arXiv subjects

Xu Zhao

Publications and source records attributed to Xu Zhao.

At least 73 records · Page 4Linked to original sources

arXiv2023

ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection

Background subtraction (BGS) aims to extract all moving objects in the video frames to obtain binary foreground segmentation masks. Deep learning has been widely used in this field. Compared with supervised-based BGS methods, unsupervised methods have better generalization. However, previous unsupervised deep learning BGS algorithms perform poorly in sophisticated scenarios such as shadows or night lights, and they cannot detect objects outside the pre-defined categories. In this work, we propose an unsupervised BGS algorithm based on zero-shot object detection called Zero-shot Background Subtraction (ZBS). The proposed method fully utilizes the advantages of zero-shot object detection to build the open-vocabulary instance-level background model. Based on it, the foreground can be effectively extracted by comparing the detection results of new frames with the background model. ZBS performs well for sophisticated scenarios, and it has rich and extensible categories. Furthermore, our method can easily generalize to other tasks, such as abandoned object detection in unseen environments. We experimentally show that ZBS surpasses state-of-the-art unsupervised BGS methods by 4.70% F-Measure on the CDnet 2014 dataset. The code is released at https://github.com/CASIA-IVA-Lab/ZBS.

cs.CV↗

arXiv2023

Item Cold Start Recommendation via Adversarial Variational Auto-encoder Warm-up

The gap between the randomly initialized item ID embedding and the well-trained warm item ID embedding makes the cold items hard to suit the recommendation system, which is trained on the data of historical warm items. To alleviate the performance decline of new items recommendation, the distribution of the new item ID embedding should be close to that of the historical warm items. To achieve this goal, we propose an Adversarial Variational Auto-encoder Warm-up model (AVAEW) to generate warm-up item ID embedding for cold items. Specifically, we develop a conditional variational auto-encoder model to leverage the side information of items for generating the warm-up item ID embedding. Particularly, we introduce an adversarial module to enforce the alignment between warm-up item ID embedding distribution and historical item ID embedding distribution. We demonstrate the effectiveness and compatibility of the proposed method by extensive offline experiments on public datasets and online A/B tests on a real-world large-scale news recommendation platform.

cs.IR↗

arXiv2023

Slate-Aware Ranking for Recommendation

We see widespread adoption of slate recommender systems, where an ordered item list is fed to the user based on the user interests and items' content. For each recommendation, the user can select one or several items from the list for further interaction. In this setting, the significant impact on user behaviors from the mutual influence among the items is well understood. The existing methods add another step of slate re-ranking after the ranking stage of recommender systems, which considers the mutual influence among recommended items to re-rank and generate the recommendation results so as to maximize the expected overall utility. However, to model the complex interaction of multiple recommended items, the re-ranking stage usually can just handle dozens of candidates because of the constraint of limited hardware resource and system latency. Therefore, the ranking stage is still essential for most applications to provide high-quality candidate set for the re-ranking stage. In this paper, we propose a solution named Slate-Aware ranking (SAR) for the ranking stage. By implicitly considering the relations among the slate items, it significantly enhances the quality of the re-ranking stage's candidate set and boosts the relevance and diversity of the overall recommender systems. Both experiments with the public datasets and internal online A/B testing are conducted to verify its effectiveness.

cs.IR↗

arXiv2023

View Consistency Aware Holistic Triangulation for 3D Human Pose Estimation

The rapid development of multi-view 3D human pose estimation (HPE) is attributed to the maturation of monocular 2D HPE and the geometry of 3D reconstruction. However, 2D detection outliers in occluded views due to neglect of view consistency, and 3D implausible poses due to lack of pose coherence, remain challenges. To solve this, we introduce a Multi-View Fusion module to refine 2D results by establishing view correlations. Then, Holistic Triangulation is proposed to infer the whole pose as an entirety, and anatomy prior is injected to maintain the pose coherence and improve the plausibility. Anatomy prior is extracted by PCA whose input is skeletal structure features, which can factor out global context and joint-by-joint relationship from abstract to concrete. Benefiting from the closed-form solution, the whole framework is trained end-to-end. Our method outperforms the state of the art in both precision and plausibility which is assessed by a new metric.

cs.CV↗

arXiv2022

ETAD: Training Action Detection End to End on a Laptop

Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train directly from video frames with extremely low GPU memory consumption. Our main idea is to minimize and balance the heavy computation among features and gradients in each training iteration. We propose to sequentially forward the snippet frame through the video encoder, and backward only a small necessary portion of gradients to update the encoder. To further alleviate the computational redundancy in training, we propose to dynamically sample only a small subset of proposals during training. Moreover, various sampling strategies and ratios are studied for both the encoder and detector. ETAD achieves state-of-the-art performance on TAD benchmarks with remarkable efficiency. On ActivityNet-1.3, training ETAD in 18 hours can reach 38.25% average mAP with only 1.3 GB memory consumption per video under end-to-end training. Our code will be publicly released.

cs.CV↗

arXiv2022

Does Deep Learning REALLY Outperform Non-deep Machine Learning for Clinical Prediction on Physiological Time Series?

