Early identification of depression is of great significance for clinical intervention. At present, artificial intelligence technology has made effective progress in the field of automatic detection of depression. However, due to the scarcity and homogeneity of data, the existing models have the problem of insufficient robustness and generalization ability for unseen data or out-ofdistribution data. To address these challenges, this paper proposes a multi-strategy collaborative training framework, DeprGen-RL, which combines the advantages of large language models (LLMs) with reinforcement learning (RL), aiming to improve the generation quality of depression text and the robustness of detection models. A large language model is used to play the role of a generator to learn and reproduce the unique vocabulary, syntactic structure and emotional expression of patients with depression. The reward mechanism of reinforcement learning was used to guide the text generation process to ensure that the generated text was highly consistent with the correlation of depression in language features. Through the collaborative training of the generator and the discriminator, the performance of the LLM generator is continuously optimized, so that the model can generate high-quality synthetic texts to expand the training set and improve the robustness of the downstream classifier. Experiments show that the DeprGen-RL discriminator performs better than traditional methods in cross-dataset experiments, achieving an accuracy of 0.72 on the Pirina dataset and 0.81 on the DAIC-WOZ dataset. At the same time, the generation quality (measured by perplexity and BLEU value) is also improved.

Graph Neural Networks (GNNs) have gained increasing popularity in learning node embeddings for graph inference tasks, but their training raises significant privacy concerns. Recent differential privacy GNN models address this issue by continuously adding Gaussian noise to the aggregation functions. While this effectively obscures individual edge information, the noise accumulates with each aggregation, degrading the quality of the final node representations and complicating the trade-off between privacy and accuracy. In this paper, we propose a novel differential privacy GNN, called HDAGAP. We decompose the GNN into a series of hierarchical sub-models and apply aggregation perturbation techniques at each layer during training. Each node then dynamically adjusts the range of its perceived neighboring nodes through an adaptive mechanism based on the actual environment. This allows the model to learn more discriminative node representations from a broader neighborhood, improving performance while reducing privacy costs. To validate our method, we conducted extensive experiments on three node classification benchmark datasets. Results demonstrate that HDAGAP significantly outperforms existing DP-GNNs in terms of the privacy-accuracy trade-off.

With the rapid development of digital technology, the proliferation of fake news not only misleads the audience but also has the potential to exacerbate social conflicts. Although some progress has been made in the field of fake news detection, most existing fake news detection methods fail to address inter-domain modal differences, overlook finer-grained alignment between text and visuals, and are limited by shallow fusion of news text, images, and comments. In this study, a new approach based on Global-Local Contrastive learning multi-Modal multi-Domain Fake News Detection(GLCMDFND) is proposed. The framework extracts detailed multi-modal features, employs global-local cross-modal integration to enrich modal diversity, uses contrastive learning for accurate modal alignment. Inspired by the way Internet users browse news, utilizes CrossMamba to compute textual and visual dependencies, fuses them, and integrates the results with comments. The proposed model has been extensively evaluated on Weibo 21 and Fakeddit. The results demonstrate that GLCMDFND enhances the performance of fake news detection.

In the treatment of various diseases, a single drug often fails to achieve the desired therapeutic effect, necessitating the use of multi-drug combinations. However, the vast combinatorial space of drug interactions makes screening for effective synergistic combinations a time-consuming and labor-intensive process. Predicting drug-drug synergies through computational models offers a promising solution to improve the efficiency of drug screening and design. Despite the development of numerous computational methods for predicting drug combination synergies, few focus on higher-order tertiary drug-drug-cell line (DDC) associations, which limits the models’ ability to learn complex patterns from the dataTo address this gap, we propose Hypergraph-Encoder, a novel approach that constructs hyperedges based on the synergistic effects between nodes. This method incorporates a dynamic weighting mechanism in hypergraph representation learning, enhancing the model’s ability to capture higher-order relationships between nodes. Additionally, we leverage Fast Kolmogorov-Arnold Networks (FastKAN) to predict the synergistic effects of drug combinations, thereby improving both the efficiency and accuracy of the predictions.Extensive experiments demonstrate that Hypergraph-Encoder outperforms existing methods, achieving promising results in predicting synergistic effects of anticancer drug combinations.

