arXiv subjects

Bin Zhao

Publications and source records attributed to Bin Zhao.

At least 127 records · Page 7Linked to original sources

arXiv2022

Low-Light Hyperspectral Image Enhancement

Due to inadequate energy captured by the hyperspectral camera sensor in poor illumination conditions, low-light hyperspectral images (HSIs) usually suffer from low visibility, spectral distortion, and various noises. A range of HSI restoration methods have been developed, yet their effectiveness in enhancing low-light HSIs is constrained. This work focuses on the low-light HSI enhancement task, which aims to reveal the spatial-spectral information hidden in darkened areas. To facilitate the development of low-light HSI processing, we collect a low-light HSI (LHSI) dataset of both indoor and outdoor scenes. Based on Laplacian pyramid decomposition and reconstruction, we developed an end-to-end data-driven low-light HSI enhancement (HSIE) approach trained on the LHSI dataset. With the observation that illumination is related to the low-frequency component of HSI, while textural details are closely correlated to the high-frequency component, the proposed HSIE is designed to have two branches. The illumination enhancement branch is adopted to enlighten the low-frequency component with reduced resolution. The high-frequency refinement branch is utilized for refining the high-frequency component via a predicted mask. In addition, to improve information flow and boost performance, we introduce an effective channel attention block (CAB) with residual dense connection, which served as the basic block of the illumination enhancement branch. The effectiveness and efficiency of HSIE both in quantitative assessment measures and visual effects are demonstrated by experimental results on the LHSI dataset. According to the classification performance on the remote sensing Indian Pines dataset, downstream tasks benefit from the enhanced HSI. Datasets and codes are available: \href{https://github.com/guanguanboy/HSIE}{https://github.com/guanguanboy/HSIE}.

eess.IV↗

arXiv2022

RCLane: Relay Chain Prediction for Lane Detection

Lane detection is an important component of many real-world autonomous systems. Despite a wide variety of lane detection approaches have been proposed, reporting steady benchmark improvements over time, lane detection remains a largely unsolved problem. This is because most of the existing lane detection methods either treat the lane detection as a dense prediction or a detection task, few of them consider the unique topologies (Y-shape, Fork-shape, nearly horizontal lane) of the lane markers, which leads to sub-optimal solution. In this paper, we present a new method for lane detection based on relay chain prediction. Specifically, our model predicts a segmentation map to classify the foreground and background region. For each pixel point in the foreground region, we go through the forward branch and backward branch to recover the whole lane. Each branch decodes a transfer map and a distance map to produce the direction moving to the next point, and how many steps to progressively predict a relay station (next point). As such, our model is able to capture the keypoints along the lanes. Despite its simplicity, our strategy allows us to establish new state-of-the-art on four major benchmarks including TuSimple, CULane, CurveLanes and LLAMAS.

cs.CV↗

arXiv2022

Audio-Visual Collaborative Representation Learning for Dynamic Saliency Prediction

The Dynamic Saliency Prediction (DSP) task simulates the human selective attention mechanism to perceive the dynamic scene, which is significant and imperative in many vision tasks. Most of existing methods only consider visual cues, while neglect the accompanied audio information, which can provide complementary information for the scene understanding. In fact, there exists a strong relation between auditory and visual cues, and humans generally perceive the surrounding scene by collaboratively sensing these cues. Motivated by this, an audio-visual collaborative representation learning method is proposed for the DSP task, which explores the audio modality to better predict the dynamic saliency map by assisting vision modality. The proposed method consists of three parts: 1) audio-visual encoding, 2) audio-visual location, and 3) collaborative integration parts. Firstly, a refined SoundNet architecture is adopted to encode audio modality for obtaining corresponding features, and a modified 3D ResNet-50 architecture is employed to learn visual features, containing both spatial location and temporal motion information. Secondly, an audio-visual location part is devised to locate the sound source in the visual scene by learning the correspondence between audio-visual information. Thirdly, a collaborative integration part is devised to adaptively aggregate audio-visual information and center-bias prior to generate the final saliency map. Extensive experiments are conducted on six challenging audiovisual eye-tracking datasets, including DIEM, AVAD, Coutrot1, Coutrot2, SumMe, and ETMD, which shows significant superiority over state-of-the-art DSP models.

cs.CV↗

arXiv2022

Eddy Covariance: A Scientometric Review (1981-2018)