Machine learning has been widely used in healthcare applications to approximate complex models, for clinical diagnosis, prognosis, and treatment. As deep learning has the outstanding ability to extract information from time series, its true capabilities on sparse, irregularly sampled, multivariate, and imbalanced physiological data are not yet fully explored. In this paper, we systematically examine the performance of machine learning models for the clinical prediction task based on the EHR, especially physiological time series. We choose Physionet 2019 challenge public dataset to predict Sepsis outcomes in ICU units. Ten baseline machine learning models are compared, including 3 deep learning methods and 7 non-deep learning methods, commonly used in the clinical prediction domain. Nine evaluation metrics with specific clinical implications are used to assess the performance of models. Besides, we sub-sample training dataset sizes and use learning curve fit to investigate the impact of the training dataset size on the performance of the machine learning models. We also propose the general pre-processing method for the physiology time-series data and use Dice Loss to deal with the dataset imbalanced problem. The results show that deep learning indeed outperforms non-deep learning, but with certain conditions: firstly, evaluating with some particular evaluation metrics (AUROC, AUPRC, Sensitivity, and FNR), but not others; secondly, the training dataset size is large enough (with an estimation of a magnitude of thousands).

cs.LG↗

arXiv2022

Detecting the oscillation and propagation of the nascent dynamic solar wind structure at 2.6 solar radii using VLBI radio telescopes

Probing the solar corona is crucial to study the coronal heating and solar wind acceleration. However, the transient and inhomogeneous solar wind flows carry large-amplitude inherent Alfven waves and turbulence, which make detection more difficult. We report the oscillation and propagation of the solar wind at 2.6 solar radii (Rs) by observation of China Tianwen and ESA Mars Express with radio telescopes. The observations were carried out on Oct.9 2021, when one coronal mass ejection (CME) passed across the ray paths of the telescope beams. We obtain the frequency fluctuations (FF) of the spacecraft signals from each individual telescope. Firstly, we visually identify the drift of the frequency spikes at a high spatial resolution of thousands of kilometers along the projected baselines. They are used as traces to estimate the solar wind velocity. Then we perform the cross-correlation analysis on the time series of FF from different telescopes. The velocity variations of solar wind structure along radial and tangential directions during the CME passage are obtained. The oscillation of tangential velocity confirms the detection of streamer wave. Moreover, at the tail of the CME, we detect the propagation of an accelerating fast field-aligned density structure indicating the presence of magnetohydrodynamic waves. This study confirm that the ground station-pairs are able to form particular spatial projection baselines with high resolution and sensitivity to study the detailed propagation of the nascent dynamic solar wind structure.

astro-ph.SR↗

arXiv2022

Transfering Low-Frequency Features for Domain Adaptation

Previous unsupervised domain adaptation methods did not handle the cross-domain problem from the perspective of frequency for computer vision. The images or feature maps of different domains can be decomposed into the low-frequency component and high-frequency component. This paper proposes the assumption that low-frequency information is more domain-invariant while the high-frequency information contains domain-related information. Hence, we introduce an approach, named low-frequency module (LFM), to extract domain-invariant feature representations. The LFM is constructed with the digital Gaussian low-pass filter. Our method is easy to implement and introduces no extra hyperparameter. We design two effective ways to utilize the LFM for domain adaptation, and our method is complementary to other existing methods and formulated as a plug-and-play unit that can be combined with these methods. Experimental results demonstrate that our LFM outperforms state-of-the-art methods for various computer vision tasks, including image classification and object detection.

cs.CV↗

arXiv2022

FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation

There exist challenging problems in 3D human pose estimation mission, such as poor performance caused by occlusion and self-occlusion. Recently, IMU-vision sensor fusion is regarded as valuable for solving these problems. However, previous researches on the fusion of IMU and vision data, which is heterogeneous, fail to adequately utilize either IMU raw data or reliable high-level vision features. To facilitate a more efficient sensor fusion, in this work we propose a framework called \emph{FusePose} under a parametric human kinematic model. Specifically, we aggregate different information of IMU or vision data and introduce three distinctive sensor fusion approaches: NaiveFuse, KineFuse and AdaDeepFuse. NaiveFuse servers as a basic approach that only fuses simplified IMU data and estimated 3D pose in euclidean space. While in kinematic space, KineFuse is able to integrate the calibrated and aligned IMU raw data with converted 3D pose parameters. AdaDeepFuse further develops this kinematical fusion process to an adaptive and end-to-end trainable manner. Comprehensive experiments with ablation studies demonstrate the rationality and superiority of the proposed framework. The performance of 3D human pose estimation is improved compared to the baseline result. On Total Capture dataset, KineFuse surpasses previous state-of-the-art which uses IMU only for testing by 8.6\%. AdaDeepFuse surpasses state-of-the-art which uses IMU for both training and testing by 8.5\%. Moreover, we validate the generalization capability of our framework through experiments on Human3.6M dataset.

