Multibehavior recommendation reflect users’ personalized preferences from multiple perspectives by exploring the dependencies among various user behaviors (such as clicks, favorites, and purchases). However, they still struggle with the sparsity of target behaviors. While some approaches have integrated contrastive learning techniques, they face two significant challenges: 1) roughly summing the contrastive tasks overlooks users’ personalized behavior patterns; and 2) unreasonable denoising methods for auxiliary behaviors disrupt the original user behavior sequence. To address these challenges, we propose a novel method called explicit personalized contrastive recommendation based on multibehavior denoising (MB-PCD). Specifically, we design an explicit personalized behavior pattern extraction module to mine users’ explicit personalized behavior patterns and behavior semantics, incorporating these insights into the contrastive task. This allows the model to more accurately capture the complex dependencies between behaviors. In addition, we create a customized denoising module tailored to the characteristics of user behaviors, effectively denoising without disrupting the original order of behaviors. Furthermore, we introduce a multibehavior information fusion module to tackle the issue of target behavior sparsity. Extensive experiments across three datasets demonstrate that our method consistently outperforms various state-of-the-art (SOTA) approaches. Analysis experiments further validate that our method effectively enhances the model’s robustness.

Outlier detection is one of the hot topics in the field of machine learning and data mining. At present, there are many kinds of outlier detection algorithms. The accuracies of traditional outlier detection algorithms are often affected by unique parameters, and an increase in the amount of data and the dimensions of the data can seriously affect their efficiency and effectiveness. Methods based on generative adversarial networks (GANs) can solve the above problems, but they are unacceptable since the model often collapses during the training period. In this article, to solve the problems of curse of dimensionality and model collapse, we propose a novel reinforced noise discriminator (RND) method for unsupervised outlier detection in tabular data. We consider outlier detection as a binary classification problem. Thus, we apply a learnable reinforced discriminator and generate a large number of potential outliers with a uniform distribution and potential outliers that are close to the original data that are used as a negative sample to train the discriminator, which learns the distribution of the original data to detect outliers. We empirically compare the proposed approach with ten state-of-the-art outlier detection methods on both synthetic and real-world tabular datasets. The experimental results show that RND outperforms its competitors in the majority of cases. The codes used to perform the experiments described in this article are available at https://github.com/urlhearts/r-n-d .

Video-based movie genre classification has garnered considerable attention due to its various applications in recommendation systems. Prior work has typically addressed this task by adapting models from traditional video classification tasks, such as action recognition or event detection. However, these models often neglect language elements (e.g., narrations or conversations) present in videos, which can implicitly convey high-level semantics of movie genres, like storylines or background context. Additionally, existing approaches are primarily designed to encode the entire content of the input video, leading to inefficiencies in predicting movie genres. Movie genre prediction may require only a few shots1to accurately determine the genres, rendering a comprehensive understanding of the entire video unnecessary. To address these challenges, we propose a Movie genre Classification method based on Language augmentatIon and shot samPling (Movie-CLIP). MovieCLIP mainly consists of two parts: a language augmentation module to recognize language elements from the input audio, and a shot sampling module to select representative shots from the entire video. We evaluate our method on MovieNet and Condensed Movies datasets, achieving approximate 6 − 9% improvement in mean Average Precision (mAP) over the baselines. We also generalize Movie-CLIP to the scene boundary detection task, achieving 1.1% improvement in Average Precision (AP) over the state-of-the-art. We release our implementation at this http URL.

Diffusion models have demonstrated impressive performance in text-guided image generation. Current methods that leverage the knowledge of these models for image editing either fine-tune them using the input image (e.g., Imagic) or incorporate structure information as additional constraints (e.g., ControlNet). However, fine-tuning large-scale diffusion models on a single image can lead to severe overfitting issues and lengthy inference time. Information leakage from pretrained models also make it challenging to preserve image content not related to the text input. Additionally, methods that incorporate structural guidance (e.g., edge maps, semantic maps, keypoints) find retaining attributes like colors and textures difficult. Using the input image as a control could mitigate these issues, but since these models are trained via reconstruction, a model can simply hide information about the original image when encoding it to perfectly reconstruct the image without learning the editing task. To address these challenges, we propose a text-to-image editing model with an Image Information Removal module (IIR) that selectively erases color-related and texture-related information from the original image, allowing us to better preserve the text-irrelevant content and avoid issues arising from information hiding. Our experiments on CUB, Outdoor Scenes, and COCO reports our approach achieves the best editability-fidelity trade-off results. In addition, a user study on COCO shows that our edited images are preferred 35% more often than prior work.