Molecular Property Prediction (MPP) plays a crucial role in the drug discovery process. Despite numerous advancements of deep learning in this field, identifying the unknown properties of molecules remains quite challenging due to the scarcity of labeled data and the imbalance in class distribution. Furthermore, many existing methods emphasize atom-level information transfer and overlook crucial data conveyed by molecular bonds and their interrelationships. This neglect results in insufficient attention being paid to the key sub-structures within molecules, such as pharmacophores and toxophores.We propose a novel framework, Meta-GraphKAN, which combines Kolmogorov-Arnold Networks (KAN) and Graph Neural Networks (GNNs) within the meta-learning framework to address these issues. Specifically, we utilize structure reconfiguration in which "bonds" are converted into nodes and "bond-atom-bond" interactions are transformed into edges to better partition the bonds. Moreover, to capture information about the molecular structure from different perspectives, we encode the original graph and the reconfigured graph using the GraphKAN network to generate molecular embeddings. We then adopt a graph contrastive learning strategy to train on both the original and structurally reconfigured molecular graphs, resulting in the final molecular representation. Our extensive experiments validate the efficacy of the proposed method, and our method achieves state-of-the-art performance on three public datasets.

Aspect Sentiment Triplet Extraction (ASTE) aims to identify aspect terms, opinion terms, and their associated sentiment polarity, playing a vital role in fine-grained sentiment analysis.Despite recent advances, existing methods struggle with modeling long-range dependencies and directional semantic flows, largely due to the isotropic limitations of traditional graph convolutional networks.To address these issues, we propose a Multi-Directional Contextual Graph Convolutional Network (MDC-GCN).Our model incorporates a dynamic position fusion module that leverages deformable convolution and a position-gated mechanism to encode contextual positional information.Multi-directional graph convolution layers capture semantic flows from various directions, while a ConvAdditive Sentiment Attention mechanism models both positional dependencies and sentiment-aware semantics through hierarchical constraints and semantic calibration.Experiments on four benchmark datasets show that MDC-GCN consistently outperforms strong baselines, demonstrating its effectiveness and robustness.

Prediction of disease-drug interactions(DDIs) plays a vital role in drug development in various areas, such as precision medicine, drug development and overcoming the issue of drug resistance. Despite continuous advancements in methods for predicting disease-drug interactions(DDIs) and the achievement of promising results, current approaches are still limited by issues related to the homogeneity of data and the consistency of vector representations. Firstly, DDI prediction should consider a variety of heterogeneous relationships, such as drug-protein associations and drug-induced side effects in patients. These diverse relationships can help uncover potential associations between diseases and drugs. Secondly, neglecting the issue of inconsistency in vector representations within heterogeneous network embeddings may affect the accuracy of capturing relationships and similarities between entities. Here, we develop KGE GCLR, a framework for DDIs prediction by combining knowledge graph(KG) and graph contrastive learning for recommendation system. This framework firstly learns a low-dimensional representation for various entities in the KG, and then under the paradigm of graph contrastive learning provided to integrate heterogeneous auxiliary information into the recommendation system(GCLR). The KGE GCLR was evaluated in realistic scenarios, and achieved accurate and robust predictions on two benchmark datasets. Our results indicate that the KGE GCLR, by addressing the inconsistency challenges in embedding heterogeneous networks, provides valuable insights for integrating knowledge graph data and recommendation system-based techniques into a framework, thereby enhancing the predictive capabilities for disease-drug association discovery.

