multi-person customization, even only trained on single-person datasets. Extensive experiments and ablation studies indicate the effectiveness of RealisID and verify its ability in fulfilling all the requirements mentioned above.

Typical spatiotemporal graph forecasting methods process graph-structured spatiotemporal data respectively from spatial and temporal perspectives with the idea of divide and conquer. Existing works are incapable of capturing long-term transdimensional correlations among different spatial points in different time planes, i.e., time-space-interlaced correlations. To tackle this issue, we propose a two-stage summarized attention network to establish transdimensional direct message passing routes between different data points in different time planes and spaces, thus enabling the extraction of time-space-interlaced long-term correlations. Specifically, a novel spatiotemporal embedding is proposed to implement time-space-interlaced learning by expanding orthogonal spatial and temporal dimensionalities into one-dimensionality, a series of temporal context fusion units are added to address the fluctuation dislocation insensitivity issue which is caused by time-space-dimension expansion, and an ingenious two-stage design can significantly reduce the computation complexity of such time-space-interlaced learning. Extensive experiments illustrate the superior performance of our proposed approach on real-world spatiotemporal datasets.

Generative flow networks (GFlowNets) have been considered as powerful tools for generating candidates with desired properties. Given that evaluating the property of candidates can be complex and time-consuming, existing GFlowNets train proxy models for efficient online evaluation. However, the performance of proxy models is heavily dependent on the amount of data and is of considerable uncertainty. Therefore, it is of great interest that how to develop an offline GFlowNet that does not rely on online evaluation. Under the offline setting, the limited data results in an insufficient exploration of state space. The insufficient exploration means that offline GFlowNets can hardly generate satisfying candidates out of the distribution of training data. Therefore, it is critical to restrict the offline model to act in the distribution of training data. The distinctive training goal of GFlownets poses a unique challenge for making such restrictions. Tackling the challenge, we propose Conservative Offline GFlowNet (COFlowNet) in this paper. We define unsupported flow, edges containing unseen states in training data. Models can learn extremely little knowledge about unsupported flow from training data. By constraining the model from exploring unsupported flows, we restrict COFlowNet to explore as optimal trajectories on the training set as possible, thus generating better candidates. In order to improve the diversity of candidates, we further introduce a quantile version of unsupported flow restriction. Experimental results on several widely-used datasets validate the effectiveness of COFlowNet in generating high-scored and diverse candidates. All implementations are available at https://github.com/yuxuan9982/COflownet.

Current spatio-temporal modeling techniques largely rely on the abundant data and the design of task-specific models. However, many cities lack well-established digital infrastructures, making data scarcity and the high cost of model development significant barriers to application deployment. Therefore, this work aims to enable spatio-temporal learning to cope with the problems of few-shot data modeling and model generalizability. To this end, we propose a Universal Spatio-Temporal Correlationship pre-training framework (USTC), for spatio-temporal modeling across different cities and tasks. To enhance the spatio-temporal representations during pre-training, we propose to decouple the time-frequency patterns within data, and leverage contrastive learning to maintain the time-frequency consistency. To further improve the adaptability to downstream tasks, we design a prompt generation module to mine personalized spatio-temporal patterns on the target city, which can be integrated with the learned common spatio-temporal representations to collaboratively serve downstream tasks. Extensive experiments conducted on real-world datasets demonstrate that USTC significantly outperforms the advanced baselines in forecasting, imputation, and extrapolation across cities.

The purpose of makeup transfer (MT) is to transfer makeup from a reference image to a target face while preserving the target's content. Existing methods have made remarkable progress in generating realistic results but do not perform well in terms of semantic correspondence and color fidelity. In addition, the straightforward extension of processing videos frame by frame tends to produce flickering results in most methods. These limitations restrict the applicability of previous methods in real-world scenarios. To address these issues, we propose a symmetric semantic-aware transfer network (SSAT++) to improve makeup similarity and video temporal consistency. For MT, the feature fusion (FF) module first integrates the content and semantic features of the input images, producing multiscale fusion features. Then, the semantic correspondence from the reference to the target is obtained by measuring the correlation of fusion features at each position. According to semantic correspondence, the symmetric mask semantic transfer (SMST) module aligns the reference makeup features with the target content features to generate MT results. Meanwhile, the semantic correspondence from the target to the reference is obtained by transposing the correlation matrix and applied to the makeup removal task. To enhance color fidelity, we propose a novel local color loss that forces the transferred results to have the same color histogram distribution as the reference. Furthermore, a morphing simulation is designed to ensure temporal consistency for video MT without requiring additional video frame input and optical flow estimation. To evaluate the effectiveness of our SSAT++, extensive experiments have been conducted on the MT dataset which has a variety of makeup styles, and on the MT-Wild dataset which contains images with diverse poses and expressions. The experiments show that SSAT++ outperforms existing MT methods through qualitative and quantitative evaluation and provides more flexible makeup control. Code and trained model will be available at https://gitee.com/sunzhaoyang0304/ssat-msp and https://github.com/Snowfallingplum/SSAT.