The history of eddy covariance (EC) measuring system could be dated back to 100 years ago, but it was not until the recent decades that EC gains popularity and being widely used in global change ecological studies, with explosion of related work published in papers from various journals. Investigating 8297 literature related with EC from 1981 to 2018, we make a comprehensive and critical review of scientific development of EC from a scientometric perspective. First, the paper outlines general bibliometric statistics, including publication number, country contribution, productive institutions, active authors, journal distribution, highly cited articles and fund support, to provide an informative picture of EC studies. Second, research trends are revealed by network visualization and modeling based on keyword analysis, from where we could discover the knowledge structure of EC and detect the research focus and hotspots transitions at different periods. Third, collaboration in EC research community has been explored. FLUXNET is the largest global network uniting EC researchers, here we have quantified and evaluated its performance by using bibliometric indicators of cooperation and citation. Specific discussions have been given to the historical development of EC, including technical maturation and application promotion. Considering the current barrier for collaboration, the review closes by analyzing the reasons hindering data sharing and makes a prospect of new models for data-intensive collaboration in the future.

cs.DL↗

arXiv2021

Community detection in censored hypergraph

Community detection refers to the problem of clustering the nodes of a network (either graph or hypergrah) into groups. Various algorithms are available for community detection and all these methods apply to uncensored networks. In practice, a network may has censored (or missing) values and it is shown that censored values have non-negligible effect on the structural properties of a network. In this paper, we study community detection in censored $m$-uniform hypergraph from information-theoretic point of view. We derive the information-theoretic threshold for exact recovery of the community structure. Besides, we propose a polynomial-time algorithm to exactly recover the community structure up to the threshold. The proposed algorithm consists of a spectral algorithm plus a refinement step. It is also interesting to study whether a single spectral algorithm without refinement achieves the threshold. To this end, we also explore the semi-definite relaxation algorithm and analyze its performance.

stat.ML↗

arXiv2021

Hierarchical Multimodal Transformer to Summarize Videos

Although video summarization has achieved tremendous success benefiting from Recurrent Neural Networks (RNN), RNN-based methods neglect the global dependencies and multi-hop relationships among video frames, which limits the performance. Transformer is an effective model to deal with this problem, and surpasses RNN-based methods in several sequence modeling tasks, such as machine translation, video captioning, \emph{etc}. Motivated by the great success of transformer and the natural structure of video (frame-shot-video), a hierarchical transformer is developed for video summarization, which can capture the dependencies among frame and shots, and summarize the video by exploiting the scene information formed by shots. Furthermore, we argue that both the audio and visual information are essential for the video summarization task. To integrate the two kinds of information, they are encoded in a two-stream scheme, and a multimodal fusion mechanism is developed based on the hierarchical transformer. In this paper, the proposed method is denoted as Hierarchical Multimodal Transformer (HMT). Practically, extensive experiments show that HMT surpasses most of the traditional, RNN-based and attention-based video summarization methods.

cs.CV↗

arXiv2021

Determining Reaction Pathways at Low Temperatures by Isotopic Substitution: The Case of BeD+ + H2O

Trapped Be+ ions are a leading platform for quantum information science [1], but reactions with background gas species, such as H2 and H2O, result in qubit loss. Our experiment reveals that the BeOH+ ion is the final trapped ion species when both H2 and H2O exist in a vacuum system with cold, trapped Be+. To understand the loss mechanism, low-temperature reactions between sympathetically cooled BeD+ ions and H2O molecules have been investigated using an integrated, laser-cooled Be+ ion trap and high-resolution Time-of-Flight (TOF) mass spectrometer (MS) [2]. Among all the possible products,BeH2O+, H2DO+, BeOD+, and BeOH+, only the BeOH+ molecular ion was observed experimentally, with the assumed co-product of HD. Theoretical analyses based on explicitly correlated restricted coupled cluster singles, doubles, and perturbative triples (RCCSD(T)-F12) method with the augmented correlation-consistent polarized triple zeta (AVTZ) basis set reveal that two intuitive direct abstraction product channels, Be + H2DO+ and D + BeH2O+, are not energetically accessible at the present reaction temperature (~150 K). Instead, a double displacement BeOH+ + HD product channel is accessible due to a large exothermicity of 1.885 eV through a submerged barrier in the reaction pathway. While the BeOD+ + H2 product channel has a similar exothermicity, the reaction pathway is dynamically unfavourable, as suggested by a Sudden Vector Projection analysis. This work sheds light on the origin of the loss and contaminations of the laser-cooled Be+ ions in quantum-information experiments.