Aspect-based Sentiment Triplet Extraction (ASTE) is an emerging research area in sentiment analysis, which aims to identify aspect terms and their corresponding sentiment polarity and opinion terms in sentences. Previous studies have tried to use graph neural networks on dependency trees to handle ASTE tasks through pipelines or end-to-end approaches, but these methods have limitations and do not effectively combine semantic and syntactic information as well as various features in span markers.To address these issues, we propose a new solution called Enhanced Syntax and Semantics Dual-Branch Graph Convolutional Network (ESSDB-GCN), which can better integrate syntactic and semantic information. Specifically, we first designed a syntactic dependency enhancement channel to enhance syntactic features, and optimized syntactic information by treating the syntactic dependency probability matrix as a graph structure. Next, we designed a semantic channel with a self-attention mechanism to enhance semantic information and proposed orthogonal and differential regularizers to strengthen semantic relevance. Lastly, we explored span-level information and constraints to solve the problem of emotion word tagging, in order to generate more accurate aspect-based sentiment triplets. Our proposed ESSDB-GCN demonstrates strong performance on multiple benchmark datasets, proving the effectiveness of our method.

The new Versatile Video Coding Standard (VVC) was finalized in July 2020. This new international standard is able to provide a higher compression efficiency by up to 50% for the same subjective quality compared to its predecessor HEVC but at the cost of an increased computational load. This paper investigates the complexity of VVC decoder processing blocks and presents a highly optimized decoder implementation that can achieve 4K 60fps VVC real-time decoding on an x86 based CPU using SIMD instruction extensions of the processor and additional parallel processing including data and task-level parallelism.

Considering that the attacks against the industrial control system are mostly organized and premeditated actions, IP traceback is significant for the security of the industrial control system. Based on the infrastructure of the internet, we have developed a novel malicious IP traceback model, ICSTrace, without deploying any new services. The model extracts the function codes and their parameters from the attack data according to the format of the industrial control protocol and employs a short sequence probability method to transform the function codes and their parameters into a vector, which characterizes the attack pattern of malicious IP addresses. Furthermore, a partial seeded K-means algorithm is proposed for the pattern’s clustering, which helps in tracing the attacks back to an organization. ICSTrace is evaluated based on the attack data captured by the large-scale deployed honeypots for the industrial control system, and the results demonstrate that ICSTrace is effective on malicious IP traceback in the industrial control system.

In the screen content coding extension for HEVC, intra block copy (IBC) was adopted to explore the redundancy between reduplicated patterns, which often occurs in a picture with screen contents. Besides reduplication, symmetry is also often observed in screen-content and even in natural pictures. In this paper, symmetric intra block copy (SIBC) is therefore proposed to further improve IBC. By flipping the reference block of IBC horizontally or vertically, SIBC may provide better predictions than IBC for symmetric patterns. Experimental results show that SIBC can achieve 1.2% and 1.9% coding gains in all intra configurations on sequences in the category of YUV, text & graphics with motion, 1080p for lossy and lossless coding respectively.

The exponential growth of surveillance videos presents an unprecedented challenge for high-efficiency surveillance video coding technology. Compared with the existing coding standards that were basically developed for generic videos, surveillance video coding should be designed to make the best use of the special characteristics of surveillance videos (e.g., relative static background). To do so, this paper first conducts two analyses on how to improve the background and foreground prediction efficiencies in surveillance video coding. Following the analysis results, we propose a background-modeling-based adaptive prediction (BMAP) method. In this method, all blocks to be encoded are firstly classified into three categories. Then, according to the category of each block, two novel inter predictions are selectively utilized, namely, the background reference prediction (BRP) that uses the background modeled from the original input frames as the long-term reference and the background difference prediction (BDP) that predicts the current data in the background difference domain. For background blocks, the BRP can effectively improve the prediction efficiency using the higher quality background as the reference; whereas for foreground-background-hybrid blocks, the BDP can provide a better reference after subtracting its background pixels. Experimental results show that the BMAP can achieve at least twice the compression ratio on surveillance videos as AVC (MPEG-4 Advanced Video Coding) high profile, yet with a slightly additional encoding complexity. Moreover, for the foreground coding performance, which is crucial to the subjective quality of moving objects in surveillance videos, BMAP also obtains remarkable gains over several state-of-the-art methods.

