Visual object tracking plays a critical role in various applications, such as autonomous driving, video surveillance, and human-computer interaction. However, it remains a challenging task due to the complexities of target motion, appearance variations, and occlusions in video sequences. To address these challenges, this paper proposes TIFTrack, a single-object tracker based on spatiotemporal information. We explore the target’s motion trajectory in video sequences and the visual features between adjacent frames, introducing an inter-frame information extraction module to adaptively capture the required temporal information during tracking. This includes changes in the target’s trajectory, appearance, and size. Furthermore, to fully leverage temporal information, we propose a novel trajectory token that maps the target’s motion within a specific frame range. Additionally, we design a Temporal Decoder to process the captured temporal information and effectively combine static visual features with dynamic temporal features, enhancing tracking robustness. Experimental results on the GOT-10k, TrackingNet, LaSOT, and LaSOTextdatasets demonstrate that TIFTrack outperforms existing trackers across multiple benchmarks.

Sequential recommendation aims to predict the next item based on users' historical interaction behaviors.Most existing methods enhance representations by generating different views of user sequences via random augmentation and maximizing their mutual information.However, user interaction behaviors are influenced by underlying intents, and random augmentation may alter the original intents of users.Furthermore, the embedding representations based on Transformer exhibit high similarity, which can obscure short-term intents.To address these challenges, we propose an approach called Diffusion Model-based Intent Contrastive Learning for Sequential Recommendation (DICLR).DICLR leverages contextual information to guide the diffusion model in generating positive samples that are consistent in intent, and uses the Gated Linear Unit (GLU) to enhance context understanding and denoising effects.Additionally, DICLR uses the Fourier transform to separate the frequency-domain features of user behavior, thereby capturing both long-term and short-term user intents.DICLR integrates the recommendation task with intent contrastive learning and diffusion tasks within a multi-task learning framework.Experiments conducted on four datasets demonstrate the superiority of the proposed model.

Due to the rare occurrence of abnormal targets in substations, detecting these anomalies can be framed as a few-shot learning problem, for which recent few-shot object detection (FSOD) methods offer promising solutions. However, the complexity of substation scenarios makes current FSOD approaches struggle to control class centers, resulting in trained models typically exhibiting bias towards base classes and tending to confuse novel classes with base classes. To address these issues, we propose a feature aggregation method based on Variational Autoencoder (VAE) that transforms instance-level features into class distributions, thereby enhancing the robustness of feature aggregation. Additionally, to improve the quality of region proposal generation in sample-limited and complex environments, we integrate a multi-head attention mechanism into the Region Proposal Network (RPN), enabling it to produce more relevant region proposals. Extensive experiments on the Substation Abnormal Target Dataset (SATD2024) demonstrate that our approach consistently outperforms existing methods across various settings. Furthermore, we validate the effectiveness and generalization of our method on the public Pascal VOC dataset.

Annotated dialogue datasets are crucial for training models related to task-oriented systems, but such datasets are often scarce. Despite the existence of automated approaches for generating dialogue data, generating high-quality dialogue and accurate annotation remains a challenge. To address this issue, we propose Few-Shot Controlled Dialogue Generation Using In-Context Learning (ICI-CDG). It uses turn-level dialogue retrieval to enhance the in-context learning ability of large language models, enabling the rapid and automatic generation of high-quality controllable dialogues. The ICI-CDG consists of three modules: goal generation, turn-level dialogue retrieval, and state matching filtering. The goal generation generates new dialogue overall goals by randomly sampling from diverse dialogues, and these goals provide a clear direction and framework for the generation of new dialogues. The turn-level dialogue retrieval searches for turns with higher similarity as prompt, improving generated dialogue quality. The state matching filtering looks for generated content corresponding to the turn goals to reduce the semantic deviation between the annotation and the dialogue. The experimental results on the two datasets show that our method generates more natural dialogues with more accurate annotations, outperforming existing methods in few-shot settings.

