Search

Data quality is crucial for training accurate, unbiased, and trustworthy machine learning models as well as for their correct evaluation. Recent work, however, has shown that even popular datasets used to train and evaluate state-of-the-art models contain a non-negligible amount of erroneous annotations, biases, or artifacts. While practices and guidelines regarding dataset creation projects exist, to our knowledge, large-scale analysis has yet to be performed on how quality management is conducted when creating natural language datasets and whether these recommendations are followed. Therefore, we first survey and summarize recommended quality management practices for dataset creation as described in the literature and provide suggestions for applying them. Then, we compile a corpus of 591 scientific publications introducing text datasets and annotate it for quality-related aspects, such as annotator management, agreement, adjudication, or data validation. Using these annotations, we then analyze how quality management is conducted in practice. A majority of the annotated publications apply good or excellent quality management. However, we deem the effort of 30% of the studies as only subpar. Our analysis also shows common errors, especially when using inter-annotator agreement and computing annotation error rates. [ABSTRACT FROM AUTHOR]

With the proliferation of large-scale 3D point cloud datasets, the high cost of per-point annotation has spurred the development of weakly supervised semantic segmentation methods. Current popular research mainly focuses on single-scale classification, which fails to address the significant feature scale differences between background and objects in large scenes. Therefore, we propose MCCR (Multi-scale Classification and Contrastive Regularization), an end-to-end semantic segmentation framework for large-scale 3D scenes under weak supervision. MCCR first aggregates features and applies random downsampling to the input data. Then, it captures the local features of a random point based on multi-layer features and the input coordinates. These features are then fed into the network to obtain the initial and final prediction results, and MCCR iteratively trains the model using strategies such as contrastive learning. Notably, MCCR combines multi-scale classification with contrastive regularization to fully exploit multi-scale features and weakly labeled information. We investigate both point-level and local contrastive regularization to leverage point cloud augmentor and local semantic information and introduce a Decoupling Layer to guide the loss optimization in different spaces. Results on three popular large-scale datasets, S3DIS, SemanticKITTI and SensatUrban, demonstrate that our model achieves state-of-the-art (SOTA) performance on large-scale outdoor datasets with only 0.1% labeled points for supervision, while maintaining strong performance on indoor datasets. [ABSTRACT FROM AUTHOR]

We examined the characteristics of video annotations frequently discussed during debriefing conversations as part of video-assisted coaching cycles. We also analyzed how mathematics coaches used written annotations to inject ideas into debriefing conversations when supporting teachers to reflect on important classroom events. Coaches and teachers asynchronously created the annotations based on what they noticed while watching video of an implemented lesson. Findings revealed annotations that were coach-created, focused on the teacher, contained content about goals and discourse, or contained connections were most frequently taken up during the debriefing conversation. In addition, we identified four unique ways coaches used annotation references to inject new ideas into the conversations. We present a rationale for continued research on the relationship between noticing artifacts from a lesson (i.e., video annotations) and subsequent reflective conversation between a coach and teacher. [ABSTRACT FROM AUTHOR]

Event extraction (EE) is capable of providing essential information to facilitate comprehension of legal cases by identifying event types and extracting corresponding arguments from legal case documents. In the legal field, events are often presented in the form of document, with arguments scattered across multiple sentences, which means that legal EE at the document level is needed to better capture the complete event. However, the existing legal EE datasets mainly focused on event extraction at the sentence level, with little attention given to the document level. Obviously, it put the development of document-level event extraction (DEE) in the legal field at a disadvantage. To address this challenge, we proposed DLEE, the first DEE dataset in the legal field with two distinctive features: (1) Document-level Semi-automated Annotation, ensuring effective annotation with high quality. (2) Large-scale and Fine-grained coverage, comprising 10,014 events and 99,423 arguments. Finally, we assessed the performance of commonly used DEE baseline models on DLEE. It revealed that the DLEE is an open question, and further attention is needed for the improvement of the models' performance. [ABSTRACT FROM AUTHOR]

Fine-grained 3D shape recognition (FGSR) is crucial for real-world applications. Existing methods face challenges in achieving high accuracy for FGSR due to high similarity within sub-categories and low dissimilarity between them, especially in the absence of part location or attribute annotations. In this paper, we propose V 2 MLP, a multi-view representation-oriented MLP network dedicated to FGSR, using only class labels as supervision. V 2 MLP comprises two key modules: the cross-view interaction MLP (CVI-MLP) and the cross-view fusion MLP (CVF-MLP). The CVI-MLP module captures contextual information, including local and global contexts through cross-view interactions, to extract discriminative view features that reinforce subtle differences between sub-categories. Meanwhile, the CVF-MLP module performs cross-view aggregation from space and view dimensions to obtain the final 3D shape features, minimizing information loss during the view feature fusion process. Extensive experiments on three categories from the FG3D dataset demonstrate the effectiveness of V 2 MLP in learning discriminative features for 3D shapes, achieving state-of-the-art accuracy for FGSR. Additionally, V 2 MLP performs competitively for meta-category recognition on the ModelNet40 dataset. [ABSTRACT FROM AUTHOR]