For the real-time and low-delay video surveillance and teleconferencing applications, the newly video coding standard HEVC can achieve much higher coding efficiency over H.264/AVC. However, we still argue that the hierarchical prediction structure in the HEVC low-delay encoder still does not fully utilize the special characteristics of surveillance and conference videos that are usually captured by stationary cameras. In this case, the background picture (G-picture), which is modeled from the original input frames, can be used to further improve the HEVC low-delay coding efficiency meanwhile reducing the complexity. Therefore, we propose an optimization method for the hierarchical prediction and coding in HEVC for these videos with background modeling. First, several experimental and theoretical analyses are conducted on how to utilize the G-picture to optimize the hierarchical prediction structure and hierarchical quantization. Following these results, we propose to encode the G-picture as the long-term reference frame to improve the background prediction, and then present a G-picture-based bit-allocation algorithm to increase the coding efficiency. Meanwhile, according to the proportions of background and foreground pixels in coding units (CUs), an adaptive speed-up algorithm is developed to classify each CU into different categories and then adopt different speed-up strategies to reduce the encoding complexity. To evaluate the performance, extensive experiments are performed on the HEVC test model. Results show our method can averagely save 39.09% bits and reduce the encoding complexity by 43.63% on surveillance videos, whereas those are 5.27% and 43.68% on conference videos.

Summary form only given. Recently, a low-delay and high-efficiency hierarchical prediction structure (HPS) has been proposed for the forthcoming HEVC. Actually, frames and coding units (CUs) at different HPS positions have different importance to predict following frames and CUs. This paper firstly analyzes what frames and CUs should be quantified less. Based on the analysis, we propose a Hierarchical-and-Adaptive BIT-allocation method with Selective background prediction (HABITS) to optimize the video performance of HEVC. Extensive experiments on HM8.0 show that, HABITS saves 13.3% and 35.5% of the total bit rate for eight HEVC conference videos and eight common used surveillance videos. Even for the normal videos in HEVC's Class B and C, there is still 2.2% bit-saving.

Among the multiple application-oriented video groups of IEEE 1857 video part, surveillance groups are the first specific video coding standards targeting on the exploring surveillance system. In this paper, we firstly present an overview of the technical features and characteristics of the Surveillance Baseline and Surveillance Groups. The video coding technologies are then described in greater detail on three main directions, including the background modeling based prediction techniques for high-efficiency surveillance video coding, error resilience methods for channel-noisy surveillance video transmission and the high-level syntax for surveillance video analysis. The surveillance groups can provide a good support for kinds of video analysis applications of computer vision and make the video transmission more applicable for noisy channels. Moreover, experimental results show that the background modeling based prediction techniques can well exploit the special characteristics of surveillance video and double the traditional compression performance.

In the recent video coding standards, the selection of Lagrange multiplier is crucial to achieve trade-off between the choices of low-distortion and low-bitrate prediction modes. For surveillance video coding, the rate-distortion analysis shows that, a larger Lagrange multiplier should be used if the background in a coding unit took a larger proportion. Therefore, a modified Lagrange multiplier might be better for rate-distortion optimization. To address this problem, we perform an in-depth analysis on the relationship between the optimal Lagrange multiplier and the background proportion, and then propose a Lagrange multiplier selection model to obtain the optimal coding performance for surveillance videos. Following this, we further develop a Lagrange multiplier optimized video coding method. Experimental results show that our coding method can averagely achieve 18.07% bitrate saving on CIF sequences and 11.88% on SD sequences against the background-irrelevant Lagrange multiplier selection method.