Sequential recommendation (SR) predicts the next item by analyzing users' historical interaction data.However, it may lead to the homogenization of recommended items due to reliance on historical data.User sequences may also reflect latent intents influenced by factors such as seasonality or age.To address these challenges, we propose a model named Stochastic Embeddings in Multi-Intent Contrastive Learning for Sequential Recommendation (SICLR).SICLR uses mean and covariance embeddings to represent stochastic embeddings of sequential intents, leveraging Wasserstein distance to measure the distance between distributions.This approach can capture the uncertainty and non-stationarity in the distributions of intents.In addition, SICLR employs a multi-perspective of local and global viewpoints for intent contrastive learning, which enhances the capture of latent intent discrepancies and interest drifts.Furthermore, SICLR also integrates the recommendation task with local and global intent contrastive learning tasks.This can improve the recommendation performance of the model.The proposed model demonstrates improved performance metrics across three realworld datasets.It shows robustness and generalization under different training parameters.

Abstract Knowledge base completion (KBC) aims to predict missing information in a knowledge base. From a data governance perspective, KBC is an important task not only in knowledge management but also in downstream knowledge base applications. The prosperity of mobile applications and online systems enables devices to generate an enormous volume of data containing valuable knowledge. However, these data are vast and contain noise, so utilizing them in KBC requires particular skill. In this paper, we propose information fusion generative adversarial network (IFGAN) to handle heterogeneous data. We design a bidirectional learning architecture including a graph convolutional neural network and graph attention network to learn contextual embeddings that fuse knowledge from a knowledge base and data generated by an application. For efficient negative sampling, we employ different kinds of convolution structures, such as depthwise separable convolution and involution in the generator of the network. The convolution structure is known to be suitable for collaborative computing and promises great potential with the progress of technology since the structure is extensible. We demonstrate the effectiveness of the proposed model on KB4Rec dataset, the evaluation metrics MRR and H@10 were improved compared with previous models; the code is available at https://github.com/Tianchen627/IFGAN .

With the continuous accumulation of social network data, social recommendation has become a widely used recommendation method. Based on the theory of social relationship propagation, mining user relationships in social networks can alleviate the problems of data sparsity and the cold start of recommendation systems. Therefore, integrating social information into recommendation systems is of profound importance. We present an efficient network model for social recommendation. The model is based on the graph neural network. It unifies the attention mechanism and bidirectional LSTM into the same framework and uses a multilayer perceptron. In addition, an embedded propagation method is added to learn the neighbor influences of different depths and extract useful neighbor information for social relationship modeling. We use this method to solve the problem that the current research methods of social recommendation only extract the superficial level of social networks but ignore the importance of the relationship strength of the users at different levels in the recommendation. This model integrates social relationships into user and project interactions, not only capturing the weight of the relationship between different users but also considering the influence of neighbors at different levels on user preferences. Experiments on two public datasets demonstrate that the proposed model is superior to other benchmark methods with respect to mean absolute error and root mean square error and can effectively improve the quality of recommendations.

Understanding temporal dependencies of videos is fundamental for vision problems, but deep learning–based models are still insufficient in this field. In this article, we propose a novel deep multiplicative neural network (DMNN) for learning hierarchical long-term representations from video. The DMNN is built upon the multiplicative block that remembers the pairwise transformations between consecutive frames using multiplicative interactions rather than the regular weighted-sum ones. The block is slided over the timesteps to update the memory of the networks on the frame pairs. Deep architecture can be implemented by stacking multiple layers of the sliding blocks. The multiplicative interactions lead to exact, rather than approximate, modeling of temporal dependencies. The memory mechanism can remember the temporal dependencies for an arbitrary length of time. The multiple layers output multiple-level representations that reflect the multi-timescale structure of video. Moreover, to address the difficulty of training DMNNs, we derive a theoretically sound convergent method, which leads to a fast and stable convergence. We demonstrate a new state-of-the-art classification performance with proposed networks on the UCF101 dataset and the effectiveness of capturing complicate temporal dependencies on a variety of synthetic datasets.

Summary Fog computing is composed of various computers with weak performance instead of servers with strong performance. As history has shown, there has not been a general pairing‐free certificateless signature scheme that is mainly designed with modular exponentiation and modular multiplication that can possess resistance to Type I and Type II adversaries. The lightweight certificateless signature algorithm with low requirements for computing and storage capabilities, which can be practicably implemented in fog computing, needs to be studied. Therefore, a new hard mathematic problem is firstly defined in this paper, which is called variant of RSA problem. Then, a new general pairing‐free certificateless signature scheme is proposed based on the variant of RSA problem and the discrete logarithm problem. Fortunately, the proposed scheme is the first RSA‐based certificateless signature scheme that can possess resistance to Type I and Type II adversaries. A formal security proof is provided to demonstrate that, under adaptively chosen message attacks, the scheme is provably secure against Type I and Type II adversaries in the random oracle model. When compared with other known pairing‐free certificateless signature schemes of the same type, the computation cost of our scheme is slightly higher; however, a higher security level can be achieved.

