arXiv subjects

Bin Luo

Publications and source records attributed to Bin Luo.

At least 199 records · Page 11Linked to original sources

arXiv2021

LasHeR: A Large-scale High-diversity Benchmark for RGBT Tracking

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 Large-scale High-diversity benchmark for RGBT 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 to clarify the research room in RGBT tracking. 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/BUGPLEASEOUT/LasHeR.

cs.CV↗

arXiv2021

Attributes Guided Feature Learning for Vehicle Re-identification

Vehicle Re-ID has recently attracted enthusiastic attention due to its potential applications in smart city and urban surveillance. However, it suffers from large intra-class variation caused by view variations and illumination changes, and inter-class similarity especially for different identities with the similar appearance. To handle these issues, in this paper, we propose a novel deep network architecture, which guided by meaningful attributes including camera views, vehicle types and colors for vehicle Re-ID. In particular, our network is end-to-end trained and contains three subnetworks of deep features embedded by the corresponding attributes (i.e., camera view, vehicle type and vehicle color). Moreover, to overcome the shortcomings of limited vehicle images of different views, we design a view-specified generative adversarial network to generate the multi-view vehicle images. For network training, we annotate the view labels on the VeRi-776 dataset. Note that one can directly adopt the pre-trained view (as well as type and color) subnetwork on the other datasets with only ID information, which demonstrates the generalization of our model. Extensive experiments on the benchmark datasets VeRi-776 and VehicleID suggest that the proposed approach achieves the promising performance and yields to a new state-of-the-art for vehicle Re-ID.

cs.CV↗

arXiv2021

Robust Graph Data Learning via Latent Graph Convolutional Representation

Graph Convolutional Representation (GCR) has achieved impressive performance for graph data representation. However, existing GCR is generally defined on the input fixed graph which may restrict the representation capacity and also be vulnerable to the structural attacks and noises. To address this issue, we propose a novel Latent Graph Convolutional Representation (LatGCR) for robust graph data representation and learning. Our LatGCR is derived based on reformulating graph convolutional representation from the aspect of graph neighborhood reconstruction. Given an input graph $\textbf{A}$, LatGCR aims to generate a flexible latent graph $\widetilde{\textbf{A}}$ for graph convolutional representation which obviously enhances the representation capacity and also performs robustly w.r.t graph structural attacks and noises. Moreover, LatGCR is implemented in a self-supervised manner and thus provides a basic block for both supervised and unsupervised graph learning tasks. Experiments on several datasets demonstrate the effectiveness and robustness of LatGCR.

cs.CV↗

arXiv2021

A High-dimensional M-estimator Framework for Bi-level Variable Selection

In high-dimensional data analysis, bi-level sparsity is often assumed when covariates function group-wisely and sparsity can appear either at the group level or within certain groups. In such cases, an ideal model should be able to encourage the bi-level variable selection consistently. Bi-level variable selection has become even more challenging when data have heavy-tailed distribution or outliers exist in random errors and covariates. In this paper, we study a framework of high-dimensional M-estimation for bi-level variable selection. This framework encourages bi-level sparsity through a computationally efficient two-stage procedure. In theory, we provide sufficient conditions under which our two-stage penalized M-estimator possesses simultaneous local estimation consistency and the bi-level variable selection consistency if certain nonconvex penalty functions are used at the group level. Both our simulation studies and real data analysis demonstrate satisfactory finite sample performance of the proposed estimators under different irregular settings.

stat.ME↗

arXiv2021

RiWNet: A moving object instance segmentation Network being Robust in adverse Weather conditions

Segmenting each moving object instance in a scene is essential for many applications. But like many other computer vision tasks, this task performs well in optimal weather, but then adverse weather tends to fail. To be robust in weather conditions, the usual way is to train network in data of given weather pattern or to fuse multiple sensors. We focus on a new possibility, that is, to improve its resilience to weather interference through the network's structural design. First, we propose a novel FPN structure called RiWFPN with a progressive top-down interaction and attention refinement module. RiWFPN can directly replace other FPN structures to improve the robustness of the network in non-optimal weather conditions. Then we extend SOLOV2 to capture temporal information in video to learn motion information, and propose a moving object instance segmentation network with RiWFPN called RiWNet. Finally, in order to verify the effect of moving instance segmentation in different weather disturbances, we propose a VKTTI-moving dataset which is a moving instance segmentation dataset based on the VKTTI dataset, taking into account different weather scenes such as rain, fog, sunset, morning as well as overcast. The experiment proves how RiWFPN improves the network's resilience to adverse weather effects compared to other FPN structures. We compare RiWNet to several other state-of-the-art methods in some challenging datasets, and RiWNet shows better performance especially under adverse weather conditions.