The absence of real targets to guide the model training is one of the main problems with the makeup transfer task. Most existing methods tackle this problem by synthesizing pseudo ground truths (PGTs). However, the generated PGTs are often sub-optimal and their imprecision will eventually lead to performance degradation. To alleviate this issue, in this paper, we propose a novel Content-Style Decoupled Makeup Transfer (CSD-MT) method, which works in a purely unsupervised manner and thus eliminates the negative effects of generating PGTs. Specifically, based on the frequency characteristics analysis, we assume that the low-frequency (LF) component of a face image is more associated with its makeup style information, while the high-frequency (HF) component is more related to its content details. This assumption allows CSD-MT to decouple the content and makeup style information in each face image through the frequency decomposition. After that, CSD-MT realizes makeup transfer by maximizing the consistency of these two types of information between the transferred result and input images, respectively. Two newly designed loss functions are also introduced to further improve the transfer performance. Extensive quantitative and qualitative analyses show the effectiveness of our CSD-MT method. Our code is available at https://github.com/Snowfallingplum/CSD-MT.

This paper studies the challenging task of makeup transfer, which aims to apply diverse makeup styles precisely and naturally to a given facial image. Due to the absence of paired data, current methods typically synthesize sub-optimal pseudo ground truths to guide the model training, resulting in low makeup fidelity. Additionally, different makeup styles generally have varying effects on the person face, but existing methods struggle to deal with this diversity. To address these issues, we propose a novel Self-supervised Hierarchical Makeup Transfer (SHMT) method via latent diffusion models. Following a "decoupling-and-reconstruction" paradigm, SHMT works in a self-supervised manner, freeing itself from the misguidance of imprecise pseudo-paired data. Furthermore, to accommodate a variety of makeup styles, hierarchical texture details are decomposed via a Laplacian pyramid and selectively introduced to the content representation. Finally, we design a novel Iterative Dual Alignment (IDA) module that dynamically adjusts the injection condition of the diffusion model, allowing the alignment errors caused by the domain gap between content and makeup representations to be corrected. Extensive quantitative and qualitative analyses demonstrate the effectiveness of our method. Our code is available at https://github.com/Snowfallingplum/SHMT.

Rapid advances in Earth observation technologies have yielded numerous remotely sensed images and corresponding text data, enabling cross-modal image–text retrieval to extract valuable clues. However, current methods often focus on learning global semantic information from text and remote sensing (RS) images, while neglecting fine-grained semantic alignment and correlation. In addition, contrastive learning between modalities is often insufficient. To address these issues, we propose an innovative cues-driven multiassociation feature matching network (CDMAN) for cross-modal RS image retrieval. The proposed method primarily involves two key steps: 1) aligning positive samples and enhancing fusion for negative samples based on modal cues. To achieve precise alignment between RS images and text and facilitate the learning process for negative samples in contrastive learning, we have developed a novel fine-grained cues injection module that aligns and guides modalities using fine-grained cues; and 2) establishing multigranularity associative learning. To address the issue of insufficient association between RS images and text, we have implemented multigranularity collaborative associative learning, focusing on general and fine-grained modal associations. By fully leveraging modal cues, our method maintains both detailed associations and overall consistency in global associations. Experiments demonstrate that, compared to baseline methods, this approach achieves more accurate cross-modal retrieval (MCR) by combining fine-grained alignment and multigranularity associations.