Abstract Multi-behavior recommendation systems exploit multi-type user–item interactions (e.g., clicking, adding to cart and collecting) as auxiliary behaviors for user modeling, which can alleviate the problem of data sparsity faced by traditional recommendation systems. The key point of multi-behavior recommendation systems is to make full use of the auxiliary behavior information for the learning of user preferences. However, there are two challenges in existing methods that need to be explored: (1) capturing personalized user preferences based on multiple auxiliary behaviors, especially for negative feedback signals; and (2) explicitly modeling the semantics between auxiliary and target behaviors, and learning the explicit interactions between multiple behaviors. To tackle the two problems described above, we propose a novel model, called explicit behavior interaction with heterogeneous graph for multi-behavior recommendation (MB-EBIH). In particular, we first construct a heterogeneous behavior graph, including both positive and negative behaviors. A pre-trained model based on graph neural network (GNN) is then used to generate explicit behavior interaction values as the edge weights for the heterogeneous behavior graph. These weights reflect the importance of each of the auxiliary behaviors in an explicit manner. Finally, the extracted explicit behavior interaction information is incorporated into the multi-behavior user–item bipartite graphs to learn better representations. Experimental results on four real-world datasets demonstrate the effectiveness of our model in terms of exploring multi-behavioral data; and ablation and analysis experiments further demonstrate the effectiveness of explicit behavior interaction information.

Online fraud is the well-known dark side of the modern Internet. Unsupervised fraud detection algorithms are widely used to address this problem. However, selecting features, adjusting hyperparameters, evaluating the algorithms, and eliminating false positives all require human expert involvement. In this work, we design and implement an end-to-end interactive visualization system, FDHelper, based on the deep understanding of the mechanism of the black market and fraud detection algorithms. We identify a workflow based on experience from both fraud detection algorithm experts and domain experts. Using a multi-granularity three-layer visualization map embedding an entropy-based distance metric ColDis, analysts can interactively select different feature sets, refine fraud detection algorithms, tune parameters and evaluate the detection result in near real-time. We demonstrate the effectiveness and significance of FDHelper through two case studies with state-of-the-art fraud detection algorithms, interviews with domain experts and algorithm experts, and a user study with eight first-time end users.

Full-waveform inversion is an important and widely used method to reconstruct subsurface velocity images. Waveform inversion is a typical nonlinear and ill-posed inverse problem. Existing physics-driven computational methods for solving waveform inversion suffer from the cycle-skipping and local-minima issues, and do not mention that solving waveform inversion is computationally expensive. In recent years, data-driven methods become a promising way to solve the waveform-inversion problem. However, most deep-learning frameworks suffer from the generalization and overfitting issue. In this article, we developed a real-time data-driven technique and we call it VelocityGAN, to reconstruct accurately the subsurface velocities. Our VelocityGAN is built on a generative adversarial network (GAN) and trained end to end to learn a mapping function from the raw seismic waveform data to the velocity image. Different from other encoder-decoder-based data-driven seismic waveform-inversion approaches, our VelocityGAN learns regularization from data and further imposes the regularization to the generator so that inversion accuracy is improved. We further develop a transfer-learning strategy based on VelocityGAN to alleviate the generalization issue. A series of experiments is conducted on the synthetic seismic reflection data to evaluate the effectiveness, efficiency, and generalization of VelocityGAN. We not only compare it with the existing physics-driven approaches and data-driven frameworks but also conduct several transfer-learning experiments. The experimental results show that VelocityGAN achieves the state-of-the-art performance among the baselines and can improve the generalization results to some extent.