cs.CV↗

arXiv2021

Reverberation Mapping of Two Luminous Quasars: the Broad-line Region Structure and Black Hole Mass

We report the results of a multi-year spectroscopic and photometric monitoring campaign of two luminous quasars, PG~0923+201 and PG~1001+291, both located at the high-luminosity end of the broad-line region (BLR) size-luminosity relation with optical luminosities above $10^{45}~{\rm erg~s^{-1}}$. PG~0923+201 is for the first time monitored, and PG~1001+291 was previously monitored but our campaign has a much longer temporal baseline. We detect time lags of variations of the broad H$β$, H$γ$, Fe {\sc ii} lines with respect to those of the 5100~Å continuum. The velocity-resolved delay map of H$β$ in PG~0923+201 indicates a complicated structure with a mix of Keplerian disk-like motion and outflow, and the map of H$β$ in PG~1001+291 shows a signature of Keplerian disk-like motion. Assuming a virial factor of $f_{\rm BLR}=1$ and FWHM line widths, we measure the black hole mass to be $118_{-16}^{+11}\times 10^7 M_{\odot}$ for PG~0923+201 and $3.33_{-0.54}^{+0.62}\times 10^7 M_{\odot}$ for PG~1001+291. Their respective accretion rates are estimated to be $0.21_{-0.07}^{+0.06} \times L_{\rm Edd}\,c^{-2}$ and $679_{-227}^{+259}\times L_{\rm Edd}\,c^{-2}$, indicating that PG~0923+201 is a sub-Eddington accretor and PG~1001+291 is a super-Eddington accretor. While the H$β$ time lag of PG~0923+201 agrees with the size-luminosity relation, the time lag of PG~1001+291 shows a significant deviation, confirming that in high-luminosity AGN the BLR size depends on both luminosity and Eddington ratio. Black hole mass estimates from single AGN spectra will be over-estimated at high luminosities and redshifts if this effect is not taken into account.

astro-ph.GA↗

arXiv2021

Tracking by Joint Local and Global Search: A Target-aware Attention based Approach

Tracking-by-detection is a very popular framework for single object tracking which attempts to search the target object within a local search window for each frame. Although such local search mechanism works well on simple videos, however, it makes the trackers sensitive to extremely challenging scenarios, such as heavy occlusion and fast motion. In this paper, we propose a novel and general target-aware attention mechanism (termed TANet) and integrate it with tracking-by-detection framework to conduct joint local and global search for robust tracking. Specifically, we extract the features of target object patch and continuous video frames, then we concatenate and feed them into a decoder network to generate target-aware global attention maps. More importantly, we resort to adversarial training for better attention prediction. The appearance and motion discriminator networks are designed to ensure its consistency in spatial and temporal views. In the tracking procedure, we integrate the target-aware attention with multiple trackers by exploring candidate search regions for robust tracking. Extensive experiments on both short-term and long-term tracking benchmark datasets all validated the effectiveness of our algorithm. The project page of this paper can be found at \url{https://sites.google.com/view/globalattentiontracking/home/extend}.

cs.CV↗

arXiv2021

RGBT Tracking via Multi-Adapter Network with Hierarchical Divergence Loss

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. However, how to effectively represent RGBT data for visual tracking remains unstudied well. 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.