Self-supervised learning (SSL) techniques have recently been integrated into the few-shot learning (FSL) framework and have shown promising results in improving the few-shot image classification performance. However, existing SSL approaches used in FSL typically seek the supervision signals from the global embedding of every single image. Therefore, during the episodic training of FSL, these methods cannot capture and fully utilize the local visual information in image samples and the data structure information of the whole episode, which are beneficial to FSL. To this end, we propose to augment the few-shot learning objective with a novel self-supervised Episodic Spatial Pretext Task (ESPT). Specifically, for each few-shot episode, we generate its corresponding transformed episode by applying a random geometric transformation to all the images in it. Based on these, our ESPT objective is defined as maximizing the local spatial relationship consistency between the original episode and the transformed one. With this definition, the ESPT-augmented FSL objective promotes learning more transferable feature representations that capture the local spatial features of different images and their inter-relational structural information in each input episode, thus enabling the model to generalize better to new categories with only a few samples. Extensive experiments indicate that our ESPT method achieves new state-of-the-art performance for few-shot image classification on three mainstay benchmark datasets. The source code will be available at: https://github.com/Whut-YiRong/ESPT.

Single-cell RNA sequencing (scRNA-seq) technology is utilized to analyze cellular heterogeneity, perform cellular-level biological research and derive novel insights from complex cellular systems. However, the raw scRNA-seq data is not directly suitable for downstream task analysis due to its high variability, sparsity and dimensionality. Therefore, in this study, we propose a new self-supervised framework based on siamese representation learning, named scSRL which can fully explore the intrinsic properties of cells by maximizing the similarity between positive pairs. These positive pairs are constructed by multiple data augmentation operations to further increase data diversity and better learn latent representation. Moreover, our method employs a gradient stopping strategy to mitigate collapsing in the siamese network. It is worth noting that the scSRL focuses on aggregating cells with similar functions without introducing negative samples, which can avoid additional computational cost. Finally, We evaluated scSRL on 10 real datasets for downstream tasks such as clustering, classification and visualization, and it consistently exhibited outstanding performance in all these fundamental tasks. Meanwhile, we did pseudotime inference experiments in two embryonic development datasets, and the scSRL model can accurately reconstruct cell trajectory and describe cell developmental process. scSRL is currently an open-source method, available at https://github.com/zysun17/scSRL.

The construction of a smart campus has become an important part of educational informatization and a significant indicator of the educational modernization. Campuses across China are moving from traditional digital campus construction to smart campus construction. Chinese telecom operators, with their innate advantages in network infrastructure and resource, have become important service providers in the construction of smart campus. Telecom operators have effectively explored the application platform and application scenarios of smart campuses by leveraging existing educational service products and big data resources at their disposal.

Makeup transfer is not only to extract the makeup style of the reference image, but also to render the makeup style to the semantic corresponding position of the target image. However, most existing methods focus on the former and ignore the latter, resulting in a failure to achieve desired results. To solve the above problems, we propose a unified Symmetric Semantic-Aware Transformer (SSAT) network, which incorporates semantic correspondence learning to realize makeup transfer and removal simultaneously. In SSAT, a novel Symmetric Semantic Corresponding Feature Transfer (SSCFT) module and a weakly supervised semantic loss are proposed to model and facilitate the establishment of accurate semantic correspondence. In the generation process, the extracted makeup features are spatially distorted by SSCFT to achieve semantic alignment with the target image, then the distorted makeup features are combined with unmodified makeup irrelevant features to produce the final result. Experiments show that our method obtains more visually accurate makeup transfer results, and user study in comparison with other state-of-the-art makeup transfer methods reflects the superiority of our method. Besides, we verify the robustness of the proposed method in the difference of expression and pose, object occlusion scenes, and extend it to video makeup transfer.

Makeup transfer aims at rendering the makeup style from a given reference image to a source image. Most existing works have achieved promising progress by disentangled representation. However, these methods do not consider the spatial distribution of makeup style, which inevitably change the makeup-irrelevant regions. To solve the problem, we introduce a novel feature space disentangling framework based on spatial attention mechanism for makeup transfer. In particular, we first utilize a single encoder to extract all the features of the image. Then we propose a learnable spatial semantic classifier to classify the extracted features into makeup-specific and makeup-irrelevant features. Finally, we complete makeup transfer by swapping the classified features. Experiments demonstrate that the makeup-specific features precisely signify the spatial distribution of makeup style. The superiority of our approach is well demonstrated by the experiment that it produces promising visual results and keeps those makeup-irrelevant regions unchanged.