physics.chem-ph↗

arXiv2021

PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

Non-maximum Suppression (NMS) is an essential postprocessing step in modern convolutional neural networks for object detection. Unlike convolutions which are inherently parallel, the de-facto standard for NMS, namely GreedyNMS, cannot be easily parallelized and thus could be the performance bottleneck in convolutional object detection pipelines. MaxpoolNMS is introduced as a parallelizable alternative to GreedyNMS, which in turn enables faster speed than GreedyNMS at comparable accuracy. However, MaxpoolNMS is only capable of replacing the GreedyNMS at the first stage of two-stage detectors like Faster-RCNN. There is a significant drop in accuracy when applying MaxpoolNMS at the final detection stage, due to the fact that MaxpoolNMS fails to approximate GreedyNMS precisely in terms of bounding box selection. In this paper, we propose a general, parallelizable and configurable approach PSRR-MaxpoolNMS, to completely replace GreedyNMS at all stages in all detectors. By introducing a simple Relationship Recovery module and a Pyramid Shifted MaxpoolNMS module, our PSRR-MaxpoolNMS is able to approximate GreedyNMS more precisely than MaxpoolNMS. Comprehensive experiments show that our approach outperforms MaxpoolNMS by a large margin, and it is proven faster than GreedyNMS with comparable accuracy. For the first time, PSRR-MaxpoolNMS provides a fully parallelizable solution for customized hardware design, which can be reused for accelerating NMS everywhere.

cs.CV↗

arXiv2021

AudioVisual Video Summarization

Audio and vision are two main modalities in video data. Multimodal learning, especially for audiovisual learning, has drawn considerable attention recently, which can boost the performance of various computer vision tasks. However, in video summarization, existing approaches just exploit the visual information while neglect the audio information. In this paper, we argue that the audio modality can assist vision modality to better understand the video content and structure, and further benefit the summarization process. Motivated by this, we propose to jointly exploit the audio and visual information for the video summarization task, and develop an AudioVisual Recurrent Network (AVRN) to achieve this. Specifically, the proposed AVRN can be separated into three parts: 1) the two-stream LSTM is utilized to encode the audio and visual feature sequentially by capturing their temporal dependency. 2) the audiovisual fusion LSTM is employed to fuse the two modalities by exploring the latent consistency between them. 3) the self-attention video encoder is adopted to capture the global dependency in the video. Finally, the fused audiovisual information, and the integrated temporal and global dependencies are jointly used to predict the video summary. Practically, the experimental results on the two benchmarks, \emph{i.e.,} SumMe and TVsum, have demonstrated the effectiveness of each part, and the superiority of AVRN compared to those approaches just exploiting visual information for video summarization.

cs.CV↗

arXiv2021

EA-Net: Edge-Aware Network for Flow-based Video Frame Interpolation

Video frame interpolation can up-convert the frame rate and enhance the video quality. In recent years, although the interpolation performance has achieved great success, image blur usually occurs at the object boundaries owing to the large motion. It has been a long-standing problem, and has not been addressed yet. In this paper, we propose to reduce the image blur and get the clear shape of objects by preserving the edges in the interpolated frames. To this end, the proposed Edge-Aware Network (EA-Net) integrates the edge information into the frame interpolation task. It follows an end-to-end architecture and can be separated into two stages, \emph{i.e.}, edge-guided flow estimation and edge-protected frame synthesis. Specifically, in the flow estimation stage, three edge-aware mechanisms are developed to emphasize the frame edges in estimating flow maps, so that the edge-maps are taken as the auxiliary information to provide more guidance to boost the flow accuracy. In the frame synthesis stage, the flow refinement module is designed to refine the flow map, and the attention module is carried out to adaptively focus on the bidirectional flow maps when synthesizing the intermediate frames. Furthermore, the frame and edge discriminators are adopted to conduct the adversarial training strategy, so as to enhance the reality and clarity of synthesized frames. Experiments on three benchmarks, including Vimeo90k, UCF101 for single-frame interpolation and Adobe240-fps for multi-frame interpolation, have demonstrated the superiority of the proposed EA-Net for the video frame interpolation task.