cs.CV↗

arXiv2021

Dynamic Attention guided Multi-Trajectory Analysis for Single Object Tracking

Most of the existing single object trackers track the target in a unitary local search window, making them particularly vulnerable to challenging factors such as heavy occlusions and out-of-view movements. Despite the attempts to further incorporate global search, prevailing mechanisms that cooperate local and global search are relatively static, thus are still sub-optimal for improving tracking performance. By further studying the local and global search results, we raise a question: can we allow more dynamics for cooperating both results? In this paper, we propose to introduce more dynamics by devising a dynamic attention-guided multi-trajectory tracking strategy. In particular, we construct dynamic appearance model that contains multiple target templates, each of which provides its own attention for locating the target in the new frame. Guided by different attention, we maintain diversified tracking results for the target to build multi-trajectory tracking history, allowing more candidates to represent the true target trajectory. After spanning the whole sequence, we introduce a multi-trajectory selection network to find the best trajectory that delivers improved tracking performance. Extensive experimental results show that our proposed tracking strategy achieves compelling performance on various large-scale tracking benchmarks. The project page of this paper can be found at https://sites.google.com/view/mt-track/.

cs.CV↗

arXiv2021

Reversible data hiding in encrypted images based on pixel prediction and multi-MSB planes rearrangement

Great concern has arisen in the field of reversible data hiding in encrypted images (RDHEI) due to the development of cloud storage and privacy protection. RDHEI is an effective technology that can embed additional data after image encryption, extract additional data error-free and reconstruct original images losslessly. In this paper, a high-capacity and fully reversible RDHEI method is proposed, which is based on pixel prediction and multi-MSB (most significant bit) planes rearrangement. First, the median edge detector (MED) predictor is used to calculate the predicted value. Next, unlike previous methods, in our proposed method, signs of prediction errors (PEs) are represented by one bit plane and absolute values of PEs are represented by other bit planes. Then, we divide bit planes into uniform blocks and non-uniform blocks, and rearrange these blocks. Finally, according to different pixel prediction schemes, different numbers of additional data are embedded adaptively. The experimental results prove that our method has higher embedding capacity compared with state-of-the-art RDHEI methods.

cs.MM↗

arXiv2021

Chandra and Magellan/FIRE follow-up observations of PSO167-13: an X-ray weak QSO at $z=6.515$

The discovery of hundreds of QSOs in the first Gyr of the Universe powered by already grown SMBHs challenges our knowledge of SMBH formation. In particular, investigations of $z>6$ QSOs presenting notable properties can provide unique information on the physics of fast SMBH growth in the early universe. We present the results of follow-up observations of the $z=6.515$ radio-quiet QSO PSO167-13, which is interacting with a close companion galaxy. The PSO167-13 system has been recently proposed to host the first heavily obscured X-ray source at high redshift. We observed PSO167-13 with Chandra/ACIS-S (177 ks), and obtained new spectroscopic observations (7.2 h) with Magellan/FIRE. No significant X-ray emission is detected from the PSO167-13 system, suggesting that the obscured X-ray source previously tentatively detected was either due to a strong background fluctuation or is highly variable. The upper limit (90% confidence level) on the X-ray emission of PSO167-13 ($L_{2-10\,\mathrm{keV}}<8.3\times10^{43}\,\mathrm{erg s^{-1}}$) is the lowest available for a $z>6$ QSO. The ratio between the X-ray and UV luminosity of $α_{ox}<-1.95$ makes PSO167-13 a strong outlier from the $α_{ox}-L_{UV}$ and $L_X-L_{\mathrm{bol}}$ relations. In particular, its X-ray emission is $>6$ times weaker than the expectation based on its UV luminosity. The new Magellan/FIRE spectrum of PSO167-13 is strongly affected by the unfavorable sky conditions, but the tentatively detected C IV and Mg II emission lines appear strongly blueshifted. The most plausible explanations for the X-ray weakness of PSO167-13 are intrinsic weakness or small-scale absorption by Compton-thick material. The possible strong blueshift of its emission lines hints at the presence of nuclear winds, which could be related to its X-ray weakness.

astro-ph.GA↗

arXiv2021

PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack

The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs). However, the performance of emerging attacks is negatively impacted when fooling DNNs tailored for high-resolution images. One of the explanations is that these methods usually focus on attacking the entire image, regardless of its spatial semantic information, and thereby encounter the notorious curse of dimensionality. To this end, we propose a pixel correlation-based attentional black-box adversarial attack, termed as PICA. Firstly, we take only one of every two neighboring pixels in the salient region as the target by leveraging the attentional mechanism and pixel correlation of images, such that the dimension of the black-box attack reduces. After that, a general multiobjective evolutionary algorithm is employed to traverse the reduced pixels and generate perturbations that are imperceptible by the human vision. Extensive experimental results have verified the effectiveness of the proposed PICA on the ImageNet dataset. More importantly, PICA is computationally more efficient to generate high-resolution adversarial examples compared with the existing black-box attacks.