The data for recommendations, usually a matrix composed of users and items, include a large number of missing data, noise data, etc, which have a negative effect on the accuracy of recommendations.In order to improve recommendation performance, this paper put forwards an improved model named Stacked Denoising AutoEncoder (SDAE), which improves the autoencoder by both indicators and denoising parts to construct an effective stacked autoencoding network.The first layer of the encoding network is responsible for dealing with missing data with the help of indicators and to get a new encoding for features, and then stacked denoising is applied to process noise data for a further optimization.SDAE's output can be accepted by collaborative filtering methods to provide a more accurate recommendation.Three data sets are used to verify the proposed model, the experimental results show that the proposed model presents an active ability on improving recommendation performance and mitigates the negative influence caused by missing data, noise data, etc.Index Terms-recommendation, data preprocessing, stacked encoding I. .

Summary Attribute reduction is one of the most important topics in rough set theory. In the classical rough sets, the method for attribute reduction is mainly to keep positive region, boundary region, and negative region unchanged. However, the three regions are no longer monotonic with respect to adding or deleting an attribute in decision‐theoretic rough sets. In decision‐theoretic rough set model, the decision regions are determined by using the Bayesian decision procedure, and decision‐making should take consideration of the cost. In this paper, two attribute reduction methods based on minimum decision cost are proposed from the algebraic view and the information theory, respectively. First, significance of joint attributes is introduced to measure the classification ability of selected attribute subset to decision‐making, which overcomes the disadvantage of only considering the significance of single attribute. By using significance of joint attributes, a heuristic method based on minimum decision cost for attribute reduction is presented. Second, conditional mutual information is proposed to evaluate the significance of attribute subset for decision‐making in minimum cost attribute reduction. To decrease the computational complexity of the conditional mutual information, an approximate computation method is calculated from both maximum relevance and maximum significance. To evaluate the two proposed algorithms, extensive experiments are conducted on 10 University of California at Irvine data sets. We compare our proposed algorithms with several existing cost minimization attribute reduction algorithms. Experiment results show that our proposed algorithms have a superior performance in achieving the reduct. Copyright © 2016 John Wiley & Sons, Ltd.

Unsupervised hyperspectral band selection has been an important topic in hyperspectral imagery. This technique aims at selecting some critical and decisive spectral bands from an original image for compact representation without compromising and distorting the raw information in the relevant spectral bands. Although many efforts have been made to this topic, the structural information has not yet been well exploited during band selection, and there are still several deficiencies in search strategies, leaving room for further improvement. This paper tackles the unsupervised hyperspectral band selection problem from a global perspective and proposes a novel method claiming the following main contributions: structure-aware measures for band informativeness and independence; and a graph formulation of band selection allowing for an efficient integrated search by means of dominant set extraction. Experiments on three real hyperspectral images demonstrate the superiority of the proposed band selector in comparison with benchmark methods.

This paper tackles a recent challenge in identifying culprit actors, who try to hide confidential payload with steganography, among many innocent actors in social media networks. The problem is called steganographer detection problem and is significantly different from the traditional stego detection problem that classifies an individual object as a cover or a stego. To solve the steganographer detection problem over large-scale social media networks, this paper proposes a method that uses high-order joint features and clustering ensembles. It employs 250-D features calculated from the high-order joint matrices of Discrete Cosine Transform (DCT) coefficients of JPEG images, which indicate the dependencies of image content. Furthermore, a number of hierarchical sub-clusterings trained by the features are integrated as a clustering ensemble based on the majority voting strategy, which is used to make optimal decisions on suspicious steganographers. Experimental results show that the proposed scheme is effective and efficient in identifying potential steganographers in large-scale social media networks, and has better performance when tested against the state-of-the-art steganographic methods.