Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of documents. While large language models (LLMs) have preliminarily achieved promising performance in part of these tasks individually, their capability in event analysis still lacks comprehensive understanding due to restricted document granularity, task designs, and data source of existing benchmarks. To address these limitations, we introduce MiGUE-Bench, a systematic benchmark for assessing the performance of LLMs in multi-granularity event analysis. To support large-scale evaluation, we first develop an LLM-driven self-correcting annotation framework called MiGUE-Pipeline, enabling scalable acquisition of high-quality source data of events with automatic labels. Then, we design four core tasks in our benchmark, i.e., event detection, relation reasoning, structure induction, and future prediction, to probe model competence at different levels, from atomic event details to complex cross-document narratives. Extensive experiments on state-of-the-art LLMs and retrieval-augmented generation (RAG) methods delineate the current capability boundary and identify critical deficiencies, providing insights into the future improvement of LLMs in challenging event analysis tasks.

A graph G is many-to-many t -disjoint path coverable if, for any two disjoint vertex subsets X = { x 1 , x 2 , … , x t } and Y = { y 1 , y 2 , … , y t } of V ( G ) , there exist t -disjoint paths such that each path connects x i and y τ ( i ) for some permutation τ of { 1 , 2 , … , t } and the union of these paths covers every vertex of G . By modifying the sets X and Y to X = { x } and Y = { y 1 , y 2 , … , y t } or X = { x } and Y = { y } , we can obtain the definitions of one-to-many t-disjoint path coverable and one-to-one t -disjoint path coverable , respectively. In this article, we obtain sufficient degree sum conditions on vertices at distance 2 for a graph to be one-to-one, one-to-many and many-to-many t -disjoint path coverable. Moreover, the bounds on the degree sums and the results obtained are all best possible. Our results also imply related results on Ore-type degree conditions.

Underwater imaging always suffers from color distortion and reduced visibility due to light absorption and scattering, severely hindering visual perception and analysis. In this letter, we propose an underwater image enhancement framework based on diffusion model augmented with two lightweight guidance modules. The first module is a conditional branch that extracts structural features from a coarsely enhanced version to guide the denoising process toward more faithful restoration. While the second module retrieves high-quality features from a pre-constructed feature dictionary as priors, effectively restoring colors and fine details in degraded regions. Extensive experiments on public underwater image datasets demonstrate that our proposed method outperforms the state-of-the-art approaches both quantitatively and visually. It also generalizes well across various underwater environments, highlighting the effectiveness of incorporating structural and feature-level guidance into the diffusion process. The source code and pre-trained model are available at https://github.com/Juneit/PGUIE.

Text generation for social network debates aims to generate clear and logical dialogue texts based on a correct understanding of the context. This task involves context sentiment analysis and providing factual information to support statements that align with the predetermined stance, while refuting viewpoints from opposing stances. This has significant application value in the era of We-Media. For instance, opinion leaders or influencers on social networks offer examples or advice to others based on their own views and statements. However, their opinions may contain errors or biases, potentially leading to widespread behavioral or opinion misguidance. To mitigate such misguidance, it is necessary to use artificial intelligence technology to intelligently generate rebuttal arguments. To this end, this paper proposes a debate text generation model based on sentiment analysis, aimed at generating rebuttal and corrective debate texts. A sentiment analysis module is introduced to make fine-grained sentiment judgments on the text, while a knowledge enhancement module is used to improve the model’s commonsense reasoning ability, ultimately generating debate texts. Experimental results on the dataset show that the proposed model performs better than the baseline methods in the task of debate text generation.

Object detection in remote sensing images (RSIs) plays an important role both in civil and military fields. Currently, many object detection algorithms in RSIs have shown the excellent capability. However, these methods are designed for the single RGB modality, which cannot cope with the challenges in insufficient illumination or foggy scenarios. Infrared images measure the temperature of the captured objects, and it can avoid the influence of low illumination and fog. In this paper, we propose a novel RGB-Infrared multi-modal remote sensing object detection method termed as RIFuse to address these challenges. RIFuse combines convolutional neural networks (CNNs) and Transformer in a parallel hierarchy, which can efficiently extract the local features of RGB images and the global representations of infrared images. Besides, an adaptive multi-modal feature fusion block (MFF block) is proposed to fuse the features from both branches comprehensively. Extensive experiments demonstrate the superiority of our method for multi-modal object detection on RSIs.

