arXiv subjects

Xun Wang

Publications and source records attributed to Xun Wang.

At least 127 records · Page 7Linked to original sources

arXiv2022

Hierarchical Contrast for Unsupervised Skeleton-based Action Representation Learning

This paper targets unsupervised skeleton-based action representation learning and proposes a new Hierarchical Contrast (HiCo) framework. Different from the existing contrastive-based solutions that typically represent an input skeleton sequence into instance-level features and perform contrast holistically, our proposed HiCo represents the input into multiple-level features and performs contrast in a hierarchical manner. Specifically, given a human skeleton sequence, we represent it into multiple feature vectors of different granularities from both temporal and spatial domains via sequence-to-sequence (S2S) encoders and unified downsampling modules. Besides, the hierarchical contrast is conducted in terms of four levels: instance level, domain level, clip level, and part level. Moreover, HiCo is orthogonal to the S2S encoder, which allows us to flexibly embrace state-of-the-art S2S encoders. Extensive experiments on four datasets, i.e., NTU-60, NTU-120, PKU-MMD I and II, show that HiCo achieves a new state-of-the-art for unsupervised skeleton-based action representation learning in two downstream tasks including action recognition and retrieval, and its learned action representation is of good transferability. Besides, we also show that our framework is effective for semi-supervised skeleton-based action recognition. Our code is available at https://github.com/HuiGuanLab/HiCo.

cs.CV↗

arXiv2022

Hypothesis Test Procedures for Detecting Leakage Signals in Water Pipeline Channels

We design statistical hypothesis tests for performing leak detection in water pipeline channels. By applying an appropriate model for signal propagation, we show that the detection problem becomes one of distinguishing signal from noise, with the noise being described by a multivariate Gaussian distribution with unknown covariance matrix. We first design a test procedure based on the generalized likelihood ratio test, which we show through simulations to offer appreciable leak detection performance gain over conventional approaches designed in an analogous context (for radar detection). Our proposed method requires estimation of the noise covariance matrix, which can become inaccurate under high-dimensional settings, and when the measurement data is scarce. To deal with this, we present a second leak detection method, which employs a regularized covariance matrix estimate. The regularization parameter is optimized for the leak detection application by applying results from large dimensional random matrix theory. This second proposed approach is shown to yield improved performance in leak detection compared with the first approach, at the expense of requiring higher computational complexity.

eess.SP↗

arXiv2022

Smart Contract Vulnerability Detection Technique: A Survey

Smart contract, one of the most successful applications of blockchain, is taking the world by storm, playing an essential role in the blockchain ecosystem. However, frequent smart contract security incidents not only result in tremendous economic losses but also destroy the blockchain-based credit system. The security and reliability of smart contracts thus gain extensive attention from researchers worldwide. In this survey, we first summarize the common types and typical cases of smart contract vulnerabilities from three levels, i.e., Solidity code layer, EVM execution layer, and Block dependency layer. Further, we review the research progress of smart contract vulnerability detection and classify existing counterparts into five categories, i.e., formal verification, symbolic execution, fuzzing detection, intermediate representation, and deep learning. Empirically, we take 300 real-world smart contracts deployed on Ethereum as the test samples and compare the representative methods in terms of accuracy, F1-Score, and average detection time. Finally, we discuss the challenges in the field of smart contract vulnerability detection and combine with the deep learning technology to look forward to future research directions.

cs.CR↗

arXiv2022

Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning

Despite the recent developments in the field of cross-modal retrieval, there has been less research focusing on low-resource languages due to the lack of manually annotated datasets. In this paper, we propose a noise-robust cross-lingual cross-modal retrieval method for low-resource languages. To this end, we use Machine Translation (MT) to construct pseudo-parallel sentence pairs for low-resource languages. However, as MT is not perfect, it tends to introduce noise during translation, rendering textual embeddings corrupted and thereby compromising the retrieval performance. To alleviate this, we introduce a multi-view self-distillation method to learn noise-robust target-language representations, which employs a cross-attention module to generate soft pseudo-targets to provide direct supervision from the similarity-based view and feature-based view. Besides, inspired by the back-translation in unsupervised MT, we minimize the semantic discrepancies between origin sentences and back-translated sentences to further improve the noise robustness of the textual encoder. Extensive experiments are conducted on three video-text and image-text cross-modal retrieval benchmarks across different languages, and the results demonstrate that our method significantly improves the overall performance without using extra human-labeled data. In addition, equipped with a pre-trained visual encoder from a recent vision-and-language pre-training framework, i.e., CLIP, our model achieves a significant performance gain, showing that our method is compatible with popular pre-training models. Code and data are available at https://github.com/HuiGuanLab/nrccr.

