RESUMEN

Multi-modal object re-identification (ReID) is a challenging task that seeks to identify objects across different image modalities by leveraging their complementary information. Traditional CNN-based methods are constrained by limited receptive fields, whereas Transformer-based approaches are hindered by high computational demands and a lack of convolutional biases. To overcome these limitations, we propose a novel fusion framework named MambaReID, integrating the strengths of both architectures with the effective VMamba. Specifically, our MambaReID consists of three components: Three-Stage VMamba (TSV), Dense Mamba (DM), and Consistent VMamba Fusion (CVF). TSV efficiently captures global context information and local details with low computational complexity. DM enhances feature discriminability by fully integrating inter-modality information with shallow and deep features through dense connections. Additionally, with well-aligned multi-modal images, CVF provides more granular modal aggregation, thereby improving feature robustness. The MambaReID framework, with its innovative components, not only achieves superior performance in multi-modal object ReID tasks, but also does so with fewer parameters and lower computational costs. Our proposed MambaReID's effectiveness is validated by extensive experiments conducted on three multi-modal object ReID benchmarks.

RESUMEN

The statistical model for automatic flow recognition is significant for public place management. However, the current model suffers from insufficient statistical accuracy and low lightweight. Therefore, in this study, the structure of the lightweight object detection model "You Only Live Once v3" is optimized, and the "Deep Simple Online Real-Time Tracking" algorithm with the "Person Re-Identification" module is designed, so as to construct a statistical model for people flow recognition. The results showed that the median PersonAP of the designed model was 94.2%, the total detection time was 216 ms, the Rank-1 and Rank-10 were 87.2% and 98.6%, respectively, and the maximum occupied memory of the whole test set was 2.57 MB, which was better than all comparison models. The results indicate that the intelligent identification statistical model for public crowd flow obtained through this design and training has higher statistical accuracy, less computational resource consumption, and faster computing speed. This has certain application space in the management and guidance of crowd flow in public places.

RESUMEN

Occluded person re-identification (Re-ID) is a challenging task, as pedestrians are often obstructed by various occlusions, such as non-pedestrian objects or non-target pedestrians. Previous methods have heavily relied on auxiliary models to obtain information in unoccluded regions, such as human pose estimation. However, these auxiliary models fall short in accounting for pedestrian occlusions, thereby leading to potential misrepresentations. In addition, some previous works learned feature representations from single images, ignoring the potential relations among samples. To address these issues, this paper introduces a Multi-Level Relation-Aware Transformer (MLRAT) model for occluded person Re-ID. This model mainly encompasses two novel modules: Patch-Level Relation-Aware (PLRA) and Sample-Level Relation-Aware (SLRA). PLRA learns fine-grained local features by modeling the structural relations between key patches, bypassing the dependency on auxiliary models. It adopts a model-free method to select key patches that have high semantic correlation with the final pedestrian representation. In particular, to alleviate the interference of occlusion, PLRA captures the structural relations among key patches via a two-layer Graph Convolution Network (GCN), effectively guiding the local feature fusion and learning. SLRA is designed to facilitate the model to learn discriminative features by modeling the relations among samples. Specifically, to mitigate noisy relations of irrelevant samples, we present a Relation-Aware Transformer (RAT) block to capture the relations among neighbors. Furthermore, to bridge the gap between training and testing phases, a self-distillation method is employed to transfer the sample-level relations captured by SLRA to the backbone. Extensive experiments are conducted on four occluded datasets, two partial datasets and two holistic datasets. The results show that the proposed MLRAT model significantly outperforms existing baselines on four occluded datasets, while maintains top performance on two partial datasets and two holistic datasets.