cs.CV↗

arXiv2020

Object Detection based on OcSaFPN in Aerial Images with Noise

Taking the deep learning-based algorithms into account has become a crucial way to boost object detection performance in aerial images. While various neural network representations have been developed, previous works are still inefficient to investigate the noise-resilient performance, especially on aerial images with noise taken by the cameras with telephoto lenses, and most of the research is concentrated in the field of denoising. Of course, denoising usually requires an additional computational burden to obtain higher quality images, while noise-resilient is more of a description of the robustness of the network itself to different noises, which is an attribute of the algorithm itself. For this reason, the work will be started by analyzing the noise-resilient performance of the neural network, and then propose two hypotheses to build a noise-resilient structure. Based on these hypotheses, we compare the noise-resilient ability of the Oct-ResNet with frequency division processing and the commonly used ResNet. In addition, previous feature pyramid networks used for aerial object detection tasks are not specifically designed for the frequency division feature maps of the Oct-ResNet, and they usually lack attention to bridging the semantic gap between diverse feature maps from different depths. On the basis of this, a novel octave convolution-based semantic attention feature pyramid network (OcSaFPN) is proposed to get higher accuracy in object detection with noise. The proposed algorithm tested on three datasets demonstrates that the proposed OcSaFPN achieves a state-of-the-art detection performance with Gaussian noise or multiplicative noise. In addition, more experiments have proved that the OcSaFPN structure can be easily added to existing algorithms, and the noise-resilient ability can be effectively improved.

cs.CV↗

arXiv2020

The frequency of extreme X-ray variability of radio-quiet quasars

We analyze 1598 serendipitous Chandra X-ray observations of 462 radio-quiet quasars to constrain the frequency of extreme amplitude X-ray variability that is intrinsic to the quasar corona and innermost accretion flow. The quasars in this investigation are all spectroscopically confirmed, optically bright ($m_i \leq$ 20.2), and contain no identifiable broad absorption lines in their optical/ultraviolet spectra. This sample includes quasars spanning $z \approx$ 0.1 - 4 and probes X-ray variability on timescales of up to $\approx$ 12 rest-frame years. Variability amplitudes are computed between every epoch of observation for each quasar and are analyzed as a function of timescale and luminosity. The tail-heavy distributions of variability amplitudes at all timescales indicate that extreme X-ray variations are driven by an additional physical mechanism and not just typical random fluctuations of the coronal emission. Similarly, extreme X-ray variations of low-luminosity quasars seem to be driven by an additional physical mechanism, whereas high-luminosity quasars seem more consistent with random fluctuations. The amplitude at which an X-ray variability event can be considered extreme is quantified for different timescales and luminosities. Extreme X-ray variations occur more frequently at long timescales ( $Δt \gtrsim$ 300 days) than at shorter timescales, and in low-luminosity quasars compared to high-luminosity quasars over a similar timescale. A binomial analysis indicates that extreme intrinsic X-ray variations are rare, with a maximum occurrence rate of <2.4% of observations. Finally, we present X-ray variability and basic optical emission-line properties of three archival quasars that have been newly discovered to exhibit extreme X-ray variability.

astro-ph.HE↗

arXiv2020

Piercing through Highly Obscured and Compton-thick AGNs in the Chandra Deep Fields. II. Are Highly Obscured AGNs the Missing Link in the Merger-Triggered AGN-Galaxy Coevolution Models?