cs.CV↗

arXiv2022

Modality-Balanced Embedding for Video Retrieval

Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias phenomenon that the video encoder almost entirely relies on text matching, neglecting other modalities of the videos such as vision, audio. This modality imbalanceresults from a) modality gap: the relevance between a query and a video text is much easier to learn as the query is also a piece of text, with the same modality as the video text; b) data bias: most training samples can be solved solely by text matching. Here we share our practices to improve the first retrieval stage including our solution for the modality imbalance issue. We propose MBVR (short for Modality Balanced Video Retrieval) with two key components: manually generated modality-shuffled (MS) samples and a dynamic margin (DM) based on visual relevance. They can encourage the video encoder to pay balanced attentions to each modality. Through extensive experiments on a real world dataset, we show empirically that our method is both effective and efficient in solving modality bias problem. We have also deployed our MBVR in a large video platform and observed statistically significant boost over a highly optimized baseline in an A/B test and manual GSB evaluations.

cs.CV↗

arXiv2022

Progressive Localization Networks for Language-based Moment Localization

This paper targets the task of language-based video moment localization. The language-based setting of this task allows for an open set of target activities, resulting in a large variation of the temporal lengths of video moments. Most existing methods prefer to first sample sufficient candidate moments with various temporal lengths, and then match them with the given query to determine the target moment. However, candidate moments generated with a fixed temporal granularity may be suboptimal to handle the large variation in moment lengths. To this end, we propose a novel multi-stage Progressive Localization Network (PLN) which progressively localizes the target moment in a coarse-to-fine manner. Specifically, each stage of PLN has a localization branch, and focuses on candidate moments that are generated with a specific temporal granularity. The temporal granularities of candidate moments are different across the stages. Moreover, we devise a conditional feature manipulation module and an upsampling connection to bridge the multiple localization branches. In this fashion, the later stages are able to absorb the previously learned information, thus facilitating the more fine-grained localization. Extensive experiments on three public datasets demonstrate the effectiveness of our proposed PLN for language-based moment localization, especially for localizing short moments in long videos.

cs.CV↗

arXiv2022

Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval

This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlabeled videos. The success of this task depends on cross-modal representation learning that projects both videos and sentences into common spaces for semantic similarity computation. In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval. Inspired by the reading strategy of humans, we propose a Reading-strategy Inspired Visual Representation Learning (RIVRL) to represent videos, which consists of two branches: a previewing branch and an intensive-reading branch. The previewing branch is designed to briefly capture the overview information of videos, while the intensive-reading branch is designed to obtain more in-depth information. Moreover, the intensive-reading branch is aware of the video overview captured by the previewing branch. Such holistic information is found to be useful for the intensive-reading branch to extract more fine-grained features. Extensive experiments on three datasets are conducted, where our model RIVRL achieves a new state-of-the-art on TGIF and VATEX. Moreover, on MSR-VTT, our model using two video features shows comparable performance to the state-of-the-art using seven video features and even outperforms models pre-trained on the large-scale HowTo100M dataset.

cs.CV↗

arXiv2022

Exploiting full Resolution Feature Context for Liver Tumor and Vessel Segmentation via Integrate Framework: Application to Liver Tumor and Vessel 3D Reconstruction under embedded microprocessor

Liver cancer is one of the most common malignant diseases in the world. Segmentation and labeling of liver tumors and blood vessels in CT images can provide convenience for doctors in liver tumor diagnosis and surgical intervention. In the past decades, many state-of-the-art medical image segmentation algorithms appeared during this period. With the development of embedded devices, embedded deployment for medical segmentation and automatic reconstruction brings prospects for future automated surgical tasks. Yet, most of the existing segmentation methods mostly care about the spatial feature context and have a perception defect in the semantic relevance of medical images, which significantly affects the segmentation accuracy of liver tumors and blood vessels. Deploying large and complex models into embedded devices requires a reasonable trade-off between model accuracy, reasoning speed and model capacity. Given these problems, we introduce a multi-scale feature fusion network called TransFusionNet based on Transformer. This network achieved very competitive performance for liver vessel and liver tumor segmentation tasks, meanwhile it can improve the recognition of morphologic margins of liver tumors by exploiting the global information of CT images. Experiments show that in vessel segmentation task TransFusionNet achieved mean Dice coefficients of 0.899 and in liver tumor segmentation task TransFusionNet achieved mean Dice coefficients of 0.961. Compared with the state-of-the-art framework, our model achieves the best segmentation result. In addition, we deployed the model into an embedded micro-structure and constructed an integrated model for liver tumor vascular segmentation and reconstruction. This proprietary structure will be the exclusive component of the future medical field.