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

Movement of adult western corn rootworm, Diabrotica virgifera virgifera LeConte, is of fundamental importance to this species' population dynamics, ecology, evolution, and interactions with its environment, including cultivated cornfields. Realistic parameterization of dispersal components of models is needed to predict rates of range expansion, development, and spread of resistance to control measures and improve pest and resistance management strategies. However, a coherent understanding of western corn rootworm movement ecology has remained elusive because of conflicting evidence for both short- and long-distance lifetime dispersal, a type of dilemma observed in many species called Reid's paradox. Attempts to resolve this paradox using population genetic strategies to estimate rates of gene flow over space likewise imply greater dispersal distances than direct observations of short-range movement suggest, a dilemma called Slatkin's paradox. Based on the wide-array of available evidence, we present a conceptual model of adult western corn rootworm movement ecology under the premise it is a partially migratory species. We propose that rootworm populations consist of two behavioral phenotypes, resident and migrant. Both engage in local, appetitive flights, but only the migrant phenotype also makes non-appetitive migratory flights, resulting in observed patterns of bimodal dispersal distances and resolution of Reid's and Slatkin's paradoxes.

RESUMEN

With the increasing demand for person re-identification (Re-ID) tasks, the need for all-day retrieval has become an inevitable trend. Nevertheless, single-modal Re-ID is no longer sufficient to meet this requirement, making Multi-Modal Data crucial in Re-ID. Consequently, a Visible-Infrared Person Re-Identification (VI Re-ID) task is proposed, which aims to match pairs of person images from the visible and infrared modalities. The significant modality discrepancy between the modalities poses a major challenge. Existing VI Re-ID methods focus on cross-modal feature learning and modal transformation to alleviate the discrepancy but overlook the impact of person contour information. Contours exhibit modality invariance, which is vital for learning effective identity representations and cross-modal matching. In addition, due to the low intra-modal diversity in the visible modality, it is difficult to distinguish the boundaries between some hard samples. To address these issues, we propose the Graph Sampling-based Multi-stream Enhancement Network (GSMEN). Firstly, the Contour Expansion Module (CEM) incorporates the contour information of a person into the original samples, further reducing the modality discrepancy and leading to improved matching stability between image pairs of different modalities. Additionally, to better distinguish cross-modal hard sample pairs during the training process, an innovative Cross-modality Graph Sampler (CGS) is designed for sample selection before training. The CGS calculates the feature distance between samples from different modalities and groups similar samples into the same batch during the training process, effectively exploring the boundary relationships between hard classes in the cross-modal setting. Some experiments conducted on the SYSU-MM01 and RegDB datasets demonstrate the superiority of our proposed method. Specifically, in the VIS→IR task, the experimental results on the RegDB dataset achieve 93.69% for Rank-1 and 92.56% for mAP.

RESUMEN

Cross-modality person re-identification (ReID) aims at searching a pedestrian image of RGB modality from infrared (IR) pedestrian images and vice versa. Recently, some approaches have constructed a graph to learn the relevance of pedestrian images of distinct modalities to narrow the gap between IR modality and RGB modality, but they omit the correlation between IR image and RGB image pairs. In this paper, we propose a novel graph model called Local Paired Graph Attention Network (LPGAT). It uses the paired local features of pedestrian images from different modalities to build the nodes of the graph. For accurate propagation of information among the nodes of the graph, we propose a contextual attention coefficient that leverages distance information to regulate the process of updating the nodes of the graph. Furthermore, we put forward Cross-Center Contrastive Learning (C3L) to constrain how far local features are from their heterogeneous centers, which is beneficial for learning the completed distance metric. We conduct experiments on the RegDB and SYSU-MM01 datasets to validate the feasibility of the proposed approach.

RESUMEN

Walking gait data acquired with force platforms may be used for person re-identification (re-ID) in various authentication, surveillance, and forensics applications. Current force platform-based re-ID systems classify a fixed set of identities (IDs), which presents a problem when IDs are added or removed from the database. We formulated force platform-based re-ID as a deep metric learning (DML) task, whereby a deep neural network learns a feature representation that can be compared between inputs using a distance metric. The force platform dataset used in this study is one of the largest and the most comprehensive of its kind, containing 193 IDs with significant variations in clothing, footwear, walking speed, and time between trials. Several DML model architectures were evaluated in a challenging setting where none of the IDs were seen during training (i.e., zero-shot re-ID) and there was only one prior sample per ID to compare with each query sample. The best architecture was 85% accurate in this setting, though an analysis of changes in walking speed and footwear between measurement instances revealed that accuracy was 28% higher on same-speed, same-footwear comparisons, compared to cross-speed, cross-footwear comparisons. These results demonstrate the potential of DML algorithms for zero-shot re-ID using force platform data, and highlight challenging cases.