This paper studies a new learning paradigm for noisy labels, i.e., noisy correspondence (NC). Unlike the well-studied noisy labels that consider the errors in the category annotation of a sample, the NC refers to the errors in the alignment relationship of two data points. Although such false positive pairs are common especially in the data harvested from the Internet, which however are neglected by most existing works. By taking cross-modal retrieval as a showcase, we propose a method called learning with noisy correspondence (LNC). In brief, the LNC first roughly obtains the clean and noisy subsets from the original data and then rectifies the false positive pairs by using a novel adaptive prediction function. Finally, the LNC adopts a novel triplet loss with soft margins to endow cross-modal retrieval the robustness to the NC. To verify the effectiveness of the proposed LNC, we conduct experiments on six benchmark datasets in image-text and video-text retrieval tasks. Besides the effectiveness of the LNC, the experimental results show the necessity of the explicit solution to the NC faced by not only the standard model training paradigm but also the pre-training and fine-tuning paradigms. [ABSTRACT FROM AUTHOR]

The state-of-the-art semantic segmentation methods have achieved impressive performance on predefined close-set individual datasets, but their generalization to zero-shot domains and unseen categories is limited. Labeling a large-scale dataset is challenging and expensive, Training a robust semantic segmentation model on multi-domains has drawn much attention. However, inconsistent taxonomies hinder the naive merging of current publicly available annotations. To address this, we propose a simple solution to scale up the multi-domain semantic segmentation dataset with less human effort. We replace each class label with a sentence embedding, which is a vector-valued embedding of a sentence describing the class. This approach enables the merging of multiple datasets from different domains, each with varying class labels and semantics. We merged publicly available noisy and weak annotations with the most finely annotated data, over 2 million images, which enables training a model that achieves performance equal to that of state-of-the-art supervised methods on 7 benchmark datasets, despite not using any images therefrom. Instead of manually tuning a consistent label space, we utilized a vector-valued embedding of short paragraphs to describe the classes. By fine-tuning the model on standard semantic segmentation datasets, we also achieve a significant improvement over the state-of-the-art supervised segmentation on NYUD-V2 (Silberman et al., in: European conference on computer vision, Springer, pp 746–760, 2012) and PASCAL-context (Everingham et al. in Int J Comput Visi 111(1):98–136, 2015) at 60 % and 65 % mIoU, respectively. Our method can segment unseen labels based on the closeness of language embeddings, showing strong generalization to unseen image domains and labels. Additionally, it enables impressive performance improvements in some adaptation applications, such as depth estimation and instance segmentation. Code is available at https://github.com/YvanYin/SSIW. [ABSTRACT FROM AUTHOR]

Urban regeneration is an important strategy for land redevelopment, to address the urban decay in cities. Among many tasks, urban layout is the foundation for urban regeneration. In this paper, we target a new task called function-aware urban layout regeneration, and propose UrbanEvolver, a function-aware deep generative model for the task. Given a target region to be regenerated, our model outputs a regenerated urban layout (i.e., roads and buildings) for the target region by considering the function (i.e., land use type) of the target region and its surrounding context (i.e., the functions and urban layouts of the surrounding regions). UrbanEvolver first extracts implicit regeneration rules from the target function and the surrounding context by encoding them separately in different scales through the function-layout adaptive (FA) blocks, and then constrains the regenerated urban layout based on the learned regeneration rules. To enforce the regenerated layout to be valid and to follow the road structure, we design a set of losses covering both pixel-level and geometry-level constraints. To train our model, we collect a large-scale urban layout dataset covering more than 147 K regions under 1300 km 2 with rich annotations, including functions, region shapes, urban road layouts, and urban building layouts. We conduct extensive experiments to show that our model outperforms the baseline methods in generating practical and function-aware urban layouts based on the given target function and surrounding context. [ABSTRACT FROM AUTHOR]

Wildlife observation with camera traps has great potential for ethology and ecology, as it gathers data non-invasively in an automated way. However, camera traps produce large amounts of uncurated data, which is time-consuming to annotate. Existing methods to label these data automatically commonly use a fixed pre-defined set of distinctive classes and require many labeled examples per class to be trained. Moreover, the attributes of interest are sometimes rare and difficult to find in large data collections. Large pretrained vision-language models, such as contrastive language image pretraining (CLIP), offer great promises to facilitate the annotation process of camera-trap data. Images can be described with greater detail, the set of classes is not fixed and can be extensible on demand and pretrained models can help to retrieve rare samples. In this work, we explore the potential of CLIP to retrieve images according to environmental and ecological attributes. We create WildCLIP by fine-tuning CLIP on wildlife camera-trap images and to further increase its flexibility, we add an adapter module to better expand to novel attributes in a few-shot manner. We quantify WildCLIP's performance and show that it can retrieve novel attributes in the Snapshot Serengeti dataset. Our findings outline new opportunities to facilitate annotation processes with complex and multi-attribute captions. The code is available at https://github.com/amathislab/wildclip. [ABSTRACT FROM AUTHOR]

SCoralNet (based on Faster R-CNN) is a new underwater coral detection framework that has been proposed to automatically localize and identify distinct coral species in images, allowing for fast and detailed annotation. Monitoring the coverage and abundance of underwater corals typically involves the annotation and processing of large amounts of underwater coral images. However, manually annotating a large number of images is time-consuming and labor-intensive, and CNN classifiers only provide simple classification annotations without capturing the images' finer details. SCoralNet's detection performance is improved by incorporating dilated convolutions into the backbone network. To successfully capture multi-scale and multi-level information from coral targets, a neck network called NASFPN is placed between the backbone and the detecting head. Seesaw Loss is used to reduce the impact of the dataset's long-tailed distribution on SCoralNet's classifier accuracy. CIoU loss is used to optimize the bounding box regression method. During inference, Soft-NMS is applied to suppress redundant coral detection boxes. To assess SCoralNet's effectiveness, a dataset called Coral-soft was developed using real-world photos of common soft coral species from the Sanya region of China. SCoralNet outperformed the original Faster R-CNN model on the Coral-soft dataset, with a 45.68% gain in mean average precision (mAP) and a 59.2% increase in mAP75. Furthermore, SCoralNet outperformed some advanced models in terms of overall performance. [ABSTRACT FROM AUTHOR]

