Digital images serve as the fundamental carrier for information exchange within multimedia ecosystems. However, the ubiquitous practice of screen recapturing often introduces complex moiré patterns due to spectral aliasing, which severely degrades the visual quality and impedes downstream multimedia analysis tasks. In this paper, we propose MoiréNet, a compact convolutional neural framework designed for effective moiré removal, thereby synergistically restoring high-fidelity content. To address the anisotropic and multi-scale nature of these artifacts, we introduce two novel modules: the Directional Frequency-Spatial Encoder (DFSE), which explicitly discerns moiré orientation via directional difference convolutions, and the Frequency-Spatial Adaptive Selector (FSAS), which enables feature-adaptive artifact suppression across dual domains. Extensive experiments demonstrate that MoiréNet achieves state-of-the-art performance on public and widely used datasets while being highly parameter-efficient. With only 5.513M parameters, representing a 48% reduction compared to ESDNet-L, MoiréNet combines superior restoration quality with parameter efficiency for storage-constrained multimedia applications.

Monochrome Near-Infrared (NIR) surveillance is widely used for low-light monitoring, yet pixel-level smoke segmentation remains underexplored due to scarce annotated data and strong appearance ambiguity. We introduce NIR-Smoke, a monochrome NIR smoke segmentation benchmark containing real frame-wise annotations and synthetic composites, and provide TrinitySeg as a strong baseline. Specifically, TrinitySeg integrates three complementary cues by capturing motion via lightweight frame differences, structure via multi-scale deep supervision with an auxiliary boundary head, and frequency via a compact Fourier-domain filtering module. We further study synthetic-to-real mixing for training. On NIR-Smoke, TrinitySeg achieves 85.64 ± 0.10 mIoU and 72.57 ± 0.21 Smoke IoU, outperforming representative baselines while retaining near-baseline inference cost.

As part of modern research practices, the FAIR data principles have become essential for data discoverability, usability, and sharing.Existing implementations for automatically assessing FAIR adherence (FAIRness) often suffer from limited usability, inconsistent accuracy, and difficult-to-interpret results, as they require explicit rules to cover for specific FAIR assessment frameworks, which are not easy to generalize.This paper introduces Fair-Way, an open source tool that leverages Large Language Models (LLMs) to automate FAIRness assessment.Fair-Way applies a divide-and-conquer approach to decompose the assessment process into fine-grained tasks, as well as to split the metadata into manageable chunks.Evaluation demonstrates that Fair-Way achieves performance comparable to existing tools, while outperforming them in several key metrics.Moreover, Fair-Way generalizes across FAIR assessment indicators without requiring explicitly programmed logic and supports both structured and unstructured metadata in diverse formats.Finally, it enables user-defined, domain-specific tests, which are typically not supported by other systems.Overall, Fair-Way represents a scalable and flexible solution to accelerate FAIR data practices across research domains.

Automatic Question Generation (AQG) aims to generate valid, coherent questions based on given text passages in pre-trained language models. While AQG has been a significant area of retrieval augmentation and agent-based systems, current QG models face limitations, especially with sequential models like Transformer, which struggle with modeling complex logical structures and limited question coherence and depth. This paper proposes Q-Chain, a framework designed to optimize logic and educational values. Q-Chain features: (1)Differentiable logic layers in GMP model conditional dependencies and counterfactuals, ensuring logical rigor. (2) Bloom's taxonomy-guided gating adjusts question difficulty to align with pedagogical goals. (3) Direct generation of logic-structured question graphs enhanced by counterfactual training. Experimental results show Q-Chain outperforms GPT-3.5, T5, and BART on the MedQuAD dataset (0.82 vs 0.80 vs 0.72 and 0.74 F1-score) and shows superior robustness to noisy inputs, achieving a 4.1/5 human rating on counterfactual questions, 40% better than BART.