RESUMEN

The current popular one-shot multi-object tracking (MOT) algorithms are dominated by the joint detection and embedding paradigm, which have high inference speeds and accuracy, but their tracking performance is unstable in crowded scenes. Not only does the detection branch have difficulty in obtaining the accurate object position, but the ambiguous appearance of features extracted by the re-identification (re-ID) branch also leads to identity switches. Focusing on the above problems, this paper proposes a more robust MOT algorithm, named CSMOT, based on FairMOT. First, on the basis of the encoder-decoder network, a coordinate attention module is designed to enhance the information interaction between channels (horizontal and vertical coordinates), which improves its object-detection abilities. Then, an angle-center loss that effectively maximizes intra-class similarity is proposed to optimize the re-ID branch, and the extracted re-ID features are made more discriminative. We further redesign the re-ID feature dimension to balance the detection and re-ID tasks. Finally, a simple and effective data association mechanism is introduced, which associates each detection instead of just the high-score detections during the tracking process. The experimental results show that our one-shot MOT algorithm achieves excellent tracking performance on multiple public datasets and can be effectively applied to crowded scenes. In particular, CSMOT decreases the number of ID switches by 11.8% and 33.8% on the MOT16 and MOT17 test datasets, respectively, compared to the baseline.

RESUMEN

State-of-the-art purely unsupervised learning person re-ID methods first cluster all the images into multiple clusters and assign each clustered image a pseudo label based on the cluster result. Then, they construct a memory dictionary that stores all the clustered images, and subsequently train the feature extraction network based on this dictionary. All these methods directly discard the unclustered outliers in the clustering process and train the network only based on the clustered images. The unclustered outliers are complicated images containing different clothes and poses, with low resolution, severe occlusion, and so on, which are common in real-world applications. Therefore, models trained only on clustered images will be less robust and unable to handle complicated images. We construct a memory dictionary that considers complicated images consisting of both clustered and unclustered images, and design a corresponding contrastive loss by considering both kinds of images. The experimental results show that our memory dictionary that considers complicated images and contrastive loss can improve the person re-ID performance, which demonstrates the effectiveness of considering unclustered complicated images in unsupervised person re-ID.

RESUMEN

There are many authors who consider the so-called "moral nose" a valid epistemological tool in the field of morality. The expression was used by George Orwell, following in Friedrich Nietzsche's footsteps and was very clearly described by Leo Tolstoy. It has also been employed by authors such as Elisabeth Anscombe, Bernard Williams, Noam Chomsky, Stuart Hampshire, Mary Warnock, and Leon Kass. This article examines John Harris' detailed criticism of what he ironically calls the "olfactory school of moral philosophy." Harris' criticism is contrasted with Jonathan Glover's defense of the moral nose. Glover draws some useful distinctions between the various meanings that the notion of moral nose can assume. Finally, the notion of moral nose is compared with classic notions such as Aristotelian phronesis, Heideggerian aletheia, and the concept of "sentiment" proposed by the philosopher Thomas Reid. The conclusion reached is that morality cannot be based only on reason, or-as David Hume would have it-only on feelings.

RESUMEN

For more than two years, coronavirus disease 19 (COVID-19) has represented a threat to global health and lifestyles. Computed tomography (CT) imaging provides useful information in patients with COVID-19 pneumonia. However, this diagnostic modality is based on exposure to ionizing radiation, which is associated with an increased risk of radiation-induced cancer. In this study, we evaluated the common dose descriptors, CTDIvol and DLP, for 1180 adult patients. This data was used to estimate the effective dose, and risk of exposure-induced death (REID). Awareness of the extensive use of CT as a diagnostic tool in the management of COVID-19 during the pandemic is vital for the evaluation of radiation exposure parameters, dose reduction methods development and radiation protection.