We present Mask2Hand, a self-trainable method for predicting 3D hand pose and shape from a single 2D binary silhouette. Without additional manual annotations, our method uses differentiable rendering to project 3D estimations onto the 2D silhouette. A tailored loss function, applied between the rendered and input silhouettes, provides a self-guidance mechanism during end-to-end optimization, which constrains global mesh registration and hand pose estimation. Our experiments show that Mask2Hand, using only a binary mask input, achieves accuracy comparable to state-ofthe- art methods requiring RGB or depth inputs on both unaligned and aligned datasets. [ABSTRACT FROM AUTHOR]

Annotation on the Judgment of the Court (Tenth Chamber) of 1 February 2024 in Case C-251/22 P Scania AB and Others v Commission [2024] ECLI:EU:C:2024:103 [ABSTRACT FROM AUTHOR]

Annotation on the Judgment of the Court (Ninth Chamber) of 21 September 2023 in Case C-510/22 Romaqua Group SA v Societatea Națională a Apelor Minerale SA e.a. [ABSTRACT FROM AUTHOR]

Questioning plays a vital role in education, directing knowledge construction and assessing students' understanding. However, creating high-level questions requires significant creativity and effort. Automatic question generation is expected to facilitate the generation of not only fluent and relevant but also educationally valuable questions. While rule-based methods are intuitive for short inputs, they struggle with longer and more complex inputs. Neural question generation (NQG) has shown better results in this regard. This review summarizes the advancements in NQG between 2016 and early 2022. The focus is on the development of NQG for educational purposes, including challenges and research opportunities. We found that although NQG can generate fluent and relevant factoid-type questions, few studies focus on education. Specifically, there is limited literature using context in the form of multi-paragraphs, which due to the input limitation of the current deep learning techniques, require key content identification. The desirable key content should be important to specific topics or learning objectives and be able to generate certain types of questions. A further research opportunity is controllable NQG systems, which can be customized by taking into account factors like difficulty level, desired answer type, and other individualized needs. Equally important, the results of our review also suggest that it is necessary to create datasets specific to the question generation tasks with annotations that support better learning for neural-based methods. [ABSTRACT FROM AUTHOR]

Predicting depth maps from monocular images has made an impressive performance in the past years. However, most depth estimation methods are trained with paired image-depth map data or multi-view images (e.g., stereo pair and monocular sequence), which suffer from expensive annotation costs and poor transferability. Although unsupervised domain adaptation methods are introduced to mitigate the reliance on annotated data, rare works focus on the unsupervised cross-scenario indoor monocular depth estimation. In this article, we propose to study the generalization of depth estimation models across different indoor scenarios in an adversarial-based domain adaptation paradigm. Concretely, a domain discriminator is designed for discriminating the representation from source and target domains, while the feature extractor aims to confuse the domain discriminator by capturing domain-invariant features. Further, we reconstruct depth maps from latent representations with the supervision of labeled source data. As a result, the feature extractor learned features possess the merit of both domain-invariant and low source risk, and the depth estimator can deal with the domain shift between source and target domains. We conduct the cross-scenario and cross-dataset experiments on the ScanNet and NYU-Depth-v2 datasets to verify the effectiveness of our method and achieve impressive performance. [ABSTRACT FROM AUTHOR]

Can we predict a person's appearance solely based on their voice? This article explores this question by focusing on generating a face from an unheard voice segment. Our proposed method, VoiceStyle, combines cross-modal representation learning with generation modeling, enabling us to incorporate voice semantic cues into the generated face. In the first stage, we introduce cross-modal prototype contrastive (CMPC) learning to establish the association between voice and face. Recognizing the presence of false negative and deviate positive instances in real-world unlabeled data, we not only use voice–face pairs in the same video but also construct additional semantic positive pairs through unsupervised clustering, enhancing the learning process. Moreover, we recalibrate instances based on their similarity to cluster centers in the other modality. In the second stage, we harness the powerful generative capabilities of StyleGAN to produce faces. We optimize the latent code in StyleGAN's latent space, guided by the learned voice–face alignment. To address the importance of selecting an appropriate starting point for optimization, we aim to automatically find an optimal starting point by utilizing the face prototype derived from the voice input. The entire pipeline can be implemented in a self-supervised manner, eliminating the need for manually labeled annotations. Through extensive experiments, we demonstrate the effectiveness and performance of our VoiceStyle method in both cross-modal representation learning and voice-based face generation. [ABSTRACT FROM AUTHOR]

Domain Adaptive Object Detection (DAOD) alleviates the challenge of labor-intensive annotations by transferring semantic information from a labeled source domain to an unlabeled target domain. However, the DAOD suffers from biased discrimination and negative transfer in the thermal domain due to the inherent heterogeneity between the RGB and thermal images. To address the above issues, we propose the Unbiased Granularity Alignment (UGA) framework to facilitate the unified alignment for RGB-Thermal DAOD. Specifically, we devise a Channel Self-encoding Adaptation (CSA) module to mitigate biased discrimination from the discriminative enhancement perspective. CSA aligns the intra-domain channel subspace for inter-domain channel harmonizing. Upon revisiting instance alignment, we uncovered inaccuracies proposals and unstable positive sample phenomena. Therefore, we propose the Relative Relationship Adaptation (RRA) module to mitigate negative transfer. RRA ensures inter-domain semantic consistency through sparse instance alignment. Extensive experiments are conducted on visible-to-thermal and visible-to-visible benchmarks to validate the effectiveness, and our UGA framework outperforms state-of-the-art by a remarkable margin. The code of our UGA is available at https://github.com/zyfone/UGA. [ABSTRACT FROM AUTHOR]