To save the storage and transmission cost, it is applicable now to develop fast and efficient methods to transcode the perennial surveillance videos to HEVC ones, since HEVC has doubled the compression ratio. Considering the long-time static background characteristic of surveillance videos, this paper presents a coding unit (CU) classification based AVC-to-HEVC transcoding method with background modeling. In our method, the background frame modeled from originally decoded frames is firstly transcoded into HEVC stream as long-term reference to enhance the prediction efficiency. Afterwards, a CU classification algorithm which employs decoded motion vectors and the modeled background frame as input is proposed to divide the decoded data into background, foreground and hybrid CUs. Following this, different transcoding strategies of CU partition termination, prediction unit candidate selection and motion estimation simplification are adopted for different CU categories to reduce the complexity. Experimental results show our method can achieve 45% bit saving and 50% complexity reduction against traditional AVC-to-HEVC transcoding.

It is in urgent need to develop fast and efficient transcoding methods so as to remarkably save the storage of surveillance videos and synchronously transmit conference videos over different bandwidths. Towards this end, the special characteristics of these videos, e.g., the relatively static background, should be utilized for transcoding. Therefore, we propose a fast and efficient transcoding method (FET) based on background modeling and block classification in this paper. To improve the transcoding efficiency, FET adds the background picture, which is modeled from the originally decoded frames in low complexity, into stream in the form of an intra-coded G-picture. And then, FET utilizes the reconstructed G-picture as the long-term reference frame to transcode the following frames. This is mainly because our theoretical analyses show that G-picture can significantly improve the transcoding performance. To reduce the complexity, FET utilizes an adaptive threshold updating model for block classification and then adopts different transcoding strategies for different categories. This is due to the following statistics: after dividing blocks into categories of foreground, background and hybrid ones, different block categories have different distributions of prediction modes, motion vectors and reference frames. Extensive experiments on transcoding high-bit-rate H.264/AVC streams to low-bit-rate ones are carried out to evaluate our FET. Over the traditional full-decoding-and-full-encoding methods, FET can save more than 35% of the transcoding bit-rate with a speed-up ratio of larger than 10 on the surveillance videos. On the conference videos which should be transcoded more timely, FET achieves more than 20 times speed-up ratio with 0.2 dB gain.

With the proliferation of moving surveillance cameras, how to effectively compress videos captured from them is becoming more and more important. One significant characteristic is that, these cameras always go and return cyclically within a limited area. Thus we propose to dynamically build up a background frame for each input frame from a generated panorama background and employ it for a background frame based motion compensation to improve the coding efficiency. For the background reconstruction procedure, we firstly extract limited number of feature point pairs between the robustly searched area in the decoded panorama and the current frame. Afterwards, the global motion transformation matrix is obtained to rectify the searched area into a projective plane of the current frame, and then the reconstructed background is produced. Experiments on six in-door and out-door surveillance videos show that, the background reconstruction based coding method achieves significant performance gain.

Low-complexity and high-performance surveillance video Transcoding methods play an important role for a wide range of surveillance video transmission and storage applications. Towards this end, the special characteristics of surveillance video should be utilized for Transcoding. In this paper, we propose a fast and performance-maintained Transcoding method. This method firstly divides macro blocks (MBs) into foreground MBs, foreground border MBs and background MBs. Statistics show that the three categories have different distributions of prediction modes, motion vectors and reference frames. Following this, we adopt different Transco ding strategies in terms of removing the redundant prediction modes, narrowing motion search range and reducing reference frames. In particular, we propose an algorithm to exploit the decoded motion vector to adaptively calculate motion search range. Experimental results show that, compared with the recent background modeling based full-decoding-full-encoding, our Transcoding method saves more than 93% time with ignorable quality loss.