eess.IV↗

arXiv2021

Consistency Regularization for Deep Face Anti-Spoofing

Face anti-spoofing (FAS) plays a crucial role in securing face recognition systems. Empirically, given an image, a model with more consistent output on different views of this image usually performs better, as shown in Fig.1. Motivated by this exciting observation, we conjecture that encouraging feature consistency of different views may be a promising way to boost FAS models. In this paper, we explore this way thoroughly by enhancing both Embedding-level and Prediction-level Consistency Regularization (EPCR) in FAS. Specifically, at the embedding-level, we design a dense similarity loss to maximize the similarities between all positions of two intermediate feature maps in a self-supervised fashion; while at the prediction-level, we optimize the mean square error between the predictions of two views. Notably, our EPCR is free of annotations and can directly integrate into semi-supervised learning schemes. Considering different application scenarios, we further design five diverse semi-supervised protocols to measure semi-supervised FAS techniques. We conduct extensive experiments to show that EPCR can significantly improve the performance of several supervised and semi-supervised tasks on benchmark datasets. The codes and protocols will be released at https://github.com/clks-wzz/EPCR.

cs.CV↗

arXiv2021

Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework

Model smoothing is of central importance for obtaining a reliable teacher model in the student-teacher framework, where the teacher generates surrogate supervision signals to train the student. A popular model smoothing method is the Temporal Moving Average (TMA), which continuously averages the teacher parameters with the up-to-date student parameters. In this paper, we propose "Spatial Ensemble", a novel model smoothing mechanism in parallel with TMA. Spatial Ensemble randomly picks up a small fragment of the student model to directly replace the corresponding fragment of the teacher model. Consequentially, it stitches different fragments of historical student models into a unity, yielding the "Spatial Ensemble" effect. Spatial Ensemble obtains comparable student-teacher learning performance by itself and demonstrates valuable complementarity with temporal moving average. Their integration, named Spatial-Temporal Smoothing, brings general (sometimes significant) improvement to the student-teacher learning framework on a variety of state-of-the-art methods. For example, based on the self-supervised method BYOL, it yields +0.9% top-1 accuracy improvement on ImageNet, while based on the semi-supervised approach FixMatch, it increases the top-1 accuracy by around +6% on CIFAR-10 when only few training labels are available. Codes and models are available at: https://github.com/tengteng95/Spatial_Ensemble.

cs.CV↗

arXiv2021

Multi-scale super-resolution generation of low-resolution scanned pathological images

Background. Digital pathology has aroused widespread interest in modern pathology. The key of digitalization is to scan the whole slide image (WSI) at high magnification. The lager the magnification is, the richer details WSI will provide, but the scanning time is longer and the file size of obtained is larger. Methods. We design a strategy to scan slides with low resolution (5X) and a super-resolution method is proposed to restore the image details when in diagnosis. The method is based on a multi-scale generative adversarial network, which sequentially generates three high-resolution images such as 10X, 20X and 40X. Results. The peak-signal-to-noise-ratio of 10X to 40X generated images are 24.16, 22.27 and 20.44, and the structural-similarity-index are 0.845, 0.680 and 0.512, which are better than other super-resolution networks. Visual scoring average and standard deviation from three pathologists is 3.63 plus-minus 0.52, 3.70 plus-minus 0.57 and 3.74 plus-minus 0.56 and the p value of analysis of variance is 0.37, indicating that generated images include sufficient information for diagnosis. The average value of Kappa test is 0.99, meaning the diagnosis of generated images is highly consistent with that of the real images. Conclusion. This proposed method can generate high-quality 10X, 20X, 40X images from 5X images at the same time, in which the time and storage costs of digitalization can be effectively reduced up to 1/64 of the previous costs. The proposed method provides a better alternative for low-cost storage, faster image share of digital pathology. Keywords. Digital pathology; Super-resolution; Low resolution scanning; Low cost

eess.IV↗

arXiv2021

Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection

Smart contract vulnerability detection draws extensive attention in recent years due to the substantial losses caused by hacker attacks. Existing efforts for contract security analysis heavily rely on rigid rules defined by experts, which are labor-intensive and non-scalable. More importantly, expert-defined rules tend to be error-prone and suffer the inherent risk of being cheated by crafty attackers. Recent researches focus on the symbolic execution and formal analysis of smart contracts for vulnerability detection, yet to achieve a precise and scalable solution. Although several methods have been proposed to detect vulnerabilities in smart contracts, there is still a lack of effort that considers combining expert-defined security patterns with deep neural networks. In this paper, we explore using graph neural networks and expert knowledge for smart contract vulnerability detection. Specifically, we cast the rich control- and data- flow semantics of the source code into a contract graph. To highlight the critical nodes in the graph, we further design a node elimination phase to normalize the graph. Then, we propose a novel temporal message propagation network to extract the graph feature from the normalized graph, and combine the graph feature with designed expert patterns to yield a final detection system. Extensive experiments are conducted on all the smart contracts that have source code in Ethereum and VNT Chain platforms. Empirical results show significant accuracy improvements over the state-of-the-art methods on three types of vulnerabilities, where the detection accuracy of our method reaches 89.15%, 89.02%, and 83.21% for reentrancy, timestamp dependence, and infinite loop vulnerabilities, respectively.