cs.CV↗

arXiv2022

Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder

Embedding & MLP has become a paradigm for modern large-scale recommendation system. However, this paradigm suffers from the cold-start problem which will seriously compromise the ecological health of recommendation systems. This paper attempts to tackle the item cold-start problem by generating enhanced warmed-up ID embeddings for cold items with historical data and limited interaction records. From the aspect of industrial practice, we mainly focus on the following three points of item cold-start: 1) How to conduct cold-start without additional data requirements and make strategy easy to be deployed in online recommendation scenarios. 2) How to leverage both historical records and constantly emerging interaction data of new items. 3) How to model the relationship between item ID and side information stably from interaction data. To address these problems, we propose a model-agnostic Conditional Variational Autoencoder based Recommendation(CVAR) framework with some advantages including compatibility on various backbones, no extra requirements for data, utilization of both historical data and recent emerging interactions. CVAR uses latent variables to learn a distribution over item side information and generates desirable item ID embeddings using a conditional decoder. The proposed method is evaluated by extensive offline experiments on public datasets and online A/B tests on Tencent News recommendation platform, which further illustrate the advantages and robustness of CVAR.

cs.IR↗

arXiv2021

Estimate Metabolite Taxonomy and Structure with a Fragment-Centered Database and Fragment Network

Metabolite structure identification has become the major bottleneck of the mass spectrometry based metabolomics research. Till now, number of mass spectra databases and search algorithms have been developed to address this issue. However, two critical problems still exist: the low chemical component record coverage in databases and significant MS/MS spectra variations related to experiment equipment and parameter settings. In this work, we considered the molecule fragment as basic building blocks of the metabolic components which had relatively consistent signatures in MS/MS spectra. And from a bottom-up point of view, we built a fragment centered database, MSFragDB, by reorganizing the data from the Human Metabolome Database (HMDB) and developed an intensity-free searching algorithm to search and rank the most relative metabolite according to the users' input. We also proposed the concept of fragment network, a graph structure that encoded the relationship between the molecule fragments to find close motif that indicated a specific chemical structure. Although based on the same dataset as the HMDB, validation results implied that the MSFragDB had a higher hit ratio and furthermore, estimated possible taxonomy that a query spectrum belongs to when the corresponding chemical component was missing in the database. Aid by the Fragment Network, the MSFragDB was also proved to be able to estimate the right structure while the MS/MS spectrum suffers from the precursor-contamination. The strategy proposed is general and can be adopted in existing databases. We believe MSFragDB and Fragment Network can improve the performance of structure identification with existing data. The beta version of the database is freely available at www.xrzhanglab.com/msfragdb/.

q-bio.QM↗

arXiv2020

An End to End Network Architecture for Fundamental Matrix Estimation

In this paper, we present a novel end-to-end network architecture to estimate fundamental matrix directly from stereo images. To establish a complete working pipeline, different deep neural networks in charge of finding correspondences in images, performing outlier rejection and calculating fundamental matrix, are integrated into an end-to-end network architecture. To well train the network and preserve geometry properties of fundamental matrix, a new loss function is introduced. To evaluate the accuracy of estimated fundamental matrix more reasonably, we design a new evaluation metric which is highly consistent with visualization result. Experiments conducted on both outdoor and indoor data-sets show that this network outperforms traditional methods as well as previous deep learning based methods on various metrics and achieves significant performance improvements.

cs.CV↗

arXiv2020

A Relaxed Matching Procedure for Unsupervised BLI

Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest. One of the crucial parts in methods for the BLI task is the matching procedure. Previous works impose a too strong constraint on the matching and lead to many counterintuitive translation pairings. Thus, We propose a relaxed matching procedure to find a more precise matching between two languages. We also find that aligning source and target language embedding space bidirectionally will bring significant improvement. We follow the previous iterative framework to conduct experiments. Results on standard benchmark demonstrate the effectiveness of our proposed method, which substantially outperforms previous unsupervised methods.