Facial makeup transfer aims to transfer the makeup style from a reference makeup image to a source image. In daily life, the reference makeup images from various scenes are uneasy about guaranteeing quality. In contrast, the source images photoed by ourselves are likely to control illumination and avoid shadows cast by occlusion. To this end, we propose a novel robust makeup transfer network (SRMT) for facial makeup and de-makeup under the foreign shadow. The reference image is hierarchically aggregated multi-context features for predicting makeup style which is input into a disentangled network with source image for achieving shadow robust makeup transfer. In particular, we first incorporate a shadow manipulation module(SMM) to manipulate the reference makeup, which furtherly restores the original color distribution on the face. Then we propose a makeup transfer module(MTM) based on disentangled representation, producing a high-quality source image from the predicted reference makeup. Extensive experiments show the superiority of our method in terms of visual effects. Moreover, a carefully designed makeup dataset with paired shadow-deshadow makeup images is available at https://github.com/lucuspring/Deshadow-dataset.

In this paper, the defocus of a 2-D image reconstruction of targets illuminated by Gaussian beams in terahertz (THz) single-frequency holography was studied. An analytical point-spread function was derived to quantitatively evaluate the defocus effect, considering the deviation of the restoration distance from the real distance of the target. It is found that the cross-range image defocuses in a similar way to the diffusion of a Gaussian beam from its beam waist, which limits the depth of focus for image restoration. To improve the restored images for targets with varying range distances, an adaptive focusing algorithm based on the minimum-entropy method was proposed for single-frequency holography. Simulation results with fairly good agreement were performed to verify the theoretical results and the proposed algorithm. Proof-of-principle experiments in the 0.2-THz band were also performed based on a monostatic prototype imager with a Gaussian beam transceiver. The experimental results confirm the effectiveness of the adaptive focusing reconstruction algorithm proposed in this paper.

In this paper, the wave equation based on phase shift migration technique is extended for terahertz 3-D imaging with quasi-optical transceivers. An analytical expression of the reconstructed 3-D point-spread function for targets under the illumination of a terahertz Gaussian beam was derived with this reconstruction technique. The quantitative relationship between the imaging quality and the parameters of the transmitted Gaussian beam was obtained, which provides a good criterion to be followed when designing the terahertz quasi-optical transceivers in the imaging systems. Moreover, the spatial sampling criterion was derived strictly which is also quantitatively related to the parameters of the transmitted Gaussian beam. Simulation results with fairly good agreement were given to verify the theoretical results derived in this paper. Finally, a monostatic prototype imager with a Gaussian beam transceiver was designed for the proof-of-principle experiments in 0.2-THz band. The 3-D imaging results of different targets and a mannequin with concealed threat objects were given to demonstrate the theoretical results obtained in this paper and the effectiveness of the 3-D terahertz image reconstruction for security applications.

One way to reduce potentially serious problems caused by modifications to the original design is to find out design thinking process of the original designer. The knowledge structure of design thinking process is represented, which is composed of design intent, design decision, design rationale and design operation. Semi-formal structure is adopted by the presentation, which means both the expressiveness and computability of the representation can be improved. Context in the design thinking process is defined, which can reduce complexity of the design thinking process. Independence between contexts that share an intent allows the designer to propose more assumptions about the design without necessarily affecting previous design thinking process. A graphical modeling system is established for capturing and formalizing the design thinking process.

A review for product development and knowledge management including product development process, process history, design intent and domain knowledge is presented. Modeling the product development process is the first step of the history knowledge management in the product development process. The integrated framework of the history knowledge management (HKM) is set up and the hierarchical model of history knowledge is built based on process. Methods for the acquisition and management of history knowledge are presented including process history, design intent and domain knowledge. A method of integrated knowledge representation (KR), generalized rule (GR), is described for history knowledge. The functional modules of knowledge-based PDPM system are described and HKM is its important part. The architecture of HKM system based on PDPM is clarified. The prototyping software for HKM is developed and used successfully during the lifecycle of a new type of railway rolling stock development in a Chinese enterprise, QQHR Railway Rolling Stock Company.