Prostate cancer is the most commonly diagnosed cancer in men, accounting for 27% of the new male cancer diagnoses in 2022. If organ-confined, removal of the prostate through radical prostatectomy is considered curative; however, distant metastases may occur, resulting in a poor patient prognosis. This study sought to determine whether quantitative pathomic features of prostate cancer differ in patients who biochemically experience biological recurrence after surgery. Whole-mount prostate histology from 78 patients was analyzed for this study. In total, 614 slides were hematoxylin and eosin stained and digitized to produce whole slide images (WSI). Regions of differing Gleason patterns were digitally annotated by a genitourinary fellowship-trained pathologist, and high-resolution tiles were extracted from each annotated region of interest for further analysis. Individual glands within the prostate were identified using automated image processing algorithms, and histomorphometric features were calculated on a per-tile basis and across WSI and averaged by patients. Tiles were organized into cancer and benign tissues. Logistic regression models were fit to assess the predictive value of the calculated pathomic features across tile groups and WSI; additionally, models using clinical information were used for comparisons. Logistic regression classified each pathomic feature model at accuracies >80% with areas under the curve of 0.82, 0.76, 0.75, and 0.72 for all tiles, cancer only, noncancer only, and across WSI. This was comparable with standard clinical information, Gleason Grade Groups, and CAPRA score, which achieved similar accuracies but areas under the curve of 0.80, 0.77, and 0.70, respectively. This study demonstrates that the use of quantitative pathomic features calculated from digital histology of prostate cancer may provide clinicians with additional information beyond the traditional qualitative pathologist assessment. Further research is warranted to determine possible inclusion in treatment guidance.

Copyright of Campus Virtuales is the property of Campus Virtuales and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This paper stems from the project A World of Possibilities. Modal pathways over an extra-long period of time: the diachrony of modality in the Latin language (WoPoss) which involves a corpus-based approach to the study of modality in the history of the Latin language. Linguistic annotation and, in particular, the semantic annotation of modality is a keystone of the project. Besides the difficulties intrinsic to any annotation task dealing with semantics, our annotation scheme involves multiple layers of annotation that are interconnected, adding complexity to the task. Considering the intricacies of our fine-grained semantic annotation, we needed to develop well-documented schemas in order to control the consistency of the annotation, but also to enable an efficient reuse of our annotated corpus. This paper presents the different elements involved in the annotation task, and how the description and the relations between the different linguistic components were formalised and documented, combining schema languages with XML documentation. [ABSTRACT FROM AUTHOR]

Accurately representing changes in mental states over time is crucial for understanding their complex dynamics. However, there is little methodological research on the validity and reliability of human-produced continuous-time annotation of these states. We present a psychometric perspective on valid and reliable construct assessment, examine the robustness of interval-scale (e.g., values between zero and one) continuous-time annotation, and identify three major threats to validity and reliability in current approaches. We then propose a novel ground truth generation pipeline that combines emerging techniques for improving validity and robustness. We demonstrate its effectiveness in a case study involving crowd-sourced annotation of perceived violence in movies, where our pipeline achieves a.95 Spearman correlation in summarized ratings compared to a.15 baseline. These results suggest that highly accurate ground truth signals can be produced from continuous annotations using additional comparative annotation (e.g., a versus b) to correct structured errors, highlighting the need for a paradigm shift in robust construct measurement over time. [ABSTRACT FROM AUTHOR]

Achieving reliable automatic left ventricle (LV) segmentation from echocardiograms is challenging due to the inherent sparsity of annotations in the dataset, as clinicians typically only annotate two specific frames for diagnostic purposes. Here we aim to address this challenge by introducing simplified LV segmentation (SimLVSeg), a novel paradigm that enables video-based networks for consistent LV segmentation from sparsely annotated echocardiogram videos. SimLVSeg consists of two training stages: (i) self-supervised pre-training with temporal masking, which involves pre-training a video segmentation network by capturing the cyclic patterns of echocardiograms from largely unannotated echocardiogram frames, and (ii) weakly supervised learning tailored for LV segmentation from sparse annotations. We extensively evaluated SimLVSeg using EchoNet-Dynamic, the largest echocardiography dataset. SimLVSeg outperformed state-of-the-art solutions by achieving a 93.32% (95% confidence interval: 93.21–93.43%) dice score while being more efficient. We further conducted an out-of-distribution test to showcase SimLVSeg's generalizability on distribution shifts (CAM US dataset). Our findings show that SimLVSeg exhibits excellent performance on LV segmentation with a relatively cheaper computational cost. This suggests that adopting video-based networks for LV segmentation is a promising research direction to achieve reliable LV segmentation. Our code is publicly available at https://github.com/BioMedIA-MBZUAI/SimLVSeg. [ABSTRACT FROM AUTHOR]