cs.CV↗

arXiv2021

Reconstructive Sequence-Graph Network for Video Summarization

Exploiting the inner-shot and inter-shot dependencies is essential for key-shot based video summarization. Current approaches mainly devote to modeling the video as a frame sequence by recurrent neural networks. However, one potential limitation of the sequence models is that they focus on capturing local neighborhood dependencies while the high-order dependencies in long distance are not fully exploited. In general, the frames in each shot record a certain activity and vary smoothly over time, but the multi-hop relationships occur frequently among shots. In this case, both the local and global dependencies are important for understanding the video content. Motivated by this point, we propose a Reconstructive Sequence-Graph Network (RSGN) to encode the frames and shots as sequence and graph hierarchically, where the frame-level dependencies are encoded by Long Short-Term Memory (LSTM), and the shot-level dependencies are captured by the Graph Convolutional Network (GCN). Then, the videos are summarized by exploiting both the local and global dependencies among shots. Besides, a reconstructor is developed to reward the summary generator, so that the generator can be optimized in an unsupervised manner, which can avert the lack of annotated data in video summarization. Furthermore, under the guidance of reconstruction loss, the predicted summary can better preserve the main video content and shot-level dependencies. Practically, the experimental results on three popular datasets i.e., SumMe, TVsum and VTW) have demonstrated the superiority of our proposed approach to the summarization task.

cs.CV↗

arXiv2021

Spectral halo for Hilbert modular forms

Let $F$ be a totally real field and $p$ be an odd prime which splits completely in $F$. We prove that the eigenvariety associated to a definite quaternion algebra over $F$ satisfies the following property: over a boundary annulus of the weight space, the eigenvariety is a disjoint union of countably infinitely many connected components which are finite over the weight space; on each fixed connected component, the ratios between the $U_\mathfrak{p}$-slopes of points and the $p$-adic valuations of the $\mathfrak{p}$-parameters are bounded by explicit numbers, for all primes $\mathfrak{p}$ of $F$ over $p$. Applying Hansen's $p$-adic interpolation theorem, we are able to transfer our results to Hilbert modular eigenvarieties. In particular, we prove that on every irreducible component of Hilbert modular eigenvarieties, as a point moves towards the boundary, its $U_p$ slope goes to zero. In the case of eigencurves, this completes the proof of Coleman-Mazur's `halo' conjecture.

math.NT↗

arXiv2021

Weather GAN: Multi-Domain Weather Translation Using Generative Adversarial Networks

In this paper, a new task is proposed, namely, weather translation, which refers to transferring weather conditions of the image from one category to another. It is important for photographic style transfer. Although lots of approaches have been proposed in traditional image translation tasks, few of them can handle the multi-category weather translation task, since weather conditions have rich categories and highly complex semantic structures. To address this problem, we develop a multi-domain weather translation approach based on generative adversarial networks (GAN), denoted as Weather GAN, which can achieve the transferring of weather conditions among sunny, cloudy, foggy, rainy and snowy. Specifically, the weather conditions in the image are determined by various weather-cues, such as cloud, blue sky, wet ground, etc. Therefore, it is essential for weather translation to focus the main attention on weather-cues. To this end, the generator of Weather GAN is composed of an initial translation module, an attention module and a weather-cue segmentation module. The initial translation module performs global translation during generation procedure. The weather-cue segmentation module identifies the structure and exact distribution of weather-cues. The attention module learns to focus on the interesting areas of the image while keeping other areas unaltered. The final generated result is synthesized by these three parts. This approach suppresses the distortion and deformation caused by weather translation. our approach outperforms the state-of-the-arts has been shown by a large number of experiments and evaluations.

cs.CV↗

arXiv2021

Semantics-Consistent Representation Learning for Remote Sensing Image-Voice Retrieval

With the development of earth observation technology, massive amounts of remote sensing (RS) images are acquired. To find useful information from these images, cross-modal RS image-voice retrieval provides a new insight. This paper aims to study the task of RS image-voice retrieval so as to search effective information from massive amounts of RS data. Existing methods for RS image-voice retrieval rely primarily on the pairwise relationship to narrow the heterogeneous semantic gap between images and voices. However, apart from the pairwise relationship included in the datasets, the intra-modality and non-paired inter-modality relationships should also be taken into account simultaneously, since the semantic consistency among non-paired representations plays an important role in the RS image-voice retrieval task. Inspired by this, a semantics-consistent representation learning (SCRL) method is proposed for RS image-voice retrieval. The main novelty is that the proposed method takes the pairwise, intra-modality, and non-paired inter-modality relationships into account simultaneously, thereby improving the semantic consistency of the learned representations for the RS image-voice retrieval. The proposed SCRL method consists of two main steps: 1) semantics encoding and 2) semantics-consistent representation learning. Firstly, an image encoding network is adopted to extract high-level image features with a transfer learning strategy, and a voice encoding network with dilated convolution is devised to obtain high-level voice features. Secondly, a consistent representation space is conducted by modeling the three kinds of relationships to narrow the heterogeneous semantic gap and learn semantics-consistent representations across two modalities. Extensive experimental results on three challenging RS image-voice datasets show the effectiveness of the proposed method.