Radio frequency fingerprint (RFF) identification is an emerging physical layer security technique, which provokes many promising applications in the internet of things (IoT). However, traditional machine learning-based RFF identification methods rely on complex manual feature extraction, while it is difficult for methods based on deep learning to deal with RFF identification under different channel environments. To solve these problems, we propose three different transfer learning-based RFF identification methods based on ConvMixer network, which is a mixture of different convolutional layers, using pre-trained model in the previous channel environment to assist in training under the new channel environment. Experimental results show that, compared with the previous retraining method, our proposed method reduces the number of training parameters and improves the identification performance at low SNR. Moreover, the proposed method can still have a certain performance guarantee with less training data.

This paper presents the analysis and intelligent prediction for the displacement of stratum and tunnel lining of Qingdao Metro Line 4 by earth pressure balance (EPB) shield tunnel excavation in complex strata. When the tunnel is excavated in different stratum sections, the tunneling parameters of shield machine are systematically analyzed and compared, and the vertical displacement of the tunnel crown and the horizontal convergence deformation on both sides are investigated. When the tunnel body passes through the soft soil stratum and rock stratum, the curves of the vertical displacement of the stratum surface with time are respectively discussed. A machine learning method for predicting stratum surface deformation induced by shield tunnel excavation in complex strata is developed, where extreme learning machine (ELM), particle swarm optimization (PSO) algorithm and$k$-fold cross-validation method are comprehensively considered. 65 data samples are collected from the field monitoring data of Qingdao Metro Line 4 and each data sample includes seven input values and one output value. The developed PSO-ELM has good prediction performance for stratum surface vertical displacement due to shield tunnel excavation. The case study in this work can provide a practical reference for similar tunneling projects.

A block-level perceptual image compression framework is proposed in this work, including a block-level just noticeable difference (JND) prediction model and a preprocessing scheme. Specifically speaking, block-level JND values are first deduced by utilizing the OTSU method based on the variation of block-level structural similarity values between two adjacent picture-level JND values in the MCL-JCI dataset. After the JND value for each image block is generated, a convolutional neural network–based prediction model is designed to forecast block-level JND values for a given target image. Then, a preprocessing scheme is devised to modify the discrete cosine transform coefficients during JPEG compression on the basis of the distribution of block-level JND values of the target test image. Finally, the test image is compressed by the max JND value across all of its image blocks in the light of the initial quality factor setting. The experimental results demonstrate that the proposed block-level perceptual image compression method is able to achieve 16.75% bit saving as compared to the state-of-the-art method with similar subjective quality. The project page can be found at https://mic.tongji.edu.cn/43/3f/c9778a148287/page.htm.

Perceptual video coding (PVC) is able to improve video compression efficiency by employing just noticeable distortion (JND) models. However, there are limitations of conventional JND models on simulating complex human visual system. To address this issue, a novel PVC framework is proposed in this work, in which a JND model based on staircase perceptual characteristics is designed to calculate block-level JND (BLJND) levels and a convolutional neural network based predictive model is developed to predict BLJND levels for video coding. Experimental results demonstrate that the proposed PVC framework is effective and robust in terms of video compression efficiency and subjective video quality.

The expanding social network and multimedia technologies encourage more and more people to store and transmit information in visual format, such as image and video. However, the cost of this convenience brings about a shock to traditional video severs and exposes them under the risk of overloading. In the huge volume of online videos, there are a large amount of near-duplicate videos (NDVs). Although quite a number of research work have been proposed to detect NDVs, little research effort is made to compress these NDVs in a more effective manner than independent video compression. In this study, we make an in-depth exploration of the data redundancy of NDVs and propose a video analysis and coding framework to jointly compress NDVs. In order to employ the proposed NDV analysis and coding framework, a graph-based similar video grouping method and a number of preprocessing functions are designed to explore the correlation of visual information among NDVs and thus suit the requirement of joint video coding. Experimental results verify that the proposed NDV analysis and coding framework is able to effectively compress NDVs and thus save video data storage.

With the increasing popularity of social network, more and more people tend to store and transmit information in visual format, such as image and video. However, the cost of this convenience brings about a shock to traditional video servers and expose them under the risk of overloading. Among the huge amount of online videos, there are quite a number of Near-Duplicate Videos (NDVs). Although many works have been proposed to detect NDVs, few researches are investigated to compress these NDVs in a more effective way than independent compression. In this work, we utilize the data redundancy of NDVs and propose a video coding method to jointly compress NDVs. In order to employ the proposed video coding method, a number of pre-processing functions are designed to explore the correlation of visual information among NDVs and to suit the video coding requirements. Experimental results verify that the proposed video coding method is able to effectively compress NDVs and thus save video data storage.