Recent advances in multi-view multi-label learning are often hampered by the prevalent challenges of incomplete views and missing labels, common in real-world data due to uncertainties in data collection and manual annotation. These challenges restrict the capacity of the model to fully utilize the diverse semantic information of each sample, posing significant barriers to effective learning. Despite substantial scholarly efforts, many existing methods inadequately capture the depth of semantic information, focusing primarily on shallow feature extractions that fail to maintain semantic consistency. To address these shortcomings, we propose a novel Deep semantic structure-preserving (SSP) model that effectively tackles both incomplete views and missing labels. SSP innovatively incorporates a graph constraint learning (GCL) scheme to ensure the preservation of semantic structure throughout the feature extraction process across different views. Additionally, the SSP integrates a pseudo-labeling self-paced learning (PSL) strategy to address the often-overlooked issue of missing labels, enhancing the classification accuracy while preserving the distribution structure of data. The SSP model creates a unified framework that synergistically employs GCL and PSL to maintain the integrity of semantic structural information during both feature extraction and classification phases. Extensive evaluations across five real datasets demonstrate that the SSP method outperforms existing approaches, including lrMMC, MVL-IV, MvEL, iMSF, iMvWL, NAIML, and DD-IMvMLC-net. It effectively mitigates the impacts of data incompleteness and enhances semantic representation fidelity. [ABSTRACT FROM AUTHOR]

Calcium (Ca) and cadmium (Cd) are transition metals coexisting in the ecosystem. Ca is indispensable for the growth and development of plants as well as animals, while Cd is regarded as a toxic heavy metal for the living system. The transportation of Cd in the biological systems often used the pathways of Ca because of chemical similarities. High concentrations of cadmium replace Ca, Mn, and Zn from their respective metalloprotein sites and strongly associated with them. Replaced minerals from their metalloprotein sites are often released as an oxidative ion that is detrimental to it. The common transportation mechanism of Ca and Cd is implicit in the role of common and similar transporters for transporting them in plants. Thus, our study was done to identify the transporters for Ca and Cd and characterize them for similarity in terms of cotransportation system. A profile-based search program identified 44 transporters genes for Ca transportation and 70 genes for cadmium transportation. They were categorized into different groups based on the presence of signature motifs and domains. Identified transporters were characterized for genomic distribution, gene structure, annotation, conserved signature motifs, and domain. Further, cis motif analysis, heat map, gene ontology, and protein–protein interaction were conducted for Ca and Cd transporter genes. In silico expression showed Os05g0319800-1304 and Os0319800-6065 transporter genes were overexpressed for Ca and Os07g00232800-40298 and Os07g00384500-25924 transporter genes overexpressed for Cd transporter. These genes could be used as a candidate genes for enhancing the Ca concentration with reduced Cd content in rice using biotechnological approaches. Twenty-seven genes were found as the common transporters for Ca and Cd. Both active and passive transporter mechanisms act as cotransporters for Ca and Cd. The common signature motifs and domains can be targeted for the characterization of cotransporters of different minerals. [ABSTRACT FROM AUTHOR]

Battista Guarini’s letters had a great fortune in print between the Nineties of the Sixteenth and the first decade of the Seventeenth century. Then comes a period of oblivion, ending in the Thirties of the Eighteenth century, when the letters were included into the draft edition of all Guarini’s Works, made by the printer Giovanni Alberto Tumermani. Although the three volumes of letters (edited by Apostolo Zeno in cooperation with Lodovico Antonio Muratori) were never published, the contribution of the studies made in preparation for printing is still relevant today. Specifically, Zeno found and transcribed letters, whose originals are lost; moreover, he copied twice the annotations that Giovan Niccolò Panizzari, a Guarini’s friend, had written at the first edition of the printed letters (Venezia, Ciotti, 1593). These annotations provide important information about the transition from letter-document to letter-work and about the author will. In this article I want to reconstruct the authorial intervention in Ciotti’s first edition and provide the Panizzari’s annotations scholar edition.

This work delves into the papers of the most significant and rare Petrarchian editions - including incunabula and cinquecentine - contained in the precious book collection of Jacopo Loris Bononi preserved in Castiglione del Terziere. It investigates the peculiar characteristics and cultural contexts that gave rise to the individual prints, the possession notes and the heterogeneous typology of annotations and marginal notes found in the volumes, opening up unprecedented scenarios of responsive readers interacting in various ways with the text.

In East Asia, anguillid eels are commercially important. However, unlike other species, they have not been successfully cultivated throughout their lifecycle. Facing population decline due to overharvesting and environmental pressures, the industry is turning to alternatives, such as Anguilla bicolor pacifica (short-finned eel). However, genomic data for short-finned eels are unavailable. Here, we present in-depth whole-genome sequencing results for short-finned eel obtained using two sequencing platforms (PacBio Revio, and Illumina). In this study, we achieved a highly contiguous genome assembly of the short-finned eel, comprising 19 pseudochromosomes encompassing 99.76% of the 1.087 Gb genome sequence with an N50 of 16.88 and 61.07 Mb from contig and scaffold, respectively. Transcripts from four different tissues led to the annotation of 23,095 protein-coding genes in the eel genome, 98.66% of which were functionally annotated. This high-quality genome assembly, along with the annotation data, provides a foundation for future functional genomic studies of short-finned eels. [ABSTRACT FROM AUTHOR]

Spinibarbus caldwelli is an important freshwater economic fish in China. Owing to uncontrolled fishing, wild resources of S. caldwelli have decreased rapidly and may be on the verge of extinction. In this study, utilizing single-molecule real-time (SMRT) sequencing technology and chromatin interaction mapping (Hi-C) technologies, we assembled the first chromosome-scale genome for S. caldwelli about 1.77 Gb in size, with a contig N50 length of 11.83 Mb and scaffold N50 length of 33.91 Mb. In total 1.72 Gb (97.01%) of the contig sequences were anchored onto fifty chromosomes with the longest scaffold being 56.20 Mb. Furthermore, proximately 49.41% of the genome was composed of repetitive elements. In total, 49,377 protein-coding genes were predicted, of which 47,724 (96.65%) genes have been functionally annotated. The high-quality chromosome-level reference genome and annotation are vital for supporting basic genetic studies and will be contribute to genetic structure, functional elucidation, evolutionary inquiry, and germplasm conservation for S. caldwelli. [ABSTRACT FROM AUTHOR]