RESUMEN

Visible thermal person re-identification (VT Re-ID) is the task of matching pedestrian images collected by thermal and visible light cameras. The two main challenges presented by VT Re-ID are the intra-class variation between pedestrian images and the cross-modality difference between visible and thermal images. Existing works have principally focused on local representation through cross-modality feature distribution, but ignore the internal connection of the local features of pedestrian body parts. Therefore, this paper proposes a dual-path attention network model to establish the spatial dependency relationship between the local features of the pedestrian feature map and to effectively enhance the feature extraction. Meanwhile, we propose cross-modality dual-constraint loss, which adds the center and boundary constraints for each class distribution in the embedding space to promote compactness within the class and enhance the separability between classes. Our experimental results show that our proposed approach has advantages over the state-of-the-art methods on the two public datasets SYSU-MM01 and RegDB. The result for the SYSU-MM01 is Rank-1/mAP 57.74%/54.35%, and the result for the RegDB is Rank-1/mAP 76.07%/69.43%.

RESUMEN

INTRODUCTION: The aim of this study is to evaluate the effective dose and cancer risk of examinations in EOS imaging system in different age and gender groups. MATERIALS AND METHODS: In total, 555 patients who had undergone common EOS imaging examinations were entered into the study. Exposure parameters and patients' characteristics for lower limb, full spine and full body imaging techniques, at different gender and age groups, were evaluated. Finally, effective dose and risk of exposure induced cancer death (REID) was calculated with the Monte Carlo based PCXMC software. RESULTS: The difference between average effective doses of male and female was not significant (p ≥ 0.05), however, the corresponding REID showed statistically significant difference (p ≤ 0.001). The average effective dose of patients (without considering technique, age and gender) was obtained as 0.13 mSv. The corresponding average REID was 8.84 per million. The maximum average effective dose value was obtained for patients over 10 years of age with the full body technique (0.17 ± 0.05 mSv). The maximum average REID value was obtained for full body technique and for patient with 0-10 years old (15.20 ± 10.00 per million). CONCLUSION: In common EOS imaging examinations, the effective dose and REID values of patients in both genders in all age groups are less than the corresponding values in other imaging modalities (according to previous studies). However, according to stochastic effects of ionizing radiation and based on the As Low As Reasonably Achievable (ALARA) principle, more considerations are necessary, especially in the full body technique and for female examinations.

Asunto(s)

RESUMEN

OBJECTIVES: To assess the effectiveness of colposcopy in detecting cervical lesions and to grade them according to Reid score and Swede score, and compare it with histopathology results. METHODS: This study was conducted on 130 patients in a tertiary care centre, who were subjected to pap smear and colposcopy. The cervical lesions were graded according to Reid score and Swede score, and a biopsy was obtained from the lesion. Histopathology results were correlated with colposcopy findings, and the scores were compared. RESULTS: The colposcopic findings using Reid score and Swede score correlated with histopathology results in the study population. The association between colposcopic impression and histopathology result was highly significant (p < 0.001), using both Reid score and Swede score. The sensitivity, specificity, PPV and NPV of Reid score (overall) was 86.2%, 80.20%, 55.56% and 95.3%, respectively. The diagnostic accuracy was 81.54%. At score > 5, specificity increased to 99% and diagnostic accuracy was 92.31%. The overall sensitivity, specificity, PPV, NPV and diagnostic accuracy of Swede score was 89.7%, 49.5%, 33.8%, 94.3% and 48.46%, respectively. As the cut off value increased, the sensitivity decreased. But the specificity, PPV, NPV and diagnostic accuracy increased and was statistically significant. The specificity and PPV was 100% at score > 8. CONCLUSION: As the cut off value increased, the diagnostic accuracy of both the Scores increased, and was more accurate in detecting high-grade lesions.