By using a large highly obscured ($N_{\rm H} > 10^{23}\ \rm cm^{-2}$) AGN sample (294 sources at $z \sim 0-5$) selected from detailed X-ray spectral analyses in the deepest Chandra surveys, we explore distributions of these X-ray sources in various optical/IR/X-ray color-color diagrams and their host-galaxy properties, aiming at characterizing the nuclear obscuration environment and the triggering mechanism of highly obscured AGNs. We find that the refined IRAC color-color diagram fails to identify the majority of X-ray selected highly obscured AGNs, even for the most luminous sources with ${\rm log}\,L_{\rm X}\, \rm (erg\ s^{-1}) > 44$. Over 80% of our sources will not be selected as heavily obscured candidates using the flux ratio of $f_{\rm 24 μm}\, /\,f_R > 1000$ and $R - K > 4.5$ criteria, implying complex origins and conditions for the obscuring materials that are responsible for the heavy X-ray obscuration. The average star formation rate of highly obscured AGNs is similar to that of stellar mass- ($M_*$-) and $z$-controlled normal galaxies, while the lack of quiescent hosts is observed for the former. Partial correlation analyses imply that highly obscured AGN activity (traced by $L_{\rm X}$) appears to be more fundamentally related to $M_*$, and no dependence of $N_{\rm H}$ on either $M_*$ or SFR is detected. Morphology analyses reveal that 61% of our sources have a significant disk component, while only 27% of them exhibit irregular morphological signatures. These findings together point toward a scenario where secular processes (e.g., galactic-disk instabilities), instead of mergers, are most probable to be the leading mechanism that triggers accretion activities of X-ray-selected highly obscured AGNs.

astro-ph.GA↗

arXiv2020

U2-ONet: A Two-level Nested Octave U-structure with Multiscale Attention Mechanism for Moving Instances Segmentation

Most scenes in practical applications are dynamic scenes containing moving objects, so segmenting accurately moving objects is crucial for many computer vision applications. In order to efficiently segment out all moving objects in the scene, regardless of whether the object has a predefined semantic label, we propose a two-level nested Octave U-structure network with a multiscale attention mechanism called U2-ONet. Each stage of U2-ONet is filled with our newly designed Octave ReSidual U-block (ORSU) to enhance the ability to obtain more context information at different scales while reducing spatial redundancy of feature maps. In order to efficiently train our multi-scale deep network, we introduce a hierarchical training supervision strategy that calculates the loss at each level while adding a knowledge matching loss to keep the optimization consistency. Experimental results show that our method achieves state-of-the-art performance in several general moving objects segmentation datasets.

cs.CV↗

arXiv2020

Can Synthetic Data Improve Object Detection Results for Remote Sensing Images?

Deep learning approaches require enough training samples to perform well, but it is a challenge to collect enough real training data and label them manually. In this letter, we propose the use of realistic synthetic data with a wide distribution to improve the performance of remote sensing image aircraft detection. Specifically, to increase the variability of synthetic data, we randomly set the parameters during rendering, such as the size of the instance and the class of background images. In order to make the synthetic images more realistic, we then refine the synthetic images at the pixel level using CycleGAN with real unlabeled images. We also fine-tune the model with a small amount of real data, to obtain a higher accuracy. Experiments on NWPU VHR-10, UCAS-AOD and DIOR datasets demonstrate that the proposed method can be applied for augmenting insufficient real data.

cs.CV↗

arXiv2020

\emph{cm}SalGAN: RGB-D Salient Object Detection with Cross-View Generative Adversarial Networks

Image salient object detection (SOD) is an active research topic in computer vision and multimedia area. Fusing complementary information of RGB and depth has been demonstrated to be effective for image salient object detection which is known as RGB-D salient object detection problem. The main challenge for RGB-D salient object detection is how to exploit the salient cues of both intra-modality (RGB, depth) and cross-modality simultaneously which is known as cross-modality detection problem. In this paper, we tackle this challenge by designing a novel cross-modality Saliency Generative Adversarial Network (\emph{cm}SalGAN). \emph{cm}SalGAN aims to learn an optimal view-invariant and consistent pixel-level representation for RGB and depth images via a novel adversarial learning framework, which thus incorporates both information of intra-view and correlation information of cross-view images simultaneously for RGB-D saliency detection problem. To further improve the detection results, the attention mechanism and edge detection module are also incorporated into \emph{cm}SalGAN. The entire \emph{cm}SalGAN can be trained in an end-to-end manner by using the standard deep neural network framework. Experimental results show that \emph{cm}SalGAN achieves the new state-of-the-art RGB-D saliency detection performance on several benchmark datasets.

cs.CV↗