Multi-party conversations are a practical and challenging scenario with more than two sessions entangled with each other. Therefore, it is necessary to disentangle a whole conversation into several sessions to help listeners decide which session each utterance is part of to respond to it appropriately. This task is referred to as dialogue disentanglement. Most existing methods focus on message-pair modeling and clustering in two-step methods, which are sensitive to the noise classification pairs and result in poor clustering performance. To address this challenge, we propose a contrastive learning framework named IAM for end-to-end implicit addressee modeling. To be more specific, IAM makes utterances in different sessions mutually exclusive to identify the sessions of utterances better. Then a clustering method is adopted to generate predicted clustering labels. Moreover, to alleviate the lack of massive annotated data, we introduce a strategy to select pseudo samples for unsupervised training without manual annotations. Comprehensive experiments conducted on the Movie Dialogue and IRC datasets demonstrate that IAM achieves state-of-the-art in both supervised and unsupervised manners. [ABSTRACT FROM AUTHOR]

Copyright of Zhejiang Electric Power is the property of Zhejiang Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The amount of labelled data in industrial use cases is limited because the annotation process is time-consuming and costly. As in research, self-supervised pretraining such as MAE resulted in training segmentation models with fewer labels, this is also an interesting direction for industry. The reduction of required labels is achieved with large amounts of unlabelled images for the pretraining that aims to learn image features. This paper analyses the influence of MAE pretraining on the efficiency of label usage for semantic segmentation with UNETR. This is investigated for the use case of log-yard cranes. Additionally, two transfer learning cases with respect to crane type and perspective are considered in the context of label-efficiency. The results show that MAE is successfully applicable to the use case. With respect to the segmentation, an IoU improvement of 3.26% is reached while using 2000 labels. The strongest positive influence is found for all experiments in the lower label amounts. The highest effect is achieved with transfer learning regarding cranes, where IoU and Recall increase about 4.31% and 8.58%, respectively. Further analyses show that improvements result from a better distinction between the background and the segmented crane objects. [ABSTRACT FROM AUTHOR]

Existing Super-Resolution (SR) methods are typically trained using bicubic degradation simulations, resulting in unsatisfactory results when applied to remote sensing images that contain a wide variety of object shapes and sizes. The insufficient learning approach reduces the focus of models on critical object regions within the images. As a result, their practical performance is significantly hindered, especially in real-world applications where accuracy in object reconstruction is crucial. In this work, we propose a general learning strategy for SR models based on expert knowledge supervision, named EKS-SR, which can incorporate a few coarse-grained semantic information derived from high-level visual tasks into the SR reconstruction process. It utilizes prior information from three perspectives: regional constraints, feature constraints, and attributive constraints, to guide the model to focus more on the object regions within the images. By integrating these expert knowledge-driven constraints, EKS-SR can enhance the model's ability to accurately reconstruct object regions and capture the key information needed for practical applications. Importantly, this improvement does not increase the inference time and does not require full annotation of the large-scale datasets, but only a few labels, making EKS-SR both efficient and effective. Experimental results demonstrate that the proposed method can achieve improvements in both reconstruction quality and machine vision analysis performance. [ABSTRACT FROM AUTHOR]

Weakly supervised semantic segmentation (WSSS) aims to segment objects without a heavy burden of dense annotations. Pseudo-masks serve as supervisory information for training segmentation models, which is crucial to the performance of segmentation models. However, the generated pseudo-masks contain significant noisy labels, which leads to poor performance of the segmentation models trained on these pseudo-masks. Few studies address this issue, as these noisy labels remain inevitable even after the pseudo-masks are improved. In this paper, we propose an uncertainty-weight transform module to mitigate the impact of noisy labels on model performance. It is noteworthy that our approach is not aimed at eliminating noisy labels but rather enhancing the robustness of the model to noisy labels. The proposed method adopts a frequency-based approach to estimate pixel uncertainty. Moreover, the uncertainty of pixels is transformed into loss weights through a set of well-designed functions. After dynamically assigning weights, the model allocates attention to each pixel in a significantly differentiated manner. Meanwhile, the impact of noisy labels on model performance is weakened. Experiments validate the effectiveness of the proposed method, achieving state-of-the-art results of 69.3% on PASCAL VOC 2012 and 39.3% on MS COCO 2014, respectively. [ABSTRACT FROM AUTHOR]

Paspalum notatum Flüggé is an economically important subtropical fodder grass that is widely used in the Americas. Here, we report a new chromosome-scale genome assembly and annotation of a diploid biotype collected in the center of origin of the species. Using Oxford Nanopore long reads, we generated a 557.81 Mb genome assembly (N50 = 56.1 Mb) with high gene completeness (BUSCO = 98.73%). Genome annotation identified 320 Mb (57.86%) of repetitive elements and 45,074 gene models, of which 36,079 have a high level of confidence. Further characterisation included the identification of 59 miRNA precursors together with their putative targets. The present work provides a comprehensive genomic resource for P. notatum improvement and a reference frame for functional and evolutionary research within the genus. [ABSTRACT FROM AUTHOR]