Asunto(s)

RESUMEN

As a crucial task in surveillance and security, person re-identification (re-ID) aims to identify the targeted pedestrians across multiple images captured by non-overlapping cameras. However, existing person re-ID solutions have two main challenges: the lack of pedestrian identification labels in the captured images, and domain shift issue between different domains. A generative adversarial networks (GAN)-based self-training framework with progressive augmentation (SPA) is proposed to obtain the robust features of the unlabeled data from the target domain, according to the preknowledge of the labeled data from the source domain. Specifically, the proposed framework consists of two stages: the style transfer stage (STrans), and self-training stage (STrain). First, the targeted data is complemented by a camera style transfer algorithm in the STrans stage, in which CycleGAN and Siamese Network are integrated to preserve the unsupervised self-similarity (the similarity of the same image between before and after transformation) and domain dissimilarity (the dissimilarity between a transferred source image and the targeted image). Second, clustering and classification are alternately applied to enhance the model performance progressively in the STrain stage, in which both global and local features of the target-domain images are obtained. Compared with the state-of-the-art methods, the proposed method achieves the competitive accuracy on two existing datasets.

RESUMEN

Person re-identification (Re-ID) is challenging due to host of factors: the variety of human positions, difficulties in aligning bounding boxes, and complex backgrounds, among other factors. This paper proposes a new framework called EXAM (EXtreme And Moderate feature embeddings) for Re-ID tasks. This is done using discriminative feature learning, requiring attention-based guidance during training. Here "Extreme" refers to salient human features and "Moderate" refers to common human features. In this framework, these types of embeddings are calculated by global max-pooling and average-pooling operations respectively; and then, jointly supervised by multiple triplet and cross-entropy loss functions. The processes of deducing attention from learned embeddings and discriminative feature learning are incorporated, and benefit from each other in this end-to-end framework. From the comparative experiments and ablation studies, it is shown that the proposed EXAM is effective, and its learned feature representation reaches state-of-the-art performance.

RESUMEN

During the first half of the 1970s, climate research gained a new significance and began to be perceived within political and academic circles as being worthy of public support. Conventional explanations for this increased status include a series of climate anomalies that generated awareness and heightened concern over the potentially devastating effects of climate change. Controversial climatologist Reid Bryson was one of the first to publicly promote what he saw as a definitive link between these climate anomalies and unidirectional climate change in the fall of 1973, and rising food prices in the same year gave him a platform on which to air his views to receptive senior members of the US Congress. Bryson's testimony before a US Senate subcommittee offers a unique glimpse into how he was able to successfully resonate his agenda with that of senior politicians in a time of crisis, as well as the immediate responses of those senior US politicians upon first hearing climate change arguments. Bryson was one of the most prominent US climatologists to break a taboo against making bold climatological predictions and de-facto policy recommendations in public. As a result, although Bryson was criticized by many in the climatological community, his actions instigated the involvement of other scientists in the public arena, leading to an important elevation in US public climate discourse.

RESUMEN

This retrospective cohort study focused on colposcopic accuracy for the diagnosis of cervical premalignant lesions using cytology and histology, as well as HPV data not included in current cervical screening practices in Kazakhstan. Colposcopy performance was assessed using the modified Reid index in women aged 18-63 years. In total, 1,129 colposcopic-HPV-cytology triple samples and 94 histology findings were collected. The sensitivity of colposcopy was 81.6% with specificity 72.6% for LSIL but fell to 56.6% with specificity 88.3% for CIN2+ vs. 89.6% and 74.5% for cytology at CIN2+, respectively. The ORs for high-grade lesion occurrence within each colposcopy group at viral load rising vs. ORs for HPV-negative women were 3.4; 5.3; and 39.7, respectively (p < 0.0001). Total attributive agreement between the colposcopy and histology findings reached 55.3%, κ 0.47 ± 0.06 vs. 0.62 ± 0.08 for cytology, and 0.34 ± 0.13 and 0.58 ± 0.1, for specialists, respectively. Outcomes obtained for colposcopy alone failed to show satisfactory reliability. Globally adopted primary HPV screening would be the best option despite the related costs.