We present X-ray source catalogs for the ≈7 Ms exposure of the Chandra Deep Field-South (CDF-S), which covers a total area of 484.2 arcmin². Utilizing wavdetect for initial source detection and ACIS Extract for photometric extraction and significance assessment, we create a main source catalog containing 1008 sources that are detected in up to three X-ray bands: 0.5–7.0 keV, 0.5–2.0 keV, and 2–7 keV. A supplementary source catalog is also provided, including 47 lower-significance sources that have bright ( ) near-infrared counterparts. We identify multiwavelength counterparts for 992 (98.4%) of the main-catalog sources, and we collect redshifts for 986 of these sources, including 653 spectroscopic redshifts and 333 photometric redshifts. Based on the X-ray and multiwavelength properties, we identify 711 active galactic nuclei (AGNs) from the main-catalog sources. Compared to the previous ≈4 Ms CDF-S catalogs, 291 of the main-catalog sources are new detections. We have achieved unprecedented X-ray sensitivity with average flux limits over the central ≈1 arcmin² region of ≈1.9 × 10⁻¹⁷, 6.4 × 10⁻¹⁸, and 2.7 × 10⁻¹⁷ erg cm⁻² s⁻¹ in the three X-ray bands, respectively. We provide cumulative number-count measurements observing, for the first time, that normal galaxies start to dominate the X-ray source population at the faintest 0.5–2.0 keV flux levels. The highest X-ray source density reaches ≈50,500 deg⁻², and 47% ± 4% of these sources are AGNs (≈23,900 deg⁻²).

RGBT tracking receives a surge of interest in the computer vision community, but this research field lacks a large-scale and high-diversity benchmark dataset, which is essential for both the training of deep RGBT trackers and the comprehensive evaluation of RGBT tracking methods. To this end, we present a La rge- ${s}$ cale ${H}$ igh-diversity $\text{b}{e}$ nchmark for short-term ${R}$ GBT tracking (LasHeR) in this work. LasHeR consists of 1224 visible and thermal infrared video pairs with more than 730K frame pairs in total. Each frame pair is spatially aligned and manually annotated with a bounding box, making the dataset well and densely annotated. LasHeR is highly diverse capturing from a broad range of object categories, camera viewpoints, scene complexities and environmental factors across seasons, weathers, day and night. We conduct a comprehensive performance evaluation of 12 RGBT tracking algorithms on the LasHeR dataset and present detailed analysis. In addition, we release the unaligned version of LasHeR to attract the research interest for alignment-free RGBT tracking, which is a more practical task in real-world applications. The datasets and evaluation protocols are available at: https://github.com/mmic-lcl/Datasets-and-benchmark-code .

We present measurements of the evolution of normal-galaxy X-ray emission from 0–7 using local galaxies and galaxy samples in the ≈6 Ms Chandra Deep Field-South (CDF-S) survey. The majority of the CDF-S galaxies are observed at rest-frame energies above 2 keV, where the emission is expected to be dominated by X-ray binary (XRB) populations; however, hot gas is expected to provide small contributions to the observed-frame ≲1 keV emission at z ≲ 1. We show that a single scaling relation between X-ray luminosity ( ) and star-formation rate (SFR) literature, is insufficient for characterizing the average X-ray emission at all redshifts. We establish that scaling relations involving not only SFR, but also stellar mass ( ) and redshift, provide significantly improved characterizations of the average X-ray emission from normal galaxy populations at 0–7. We further provide the first empirical constraints on the redshift evolution of X-ray emission from both low-mass XRB (LMXB) and high-mass XRB (HMXB) populations and their scalings with and SFR, respectively. We find (LMXB)/ and (HMXB)/SFR , and show that these relations are consistent with XRB population-synthesis model predictions, which attribute the increase in LMXB and HMXB scaling relations with redshift as being due to declining host galaxy stellar ages and metallicities, respectively. We discuss how emission from XRBs could provide an important source of heating to the intergalactic medium in the early universe, exceeding that of active galactic nuclei.

This paper presents a simple yet effective method called Category-wise Fusion and Enhancement learning (CaFE), which leverages the category priors to achieve effective feature fusion and imbalance learning, for multi-modal remote sensing image semantic segmentation. In particular, we disentangle the feature fusion process via the categories to achieve the category-wise fusion based on the fact that the feature fusion in the same category regions tends to have similar characteristics. The disentangled fusion would also increase the fusion capacity with a small number of parameters while reducing the dependence on large-scale training data. For the sample imbalance problem, we design a simple yet effective category-wise enhancement learning scheme. In particular, we assign the weight for each category region based on the proportion of samples in this region over the whole image. By this way, the learning algorithm would focus more on the regions with smaller proportion. Note that both category-wise feature fusion and imbalance learning are only performed in the training stage, and the segmentation efficiency is thus not affected. Experimental results on two benchmark datasets demonstrate the effectiveness of our CaFE against other state-of-the-art methods.

RGBT tracking has attracted increasing attention since RGB and thermal infrared data have strong complementary advantages, which could make trackers all-day and all-weather work. Existing works usually focus on extracting modality-shared or modality-specific information, but the potentials of these two cues are not well explored and exploited in RGBT tracking. In this paper, we propose a novel multi-adapter network to jointly perform modality-shared, modality-specific and instance-aware target representation learning for RGBT tracking. To this end, we design three kinds of adapters within an end-to-end deep learning framework. In specific, we use the modified VGG-M as the generality adapter to extract the modality-shared target representations. To extract the modality-specific features while reducing the computational complexity, we design a modality adapter, which adds a small block to the generality adapter in each layer and each modality in a parallel manner. Such a design could learn multilevel modality-specific representations with a modest number of parameters as the vast majority of parameters are shared with the generality adapter. We also design instance adapter to capture the appearance properties and temporal variations of a certain target. Moreover, to enhance the shared and specific features, we employ the loss of multiple kernel maximum mean discrepancy to measure the distribution divergence of different modal features and integrate it into each layer for more robust representation learning. Extensive experiments on two RGBT tracking benchmark datasets demonstrate the outstanding performance of the proposed tracker against the state-of-the-art methods.