Seismic event classification and detection have been important research topics because of their significance and wide applications on hazard assessment and global security. In the real world, seismic data acquisition are always impacted by unavoidable nature factors, which will introduce low-frequency noise to the seismic events of interests. Pre-processing of seismic signal using denoising techniques can be critical to the detection of the seismic events. In our work, we develop an end-to-end framework which can automatically learn the hyper-parameter in the denoising algorithm so that we do not need to manually set the hyper-parameter. Specifically, our network structure consists of two modules, an adaptive filtering module for signal denoising, and a classification module for signal classification. We further develop two mechanisms of the adaptive filtering module, namely, sample-specific mechanism and dataset-specific mechanism. We validate the performance of our detection method using a series of field seismic datasets. The classification results show that our framework can not only remove signal noise effectively but also improve the classification accuracy.

Acoustic-and elastic-waveform inversion is an important and widely used method to reconstruct subsurface velocity image. Waveform inversion is a typical non-linear and ill-posed inverse problem. Existing physics-driven computational methods for solving waveform inversion suffer from the cycle skipping and local minima issues, and not to mention solving waveform inversion is computationally expensive. In this paper, we developed a real-time datadriven technique, VelocityGAN, to accurately reconstruct subsurface velocities. Our VelocityGAN is an end-to-end framework which can generate high-quality velocity images directly from the raw seismic waveform data. A series of experiments are conducted on the synthetic seismic reflection data to evaluate the effectiveness and efficiency of VelocityGAN. We not only compare it with existing physics-driven approaches but also choose some deep learning frameworks as our data-driven baselines. The experiment results show that VelocityGAN outperforms the physics-driven waveform inversion methods and achieves the state-of-the-art performance among data-driven baselines.

With a growing number of social apps, people have become increasingly willing to share their everyday photos and events on social media platforms, such as Facebook, Instagram, and WeChat. In social media data mining, post popularity prediction has received much attention from both data scientists and psychologists. Existing research focuses more on exploring the post popularity on a population of users and including comprehensive factors such as temporal information, user connections, number of comments, and so on. However, these frameworks are not suitable for guiding a specific user to make a popular post because the attributes of this user are fixed. Therefore, previous frameworks can only answer the question "whether a post is popular" rather than "how to become famous by popular posts". In this paper, we aim at predicting the popularity of a post for a specific user and mining the patterns behind the popularity. To this end, we first collect data from Instagram. We then design a method to figure out the user environment, representing the content that a specific user is very likely to post. Based on the relevant data, we devise a novel dual-attention model to incorporate image, caption, and user environment. The dual-attention model basically consists of two parts, explicit attention for image-caption pairs and implicit attention for user environment. A hierarchical structure is devised to concatenate the explicit attention part and implicit attention part. We conduct a series of experiments to validate the effectiveness of our model and investigate the factors that can influence the popularity. The classification results show that our model outperforms the baselines, and a statistical analysis identifies what kind of pictures or captions can help the user achieve a relatively high "likes" number.

Image forgery detection is the task of detecting and localizing forged parts in tampered images. Previous works mostly focus on high resolution images using traces of resampling features, demosaicing features or sharpness of edges. However, a good detection method should also be applicable to low resolution images because compressed or resized images are common these days. To this end, we propose a Shallow Convolutional Neural Network (SCNN) capable of distinguishing the boundaries of forged regions from original edges in low resolution images. SCNN is designed to utilize the information of chroma and saturation. Based on SCNN, two approaches that are named Sliding Windows Detection (SWD) and Fast SCNN respectively, are developed to detect and localize image forgery region. Our model is evaluated on the CASIA 2.0 dataset. The results show that Fast SCNN performs well on low resolution images and achieves significant improvements over the state-of-the-art.

The Environmental Satellite (Envisat) mission was finished on April 8, 2012, and since that time, the attitude of the satellite has undergone significant changes. During the International Laser Ranging Service campaign, the Satellite Laser Ranging (SLR) stations have performed the range measurements to the satellite that allowed determination of the attitude and the spin period of Envisat during seven months of 2013. The spin axis of the satellite is stable within the radial coordinate system (RCS; fixed with the orbit) and is pointing in the direction opposite to the normal vector of the orbital plane in such a way that the spin axis makes an angle of 61.86° with the nadir vector and 90.69° with the along-track vector. The offset between the symmetry axis of the retroreflector panel and the spin axis of the satellite is 2.52 m and causes the meter-scale oscillations of the range measurements between the ground SLR system and the satellite during a pass. Envisat rotates in the counterclockwise (CCW) direction, with an inertial period of 134.74 s (September 25, 2013), and the spin period increases by 36.7 ms/day.