cs.CL↗

arXiv2020

Semi-Supervised Bilingual Lexicon Induction with Two-way Interaction

Semi-supervision is a promising paradigm for Bilingual Lexicon Induction (BLI) with limited annotations. However, previous semisupervised methods do not fully utilize the knowledge hidden in annotated and nonannotated data, which hinders further improvement of their performance. In this paper, we propose a new semi-supervised BLI framework to encourage the interaction between the supervised signal and unsupervised alignment. We design two message-passing mechanisms to transfer knowledge between annotated and non-annotated data, named prior optimal transport and bi-directional lexicon update respectively. Then, we perform semi-supervised learning based on a cyclic or a parallel parameter feeding routine to update our models. Our framework is a general framework that can incorporate any supervised and unsupervised BLI methods based on optimal transport. Experimental results on MUSE and VecMap datasets show significant improvement of our models. Ablation study also proves that the two-way interaction between the supervised signal and unsupervised alignment accounts for the gain of the overall performance. Results on distant language pairs further illustrate the advantage and robustness of our proposed method.

cs.CL↗

arXiv2020

Varied fusion reaction probability induced by ion stopping modification in laser-driven plasma with different temperature

The dynamics of nuclear reaction in plasma is a fundamental issue in many high energy density researches, such as the astrophysical reactions and the inertial confinement fusion. The effective reaction cross-sections and ion stopping power in plasma need to be taken into account to analyze the reactivity. In this research, we have experimentally investigated the from D-D reactions from interactions between deuteron beams and deuterated polystyrene (CD) plasma, driven by two laser pulses respectively. The neutron yields, plasma density and deuteron energy loss in plasma have been measured, and the plasma temperature and deuteron stopping power have been analyzed from simulations. It is shown that, compared with a cold target, the reaction probability in plasma conditions can be enhanced or suppressed, which is ascribed to the deuteron stopping power modifications in plasma. In hotter CD plasma, the energy loss of moderate energetic deuterons reduces, which leads to higher D-D reaction probability, while the contrary happens in colder plasma. This work provides new understanding of fusion reactions in plasma environment.

physics.plasm-ph↗

arXiv2019

EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection

Recently, leveraging on the development of end-to-end convolutional neural networks (CNNs), deep stereo matching networks have achieved remarkable performance far exceeding traditional approaches. However, state-of-the-art stereo frameworks still have difficulties at finding correct correspondences in texture-less regions, detailed structures, small objects and near boundaries, which could be alleviated by geometric clues such as edge contours and corresponding constraints. To improve the quality of disparity estimates in these challenging areas, we propose an effective multi-task learning network, EdgeStereo, composed of a disparity estimation branch and an edge detection branch, which enables end-to-end predictions of both disparity map and edge map. To effectively incorporate edge cues, we propose the edge-aware smoothness loss and edge feature embedding for inter-task interactions. It is demonstrated that based on our unified model, edge detection task and stereo matching task can promote each other. In addition, we design a compact module called residual pyramid to replace the commonly-used multi-stage cascaded structures or 3-D convolution based regularization modules in current stereo matching networks. By the time of the paper submission, EdgeStereo achieves state-of-art performance on the FlyingThings3D dataset, KITTI 2012 and KITTI 2015 stereo benchmarks, outperforming other published stereo matching methods by a noteworthy margin. EdgeStereo also achieves comparable generalization performance for disparity estimation because of the incorporation of edge cues.

cs.CV↗

arXiv2019

Parameter Sharing Decoder Pair for Auto Composing

Auto Composing is an active and appealing research area in the past few years, and lots of efforts have been put into inventing more robust models to solve this problem. With the fast evolution of deep learning techniques, some deep neural network-based language models are becoming dominant. Notably, the transformer structure has been proven to be very efficient and promising in modeling texts. However, the transformer-based language models usually contain huge number of parameters and the size of the model is usually too large to put in production for some storage limited applications. In this paper, we propose a parameter sharing decoder pair (PSDP), which reduces the number of parameters dramatically and at the same time maintains the capability of generating understandable and reasonable compositions. Works created by the proposed model are presented to demonstrate the effectiveness of the model.

cs.LG↗

arXiv2019

Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2

This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2019 Task 1 (\textbf{temporal action proposal generation}) and Task 2 (\textbf{temporal action localization/detection}). Temporal action proposal indicates the temporal intervals containing the actions and plays an important role in temporal action localization. Top-down and bottom-up methods are the two main categories used for proposal generation in the existing literature. In this paper, we devise a novel Multi-Granularity Fusion Network (MGFN) to combine the proposals generated from different frameworks for complementary filtering and confidence re-ranking. Specifically, we consider the diversity comprehensively from multiple perspectives, e.g. the characteristic aspect, the data aspect, the model aspect and the result aspect. Our MGFN achieves the state-of-the-art performance on the temporal action proposal task with 69.85 AUC score and the temporal action localization task with 38.90 mAP on the challenge testing set.

cs.CV↗