Flueggea virosa (Roxb. ex Willd.) Royle, an evergreen shrub and small tree in the Phyllanthaceae family, holds significant potential in garden landscaping and pharmacological applications. However, the lack of genomic data has hindered further scientific understanding of its horticultural and medicinal values. In this study, we have assembled a haplotype-resolved genome of F. virosa for the first time. The two haploid genomes, named haplotype A genome and haplotype B genome, are 487.33 Mb and 477.53 Mb in size, respectively, with contig N50 lengths of 31.45 Mb and 32.81 Mb. More than 99% of the assembled sequences were anchored to 13 pairs of pseudo-chromosomes. Furthermore, 21,587 and 21,533 protein-coding genes were predicted in haplotype A and haplotype B genomes, respectively. The availability of this chromosome-level genome fills the gap in genomic data for F. virosa and provides valuable resources for molecular studies of this species, supporting future research on speciation, functional genomics, and comparative genomics within the Phyllanthaceae family. [ABSTRACT FROM AUTHOR]

Motivation Protein–protein interaction (PPI) networks provide valuable insights into the function of biological systems. Aligning multiple PPI networks may expose relationships beyond those observable by pairwise comparisons. However, assessing the biological quality of multiple network alignments is a challenging problem. Results We propose two new measures to evaluate the quality of multiple network alignments using functional information from Gene Ontology (GO) terms. When aligning multiple real PPI networks across species, we observe that both measures are highly correlated with objective quality indicators, such as common orthologs. Additionally, our measures strongly correlate with an alignment's ability to predict novel GO annotations, which is a unique advantage over existing GO-based measures. Availability and implementation The scripts and the links to the raw and alignment data can be accessed at https://github.com/kimiayazdani/GO_Measures.git [ABSTRACT FROM AUTHOR]

We welcome feedback on the range maps published in Marsh et al. (2022) where it constructively improves our knowledge on species distributions. Unfortunately, we are concerned that criticisms raised by Arbogast and Kerhoulas are steps backward, not forward, particularly as they did not access the original range map data of Marsh et al. (2022). We stress that evaluating range maps using Global Biodiversity Information Facility data without the necessary quality control and filtering will lead to flawed interpretations—using the same approach, an even greater proportion, >99.5%, of IUCN mammal range maps would fail to meet their expectations. We take this opportunity to highlight the fine-scale inaccuracies, scale limitations, and range map variance that are expected across all expert range map sources and that any researcher should consider during any analysis. Finally, we again announce the availability of an online tool for providing annotations and proposing adjustments to range maps, and suggest this as a more appropriate forum for constructively and transparently improving range maps. [ABSTRACT FROM AUTHOR]

As an indispensable part of the vehicle environment perception task, road traffic marking detection plays a vital role in correctly understanding the current traffic situation. However, the existing traffic marking detection algorithms still have some limitations. Taking lane detection as an example, the current detection methods mainly focus on the location information detection of lane lines, and they only judge the overall attribute of each detected lane line instance, thus lacking more fine-grained dynamic detection of lane line attributes. In order to meet the needs of intelligent vehicles for the dynamic attribute detection of lane lines and more perfect road environment information in urban road environment, this paper constructs a fine-grained attribute detection method for lane lines, which uses pixel-level attribute sequence points to describe the complete attribute distribution of lane lines and then matches the detection results of the lane lines. Realizing the attribute judgment of different segment positions of lane instances is called the fine-grained attribute detection of lane lines (Lane-FGA). In addition, in view of the lack of annotation information in the current open-source lane data set, this paper constructs a lane data set with both lane instance information and fine-grained attribute information by combining manual annotation and intelligent annotation. At the same time, a cyclic iterative attribute inference algorithm is designed to solve the difficult problem of lane attribute labeling in areas without visual cues such as occlusion and damage. In the end, the average accuracy of the proposed algorithm reaches 97% on various types of lane attribute detection. [ABSTRACT FROM AUTHOR]

Summary: Betalains are coloring pigments produced in some families of the order Caryophyllales, where they replace anthocyanins as coloring pigments. While the betalain pathway itself is well studied, the tissue‐specific regulation of the pathway remains mostly unknown.We enhance the high‐quality Amaranthus hypochondriacus reference genome and produce a substantially more complete genome annotation, incorporating isoform details. We annotate betalain and anthocyanin pathway genes along with their regulators in amaranth and map the genetic control and tissue‐specific regulation of the betalain pathway.Our improved genome annotation allowed us to identify causal mutations that lead to a knock‐out of red betacyanins in natural accessions of amaranth. We reveal the tissue‐specific regulation of flower color via a previously uncharacterized MYB transcription factor, AhMYB2. Downregulation of AhMYB2 in the flower leads to reduced expression of key betalain enzyme genes and loss of red flower color.Our improved amaranth reference genome represents the most complete genome of amaranth to date and is a valuable resource for betalain and amaranth research. High similarity of the flower betalain regulator AhMYB2 to anthocyanin regulators and a partially conserved interaction motif support the co‐option of anthocyanin regulators for the betalain pathway as a possible reason for the mutual exclusiveness of the two pigments. [ABSTRACT FROM AUTHOR]

