Object detection has recently experienced substantial progress. Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts. In this paper, we propose a simple yet effective framework to detect multi-oriented objects. Instead of directly regressing the four vertices, we glide the vertex of the horizontal bounding box on each corresponding side to accurately describe a multi-oriented object. Specifically, We regress four length ratios characterizing the relative gliding offset on each corresponding side. This may facilitate the offset learning and avoid the confusion issue of sequential label points for oriented objects. To further remedy the confusion issue for nearly horizontal objects, we also introduce an obliquity factor based on area ratio between the object and its horizontal bounding box, guiding the selection of horizontal or oriented detection for each object. We add these five extra target variables to the regression head of fast R-CNN, which requires ignorable extra computation time. Extensive experimental results demonstrate that without bells and whistles, the proposed method achieves superior performances on multiple multi-oriented object detection benchmarks including object detection in aerial images, scene text detection, pedestrian detection in fisheye images.
Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. Automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their method on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge (https://wmh.isi.uu.nl/). Sixty T1+FLAIR images from three MR scanners were released with manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. Segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: (1) Dice similarity coefficient, (2) modified Hausdorff distance (95th percentile), (3) absolute log-transformed volume difference, (4) sensitivity for detecting individual lesions, and (5) F1-score for individual lesions. Additionally, methods were ranked on their inter-scanner robustness.Twenty participants submitted their method for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all methods generalize to unseen scanners.The challenge remains open for future submissions and provides a public platform for method evaluation.
BackgroundOrganisms need to adapt to keep pace with a changing environment. Examining recent range expansion aids our understanding of how organisms evolve to overcome environmental constraints. However, how organisms adapt to climate changes is a crucial biological question that is still largely unanswered. The plant Arabidopsis thaliana is an excellent system to study this fundamental question. Its origin is in the Iberian Peninsula and North Africa, but it has spread to the Far East, including the most south-eastern edge of its native habitats, the Yangtze River basin, where the climate is very different.ResultsWe sequenced 118 A. thaliana strains from the region surrounding the Yangtze River basin. We found that the Yangtze River basin population is a unique population and diverged about 61,409 years ago, with gene flows occurring at two different time points, followed by a population dispersion into the Yangtze River basin in the last few thousands of years. Positive selection analyses revealed that biological regulation processes, such as flowering time, immune and defense response processes could be correlated with the adaptation event. In particular, we found that the flowering time gene SVP has contributed to A. thaliana adaptation to the Yangtze River basin based on genetic mapping.Conclusions A. thaliana adapted to the Yangtze River basin habitat by promoting the onset of flowering, a finding that sheds light on how a species can adapt to locales with very different climates.Electronic supplementary materialThe online version of this article (doi:10.1186/s13059-017-1378-9) contains supplementary material, which is available to authorized users.
Person re-identification (Re-ID) requires discriminative features focusing on the full person to cope with inaccurate person bounding box detection, background clutter, and occlusion. Many recent person Re-ID methods attempt to learn such features describing full person details via part-based feature representation. However, the spatial context between these parts is ignored for the independent extractor on each separate part. In this paper, we propose to apply Long Short-Term Memory (LSTM) in an end-to-end way to model the pedestrian, seen as a sequence of body parts from head to foot. Integrating the * Corresponding author
Scene text detection is an important step of scene text reading system. The main challenges lie on significantly varied sizes and aspect ratios, arbitrary orientations and shapes. Driven by recent progress in deep learning, impressive performances have been achieved for multi-oriented text detection. Yet, the performance drops dramatically in detecting curved texts due to the limited text representation (e.g., horizontal bounding boxes, rotated rectangles, or quadrilaterals). It is of great interest to detect curved texts, which are actually very common in natural scenes. In this paper, we present a novel text detector named TextField for detecting irregular scene texts. Specifically, we learn a direction field pointing away from the nearest text boundary to each text point. This direction field is represented by an image of two-dimensional vectors and learned via a fully convolutional neural network. It encodes both binary text mask and direction information used to separate adjacent text instances, which is challenging for classical segmentationbased approaches. Based on the learned direction field, we apply a simple yet effective morphological-based post-processing to achieve the final detection. Experimental results show that the proposed TextField outperforms the state-of-the-art methods by a large margin (28% and 8%) on two curved text datasets: Total-Text and SCUT-CTW1500, respectively, and also achieves very competitive performance on multi-oriented datasets: IC-DAR 2015 and MSRA-TD500. Furthermore, TextField is robust in generalizing to unseen datasets. The code is available at https://github.com/YukangWang/TextField.
