相关论文: Radio Sources Segmentation and Classification with…

Deep radio observations at 1.4GHz for the Extended Chandra Deep Field South were performed in June through September of 2007 and presented in a first data release (Miller et al. 2008). The survey was made using six separate pointings of the…

Active Galactic Nuclei (AGN) can often be identified in radio images as two lobes, sometimes connected to a core by a radio jet. This multi-component morphology unfortunately creates difficulties for source-finders, leading to components…

The field of radio astronomy is witnessing a boom in the amount of data produced per day due to newly commissioned radio telescopes. One of the most crucial problems in this field is the automatic classification of extragalactic radio…

New-generation radio telescopes like LOFAR are conducting extensive sky surveys, detecting millions of sources. To maximise the scientific value of these surveys, radio source components must be properly associated into physical sources…

In this second paper of the Hawaii SCUBA-2 Lensing Cluster Survey series, we cross-match SCUBA-2 maps with 3 and 6 GHz images from the Janksy-VLA Frontier Fields Legacy Survey for three cluster fields, MACS J0416.1--2403, MACS J0717.5+3745,…

Using the JVLA, we explored the Galactic center (GC) with a resolution of 0.05" at 33.0 and 44.6 GHz. We detected 64 hyper-compact radio sources (HCRs) in the central parsec. The dense group of HCRs can be divided into three spectral types:…

We report the results of optical identification of a sample of RC catalog radio sources with the FIRST and SDSS surveys. For 320 sources identified with NVSS and FIRST objects we perform optical identification with the SDSS survey. When…

We positionally match the 6 cm GB6, 20 cm FIRST and NVSS, and 92 cm WENSS radio catalogs and find 16,500 matches in ~3,000 deg2 of sky. Using this unified radio database, we construct radio "color-magnitude-morphology" diagrams and find…

We carried out a large program with the Karl G. Jansky Very Large Array (VLA): "THOR: The HI, OH, Recombination line survey of the Milky Way". We observed a significant portion of the Galactic plane in the first quadrant of the Milky Way in…

Classification of HEp-2 cell patterns plays a significant role in the indirect immunofluorescence test for identifying autoimmune diseases in the human body. Many automatic HEp-2 cell classification methods have been proposed in recent…

Future deep HI surveys will be essential for understanding the nature of galaxies and the content of the Universe. However, the large volume of these data will require distributed and automated processing techniques. We introduce LiSA, a…

We present a novel multimodal neural network (MNN) for classifying astronomical sources in multiband ground-based observations, from optical to near infrared, to separate sources in stars, galaxies and quasars. Our approach combines a…

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that…

A new sample of radio sources, with the designated name CENSORS (A Combined EIS-NVSS Survey Of Radio Sources), has been defined by combining the NRAO VLA Sky Survey (NVSS) at 1.4 GHz with the ESO Imaging Survey (EIS) Patch D, a 3 by 2…

We present the largest visually selected sample of extended ($>$60 arcsec) radio-loud active galactic nuclei (RLAGN) to date, based on the LOw-Frequency Array Two-Metre Sky Survey second data release (LoTSS DR2). From the broader LoTSS DR2…

This paper presents a deep learning approach to the classification of 160 shortwave radio signals. It addresses the typical challenges of the shortwave spectrum, which are the large number of different signal types, the presence of various…

(Abridged) We construct a catalog of radio sources detected by the GB6 (6 cm), FIRST and NVSS (20 cm), and WENSS (92 cm) radio surveys, and the SDSS optical survey. The 2.7 million entries in the publicly-available master catalog are…

Deep neural network based methods have been successfully applied to music source separation. They typically learn a mapping from a mixture spectrogram to a set of source spectrograms, all with magnitudes only. This approach has several…

The continuum emission from 1 to 2 GHz of The HI/OH/Recombination line survey of the inner Milky Way (THOR) at $\lesssim$18" resolution covers $\sim 132$ square degrees of the Galactic plane and detects 10387 sources. Similarly, the first…

Accurate building segmentation from high-resolution RGB imagery remains challenging due to spectral similarity with non-building features, shadows, and irregular building geometries. In this study, we present a comprehensive deep learning…