Yawning detection is actively used in multimedia applications such as driver fatigue assessment and status monitoring. However, the accuracy and robustness of existing yawning detectors are limited due to variations in environments (especially lights), facial expressions, and confusion behaviours (e.g., talking and eating). This paper introduces a transformer-based method, YawnNet, for accurate yawning detection by leveraging spatial-temporal encoding and local cues. In particular, YawnNet contains a data processing stage with temporal downsampling and cube embedding on the input sequence. Moreover, it includes a Swin-Transformer block that operates on fine-grained patches to uncover short-range local cues. Through comprehensive experiments, we demonstrate the advantages of YawnNet: (1) significantly higher accuracy than the state-of-the-art Dense-LSTM (precision and recall increased by 2.3% and 4.2%, respectively) on the FatigueView dataset, (2) close to real-time (30 FPS on RTX 3090), and (3) a marked improvement in robustness on confusion behaviours, invariance (resolution and orientation) and complex scenarios (occlusion, over- and underexpose).

Recent advancements in skeleton extraction have significantly improved the process by simplifying the skeleton regression task into graph component detection. Despite the advancements in skeleton topology, accuracy in detailing skeletal parts remains challenging, with specific issues such as jagged edges in high-resolution images. This paper identifies the limitations of current detection models that can adapt during the decomposition and reconstruction phases, which impacts the overall precision of the extraction. In response, we propose an approach that revises the primary focus of the detection tasks. Inspired by the success of pixel-wise binary classification methods, we propose a gradual transition in focus from a coordinate localization regression task to a classification task of predicting points during the training process. This transition can be achieved by adjusting the number of object queries in the Transformer model. Theoretical and experimental evaluations validate the effectiveness of our approach. Our method yields significant improvements in performance over the baseline across various shape and image datasets (e.g., 0.836 vs. 0.826 for BlumNet on the SK1491 dataset).

Since Bitcoin first appeared on the scene in 2009, cryptocurrencies have become a worldwide phenomenon as important decentralized financial assets. Their decentralized nature, however, leads to notable volatility against traditional fiat currencies, making the task of accurately forecasting the crypto-fiat exchange rate complex. In this study, we examine the various independent factors that affect the Bitcoin-Dollar exchange rate's volatility. To this end, we propose CoMForE, a multimodal AdaBoost-LSTM ensemble model, which not only utilizes historical trading data but also incorporates public sentiments from related tweets, public interest demonstrated by search volumes, and blockchain hash-rate data. Our developed model goes a step further by predicting fluctuations in the overall cryptocurrency value distribution, thus increasing its value for investment decision-making. We have subjected this method to extensive testing via comprehensive experiments, thereby validating the importance of multimodal combination over exclusive reliance on trading data. Further experiments show that our method significantly surpasses existing forecasting tools and methodologies, demonstrating a 19.29% improvement. This result underscores the influence of external independent factors on cryptocurrency volatility.

Automatic processing of bibliographic data becomes very important in digital libraries, data science and machine learning due to its importance in keeping pace with the significant increase of published papers every year from one side and to the inherent challenges from the other side. This processing has several aspects including but not limited to I) Automatic extraction of references from PDF documents, II) Building an accurate citation graph, III) Author name disambiguation, etc. Bibliographic data is heterogeneous by nature and occurs in both structured (e.g. citation graph) and unstructured (e.g. publications) formats. Therefore, it requires data science and machine learning techniques to be processed and analysed. Here we introduce BiblioDAP'21: The 1st Workshop on Bibliographic Data Analysis and Processing.

Depth estimation is a method to estimate the depth information in a 2D image/video, where the original 3D space is projected onto an image plane. This paper introduces a novel extension of depth estimation in the video domain, where we extract 3D trajectories which individually represent the transition of an object in the 3D space. Such 3D trajectories are useful for appropriately characterising spatio-temporal object relations for video event detection. While we extract 3D trajectories by combining depth estimation and object detection results, the major problem is the inconsistency between these results. For example, significantly different depths may be estimated for the region of the same object, and an object region that is appropriately shaped by estimated depths may be missed. To overcome this, we first initialise the 3D position of an object using the frame with the highest consistency between the depth estimation and object detection results. Then, we track the object in the 3D space using particle filter, where a 3D position of the object is modelled as a hidden state to generate its 2D visual appearance. Experimental results demonstrate the effectiveness of our method.