cs.MM↗

arXiv2021

Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos

Segmenting objects in videos is a fundamental computer vision task. The current deep learning based paradigm offers a powerful, but data-hungry solution. However, current datasets are limited by the cost and human effort of annotating object masks in videos. This effectively limits the performance and generalization capabilities of existing video segmentation methods. To address this issue, we explore weaker form of bounding box annotations. We introduce a method for generating segmentation masks from per-frame bounding box annotations in videos. To this end, we propose a spatio-temporal aggregation module that effectively mines consistencies in the object and background appearance across multiple frames. We use our resulting accurate masks for weakly supervised training of video object segmentation (VOS) networks. We generate segmentation masks for large scale tracking datasets, using only their bounding box annotations. The additional data provides substantially better generalization performance leading to state-of-the-art results in both the VOS and more challenging tracking domain.

cs.CV↗

arXiv2020

Nonexistence of k-bounded sobrification

In this paper, we will focus on k-bounded sober spaces and show the existence of a T_0 space X not admitting any k-bounded sobrification. This strengthens a result of Zhao, Lu and Wang, who proved that the canonical k-bounded sobrification does not exist. Our work provides a complete solution to a question of Zhao and Ho, and shows that unlike Sob and BSob,the category KBSob of all k-bounded sober spaces is not a reflective subcategory of the category Top_0 of all T_0 spaces. Furthermore, we introduce the notion of qk-bounded sober spaces and prove that the category KBSob is a full reflective subcategory of the category QKBSob of all qk-bounded sober spaces and continuous mappings preserving existing irreducible suprema.

math.GN↗

arXiv2020

Automatic acute ischemic stroke lesion segmentation using semi-supervised learning

Ischemic stroke is a common disease in the elderly population, which can cause long-term disability and even death. However, the time window for treatment of ischemic stroke in its acute stage is very short. To fast localize and quantitively evaluate the acute ischemic stroke (AIS) lesions, many deep-learning-based lesion segmentation methods have been proposed in the literature, where a deep convolutional neural network (CNN) was trained on hundreds of fully labeled subjects with accurate annotations of AIS lesions. Despite that high segmentation accuracy can be achieved, the accurate labels should be annotated by experienced clinicians, and it is therefore very time-consuming to obtain a large number of fully labeled subjects. In this paper, we propose a semi-supervised method to automatically segment AIS lesions in diffusion weighted images and apparent diffusion coefficient maps. By using a large number of weakly labeled subjects and a small number of fully labeled subjects, our proposed method is able to accurately detect and segment the AIS lesions. In particular, our proposed method consists of three parts: 1) a double-path classification net (DPC-Net) trained in a weakly-supervised way is used to detect the suspicious regions of AIS lesions; 2) a pixel-level K-Means clustering algorithm is used to identify the hyperintensive regions on the DWIs; and 3) a region-growing algorithm combines the outputs of the DPC-Net and the K-Means to obtain the final precise lesion segmentation. In our experiment, we use 460 weakly labeled subjects and 15 fully labeled subjects to train and fine-tune the proposed method. By evaluating on a clinical dataset with 150 fully labeled subjects, our proposed method achieves a mean dice coefficient of 0.642, and a lesion-wise F1 score of 0.822.

eess.IV↗

arXiv2020

Automated Segmentation of Brain Gray Matter Nuclei on Quantitative Susceptibility Mapping Using Deep Convolutional Neural Network

Abnormal iron accumulation in the brain subcortical nuclei has been reported to be correlated to various neurodegenerative diseases, which can be measured through the magnetic susceptibility from the quantitative susceptibility mapping (QSM). To quantitively measure the magnetic susceptibility, the nuclei should be accurately segmented, which is a tedious task for clinicians. In this paper, we proposed a double-branch residual-structured U-Net (DB-ResUNet) based on 3D convolutional neural network (CNN) to automatically segment such brain gray matter nuclei. To better tradeoff between segmentation accuracy and the memory efficiency, the proposed DB-ResUNet fed image patches with high resolution and the patches with low resolution but larger field of view into the local and global branches, respectively. Experimental results revealed that by jointly using QSM and T$_\text{1}$ weighted imaging (T$_\text{1}$WI) as inputs, the proposed method was able to achieve better segmentation accuracy over its single-branch counterpart, as well as the conventional atlas-based method and the classical 3D-UNet structure. The susceptibility values and the volumes were also measured, which indicated that the measurements from the proposed DB-ResUNet are able to present high correlation with values from the manually annotated regions of interest.

eess.IV↗