Obtaining a complete good-quality sequence and annotation for the long double-stranded DNA genome of the African swine fever virus (ASFV) from next-generation sequencing (NGS) technology has proven difficult, despite the increasing availability of reference genome sequences and the increasing affordability of NGS. A gap analysis conducted by the global African swine fever research alliance (GARA) partners identified that a standardized, automatic pipeline for NGS analysis was urgently needed, particularly for new outbreak strains. Whilst there are several diagnostic and research labs worldwide that collect isolates of the ASFV from outbreaks, many do not have the capability to analyze, annotate, and format NGS data from outbreaks for submission to NCBI, and some publicly available ASFV genomes have missing or incorrect annotations. We developed an automated, standardized pipeline for the analysis of NGS reads that directly provides users with assemblies and annotations formatted for their submission to NCBI. This pipeline is freely available on GitHub and has been tested through the GARA partners by examining two previously sequenced ASFV genomes; this study also aimed to assess the accuracy and limitations of two strategies present within the pipeline: reference-based (Illumina reads) and de novo assembly (Illumina and Nanopore reads) strategies. [ABSTRACT FROM AUTHOR]

Pavement cracks are crucial indicators for assessing the structural health of asphalt roads. Existing automated crack detection models depend on large quantities of precisely annotated crack sample data. The irregular morphology of cracks makes manual annotation time-consuming and costly, thereby posing challenges to the practical application of these models. This study proposes a pavement crack image detection method integrating fractal dimension analysis and semi-supervised learning. It identifies the self-similarity characteristics within the crack regions by analyzing pavement crack images and using fractal dimensions to preliminarily determine the candidate crack regions. The Crack Similarity Learning Network (CrackSL-Net) is then employed to learn the semantic similarity of crack image regions. Semi-supervised learning facilitates automatic crack detection by combining a small amount of labeled data with a large volume of unlabeled image data. Comparative experiments are conducted on two public pavement crack datasets against the HED, U-Net, and RCF models to comprehensively evaluate the performance of the proposed method. The results indicate that, with a 50% annotation ratio, the proposed method achieves high-precision crack detection, with an intersection over union (IoU) exceeding 0.84, which is close to that of U-Net. Visual analysis of the detection results confirms the method's effectiveness in identifying cracks in complex environments. [ABSTRACT FROM AUTHOR]

The article titled "Correction to apoptin-derived peptide reverses cisplatin resistance in gastric cancer through the PI3K-AKT signaling pathway" published in Cancer Medicine in April 2018 contains corrections to several figures. The errors include the incorrect use of images and mislabeling of certain annotations. The corrected figures have been provided in the article. The authors apologize for these errors. [Extracted from the article]

Understanding protein function is pivotal in comprehending the intricate mechanisms that underlie many crucial biological activities, with far-reaching implications in the fields of medicine, biotechnology, and drug development. However, more than 200 million proteins remain uncharacterized, and computational efforts heavily rely on protein structural information to predict annotations of varying quality. Here, we present a method that utilizes statistics-informed graph networks to predict protein functions solely from its sequence. Our method inherently characterizes evolutionary signatures, allowing for a quantitative assessment of the significance of residues that carry out specific functions. PhiGnet not only demonstrates superior performance compared to alternative approaches but also narrows the sequence-function gap, even in the absence of structural information. Our findings indicate that applying deep learning to evolutionary data can highlight functional sites at the residue level, providing valuable support for interpreting both existing properties and new functionalities of proteins in research and biomedicine. Understanding protein function is vital for biomedicine. Here, authors develop a method using statistics-informed graph networks to predict functions from sequences. The method integrates evolutionary couplings and residue communities to improve the accuracy of function annotations for proteins. [ABSTRACT FROM AUTHOR]

Copyright of Comparative Literature / Primerjalna Književnost is the property of Slovenian Comparative Literature Association and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Educational Studies (1673-1298) is the property of Journal of Educational Studies Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The rise of knowledge graphs has been instrumental in advancing artificial intelligence (AI) research. Extracting entity and relation triples from unstructured text is crucial for the construction of knowledge graphs. However, Chinese text has a complex grammatical structure, which may lead to the problem of overlapping entities. Previous pipeline models have struggled to address such overlap problems effectively, while joint models require entity annotations for each predefined relation in the set, which results in redundant relations. In addition, the traditional models often lead to task imbalance by overlooking the differences between tasks. To tackle these challenges, this research proposes a global pointer network based on relation prediction and loss function improvement (GPRL) for joint extraction of entities and relations. Experimental evaluations on the publicly available Chinese datasets DuIE2.0 and CMeIE demonstrate that the GPRL model achieves a 1.2–26.1% improvement in F1 score compared with baseline models. Further, experiments of overlapping classification conducted on CMeIE have also verified the effectiveness of overlapping triad extraction and ablation experiments. The model is helpful in identifying entities and relations accurately and can reduce redundancy by leveraging relation filtering and the global pointer network. In addition, the incorporation of a multi-task learning framework balances the loss functions of multiple tasks and enhances task interactions. [ABSTRACT FROM AUTHOR]

Monocular depth estimation aims to infer a depth map from a single image. Although supervised learning-based methods have achieved remarkable performance, they generally rely on a large amount of labor-intensively annotated data. Self-supervised methods, on the other hand, do not require any annotation of ground-truth depth and have recently attracted increasing attention. In this work, we propose a self-supervised monocular depth estimation network via binocular geometric correlation learning. Specifically, considering the inter-view geometric correlation, a binocular cue prediction module is presented to generate the auxiliary vision cue for the self-supervised learning of monocular depth estimation. Then, to deal with the occlusion in depth estimation, an occlusion interference attenuated constraint is developed to guide the supervision of the network by inferring the occlusion region and producing paired occlusion masks. Experimental results on two popular benchmark datasets have demonstrated that the proposed network obtains competitive results compared to state-of-the-art self-supervised methods and achieves comparable results to some popular supervised methods. [ABSTRACT FROM AUTHOR]