This paper proposes a memory binary particle swarm optimization algorithm (MBPSO) based on a new updating strategy. Unlike the traditional binary PSO, which updates the binary bits of a particle ignoring their previous status, MBPSO memorizes the bit status and updates them according to a new defined velocity. As such, precious historical information could be retained to guide the search. The velocity vector of MBPSO is designed as a probability for deciding whether the particle bits change or not. The proposed algorithm is tested on four discrete benchmark functions. The experimental results reported over 100 runs show that MBPSO is capable of obtaining encouraging performance in discrete optimization problems.

Root and Varaiya proved the existence of a code that can communicate reliably over any linear Gaussian channel for which the channel mutual information level exceeds the transmitted rate. This paper provides several examples of scalar (single-input single-output) fading channels and shows that on these channels the performance of low-density parity-check (LDPC) codes lies in close proximity to the performance limits identified by Root and Varaiya. Specifically, we consider periodic fading channels and partial-band jamming (PBJ) channels. A special case of periodic fading is the variation of signal-to-noise ratio across orthogonal frequency division modulation subchannels. The robustness of LDPC codes to periodic fading and PBJ across parameterizations of these different channels is demonstrated through the consistency of the required mutual information to provide a specified bit error rate. For the periodic fading case, the Gaussian approximation to density evolution has been adapted such that asymptotic threshold measures can be compared to simulated code performance in various periodic fading scenarios

Rate-compatible coding is appropriate for communication systems that experience a range of operating SNRs but seek to adhere to a single underlying codec structure. This paper constructs rate-compatible low-density parity-check (LDPC) codes by carefully selecting degree distributions, followed by a combination of information nulling and parity puncturing. Techniques that suppress error floors are included as part of the construction methodology.

This letter explains the effect of graph connectivity on error-floor performance of low-density parity-check (LDPC) codes under message-passing decoding. A new metric, called extrinsic message degree (EMD), measures cycle connectivity in bipartite graphs of LDPC codes. Using an easily computed estimate of EMD, we propose a Viterbi-like algorithm that selectively avoids small cycle clusters that are isolated from the rest of the graph. This algorithm is different from conventional girth conditioning by emphasizing the connectivity as well as the length of cycles. The algorithm yields codes with error floors that are orders of magnitude below those of random codes with very small degradation in capacity-approaching capability.

Summary form only given. The problem of compressing correlated binary sources when the correlation between sources is defined by a hidden Markov model (HMM) was considered. Specifically, the HMM describes the correlation pattern such as the modulo-2 addition of the two sources. A density evolution analysis of a compression system was developed using irregular LDPC codes as source codes. To achieve this goal, the standard density evolution approach was modified to incorporate the HMM. It was then applied to the design of irregular codes to optimize system performance. The key to the incorporation of HMM in density evolution is to find the input-output characteristic of the forward-backward (F-B) decoding algorithm. The output of the F-B block subtitles the a priori message in the traditional density evolution case. Theoretical results agree with the simulations and show that it is possible to achieve a performance loss close to the theoretical Slepian-Wolf limit.

This work explains the relationship between cycles, stopping sets, and dependent columns of the parity check matrix of low-density parity-check (LDPC) codes. Furthermore, it discusses how these structures limit LDPC code performance under belief propagation decoding. A new metric called extrinsic message degree (EMD) measures cycle connectivity in bipartite graph. Using an easily computed estimate of EMD, we propose a Viterbi-like algorithm that selectively avoids cycles and increases stopping set size. This algorithm yields codes with error floors that are orders of magnitude below those of girth-conditional codes.

Root and Variya (1968) proved the existence of codes that can communicate reliably over any member of a set of linear Gaussian channels where each member exceeds a given amount of mutual information. In this paper we show that LDPC codes are such codes and that their performance lies within 0.1 bits of the Root and Variya capacity for a large family of periodic Gaussian channels. specifically, the robustness of LDPC codes to periodic fading is demonstrated through the consistency of their mutual information performance across period-2 and period-256 fading profiles. The latter case implies that these codes are ideal candidates for coding in OFDM.

To achieve more efficient usage of channel bandwidth and provide better protection for the media payload transmitted over lossy packet-switched networks, we introduce a new scheme of generic uneven level protection (ULP) forward error correction. The scheme provides different protection levels for data of different significance within a packet. The ULP scheme is designed to be independent from the nature of the media that it protects, and it is very flexible for any protection configuration the user might need without using any out-of-band signaling. Simulation using a video stream transmitted over a lossy packet-switched network shows that the ULP algorithm achieves significant gain for the quality of the transmission over a wide range of network conditions.

By constructing a model which takes into account the frame dependence of multimedia streams, we analyze the performance of different packet dropping mechanisms and find that scalable video combined with the priority dropping mechanism can bring higher throughput, lower delay and lower delay jitter. We also find the optimum system parameters for multimedia transmission. This study is important for achieving better performance for video transmission over IP networks.