Utilizing the special properties to improve the surveillance video coding efficiency still has much room, although there have been three typical paradigms of methods: object-oriented, background-prediction-based and background-difference-based methods. However, due to the inaccurate foreground segmentation, the low-quality or unclear background frame, and the potential "foreground pollution" phenomenon, there is still much room for improvement. To address this problem, this paper proposes a macro-block-level selective background difference coding method (MSBDC). MSBDC selects the following two ways to encode each macro-block (MB): coding the original MB, and directly coding the difference data between the MB and its corresponding background. MSBDC also features at employs the classification of MBs to facilitate the selection, through which, prediction and motion compensation turns more accurate, both on foreground and background. Results show that, MSBDC significantly decreases the total bitrate and obtains a remarkable performance gain on foreground compared with several state-of-the-art methods.

Background modeling is an important pre-processing step for object detection in surveillance video analysis systems. Recently, it has been proved to be useful for high-efficiency surveillance video coding. In existing works, the modeling background frame often needs to be high-quality encoded so as to achieve a large bit-rate saving. However, the high-quality background frame requires lots of bits in the code stream, so it is infeasible to update the background frame too frequently. Therefore, a better bit-allocation method is desirable to facilitate in-time background updating and bit-saving background coding. In this paper, we firstly build up a background updating model from a detailed analysis of results on surveillance video. Following this, we propose a bit-saving and quality-maintaining background frame coding method. In our method, the background frame can be updated more timely, consequently leading to the better coding efficiency. Experimental results show that our method can achieve more than 15% bit-rate decrease compared with three state-of-art methods.

Recently, background modeling (shortly BgModeling) plays a more and more important role in high-efficiency surveillance video coding. Meanwhile, many practical video coding applications also present some specific requirements for BgModeling, such as the low memory cost and low computational complexity. However, existing BgModeling methods are mostly designed for video content analysis such as object detection. Thus they may be not directly applicable for video coding. In this paper, we firstly present an analysis for the features of BgModeling in surveillance video coding and make a comparison of the performances of existing BgModeling methods. Then we propose a segment-and-weight based running average (SWRA) method for surveillance video coding. SWRA firstly divides pixels at each position in the training frames into several temporal segments, and then calculate their corresponding mean values and weights. After that, a running and weighted average procedure is used to reduce the influence of foreground pixels and finally obtain the modeling results. Experimental results show that, the SWRA-based encoder achieves the best performance over several state-of-the-art methods, with much less cost of memory and modeling time.

Real-world video surveillance applications require storing videos without neglecting any part of scenarios for weeks or months. To reduce the storage cost, the high bit-rate videos from cameras should be transcoded into a more efficient compressed format with as little quality loss as possible. In this paper, we propose a background model based method to improve the transcoding efficiency for surveillance videos captured by stationary cameras, and objectively measure it. The background model is trained by pre-decoded I frames, and then used to transcode the source stream. Following this method, an H.264/AVC based transcoder employing the background model as long-term reference frame and a difference frame coding based transcoder are implemented and evaluated. Experimental results show that both trancoders save nearly half the used bits while maintaining quality compared with the full-decoding-full-encoding method, and the latter one has slightly better performance.

In this paper, a new scheme is presented to improve the coding efficiency of sequences captured by stationary cameras (or namely, static cameras) for video surveillance applications. We introduce two novel kinds of frames (namely background frame and difference frame) for input frames to represent the foreground/background without object detection, tracking or segmentation. The background frame is built using a background modeling procedure and periodically updated while encoding. The difference frame is calculated using the input frame and the background frame. A sequence structure is proposed to generate high quality background frames and efficiently code difference frames without delay, and then surveillance videos can be easily compressed by encoding the background frames and difference frames in a traditional manner. In practice, the H.264/AVC encoder JM 16.0 is employed as a build-in coding module to encode those frames. Experimental results on eight in-door and out-door surveillance videos show that the proposed scheme achieves 0.12 dB~1.53 dB gain in PSNR over the JM 16.0 anchor specially configured for surveillance videos.