Rapid phenotypic changes in traits of adaptive significance are crucial for organisms to thrive in changing environments. How such phenotypic variation is achieved rapidly, despite limited genetic variation in species that experience a genetic bottleneck is unknown.Capsella rubella, an annual and inbreeding forb (Brassicaceae), is a great system for studying this basic question. Its distribution is wider than those of its congeneric species, despite an extreme genetic bottleneck event that severely diminished its genetic variation. Here, we demonstrate that transposable elements (TEs) are an important source of genetic variation that could account for its high phenotypic diversity. TEs are (i) highly enriched inC. rubellacompared with its outcrossing sister speciesCapsella grandiflora, and (ii) 4.2% of polymorphic TEs inC. rubellaare associated with variation in the expression levels of their adjacent genes. Furthermore, we show that frequent TE insertions atFLOWERING LOCUS C (FLC)in natural populations ofC. rubellacould explain 12.5% of the natural variation in flowering time, a key life history trait correlated with fitness and adaptation. In particular, we show that a recent TE insertion at the 3′ UTR ofFLCaffects mRNA stability, which results in reducing its steady-state expression levels, to promote the onset of flowering. Our results highlight that TE insertions can drive rapid phenotypic variation, which could potentially help with adaptation to changing environments in a species with limited standing genetic variation.
Accurate segmentation of infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is an indispensable foundation for early studying of brain growth patterns and morphological changes in neurodevelopmental disorders. Nevertheless, in the isointense phase (approximately 6-9 months of age), due to inherent myelination and maturation process, WM and GM exhibit similar levels of intensity in both T1-weighted (T1w) and T2-weighted (T2w) MR images, making tissue segmentation very challenging. Despite many efforts devoted to brain segmentation, only few studies have focused on the segmentation of 6-month infant brain images. With the idea of boosting methodological development in the community, iSeg-2017 challenge (http://iseg2017.web.unc.edu) provides a set of 6-month infant subjects with manual labels for training and testing the participating methods. Among the 21 automatic segmentation methods participating in iSeg-2017, we review the 8 top-ranked teams, in terms of Dice ratio, modified Hausdorff distance and average surface distance, and introduce their
Dense crowd counting aims to predict thousands of human instances from an image, by calculating integrals of a density map over image pixels. Existing approaches mainly suffer from the extreme density variances. Such density pattern shift poses challenges even for multi-scale model ensembling. In this paper, we propose a simple yet effective approach to tackle this problem. First, a patch-level density map is extracted by a density estimation model and further grouped into several density levels which are determined over full datasets. Second, each patch density map is automatically normalized by an online center learning strategy with a multipolar center loss. Such a design can significantly condense the density distribution into several clusters, and enable that the density variance can be learned by a single model. Extensive experiments demonstrate the superiority of the proposed method. Our work outperforms the state-of-the-art by 4.Sparse Medium Dense (a) Shanghai-B Shanghai-A UCF_CC_50 UCF-QNRF Dataset 0.00 0.05 0.10 0.15 0.20 0.25 0.30 0.35 Mean Relative Error MRE Overview Ours MCNN [33] Switch-CNN [23] CMTL [27] ACSCP [24] SANet [3] CSRNet [15] CP-CNN [28] L2R [18] D-ConvNet-v1 [25] ic-CNN [22] arXiv:1907.12428v2 [cs.CV]
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.