cs.CR↗

arXiv2021

Rethinking Deep Contrastive Learning with Embedding Memory

Pair-wise loss functions have been extensively studied and shown to continuously improve the performance of deep metric learning (DML). However, they are primarily designed with intuition based on simple toy examples, and experimentally identifying the truly effective design is difficult in complicated, real-world cases. In this paper, we provide a new methodology for systematically studying weighting strategies of various pair-wise loss functions, and rethink pair weighting with an embedding memory. We delve into the weighting mechanisms by decomposing the pair-wise functions, and study positive and negative weights separately using direct weight assignment. This allows us to study various weighting functions deeply and systematically via weight curves, and identify a number of meaningful, comprehensive and insightful facts, which come up with our key observation on memory-based DML: it is critical to mine hard negatives and discard easy negatives which are less informative and redundant, but weighting on positive pairs is not helpful. This results in an efficient but surprisingly simple rule to design the weighting scheme, making it significantly different from existing mini-batch based methods which design various sophisticated loss functions to weight pairs carefully. Finally, we conduct extensive experiments on three large-scale visual retrieval benchmarks, and demonstrate the superiority of memory-based DML over recent mini-batch based approaches, by using a simple contrastive loss with momentum-updated memory.

cs.CV↗

arXiv2021

Deep Dual Consecutive Network for Human Pose Estimation

Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to video sequences. Prevalent shortcomings include the failure to handle motion blur, video defocus, or pose occlusions, arising from the inability in capturing the temporal dependency among video frames. On the other hand, directly employing conventional recurrent neural networks incurs empirical difficulties in modeling spatial contexts, especially for dealing with pose occlusions. In this paper, we propose a novel multi-frame human pose estimation framework, leveraging abundant temporal cues between video frames to facilitate keypoint detection. Three modular components are designed in our framework. A Pose Temporal Merger encodes keypoint spatiotemporal context to generate effective searching scopes while a Pose Residual Fusion module computes weighted pose residuals in dual directions. These are then processed via our Pose Correction Network for efficient refining of pose estimations. Our method ranks No.1 in the Multi-frame Person Pose Estimation Challenge on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018. We have released our code, hoping to inspire future research.

cs.CV↗

arXiv2021

Dual Encoding for Video Retrieval by Text

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Our novelty is two-fold. First, different from prior art that resorts to a specific single-level encoder, the proposed network performs multi-level encoding that represents the rich content of both modalities in a coarse-to-fine fashion. Second, different from a conventional common space learning algorithm which is either concept based or latent space based, we introduce hybrid space learning which combines the high performance of the latent space and the good interpretability of the concept space. Dual encoding is conceptually simple, practically effective and end-to-end trained with hybrid space learning. Extensive experiments on four challenging video datasets show the viability of the new method.

cs.CV↗

arXiv2020

Automatic Detection of Cardiac Chambers Using an Attention-based YOLOv4 Framework from Four-chamber View of Fetal Echocardiography

Echocardiography is a powerful prenatal examination tool for early diagnosis of fetal congenital heart diseases (CHDs). The four-chamber (FC) view is a crucial and easily accessible ultrasound (US) image among echocardiography images. Automatic analysis of FC views contributes significantly to the early diagnosis of CHDs. The first step to automatically analyze fetal FC views is locating the fetal four crucial chambers of heart in a US image. However, it is a greatly challenging task due to several key factors, such as numerous speckles in US images, the fetal cardiac chambers with small size and unfixed positions, and category indistinction caused by the similarity of cardiac chambers. These factors hinder the process of capturing robust and discriminative features, hence destroying fetal cardiac anatomical chambers precise localization. Therefore, we first propose a multistage residual hybrid attention module (MRHAM) to improve the feature learning. Then, we present an improved YOLOv4 detection model, namely MRHAM-YOLOv4-Slim. Specially, the residual identity mapping is replaced with the MRHAM in the backbone of MRHAM-YOLOv4-Slim, accurately locating the four important chambers in fetal FC views. Extensive experiments demonstrate that our proposed method outperforms current state-of-the-art, including the precision of 0.919, the recall of 0.971, the F1 score of 0.944, the mAP of 0.953, and the frames per second (FPS) of 43.

cs.CV↗

arXiv2020

Tree-Augmented Cross-Modal Encoding for Complex-Query Video Retrieval

The rapid growth of user-generated videos on the Internet has intensified the need for text-based video retrieval systems. Traditional methods mainly favor the concept-based paradigm on retrieval with simple queries, which are usually ineffective for complex queries that carry far more complex semantics. Recently, embedding-based paradigm has emerged as a popular approach. It aims to map the queries and videos into a shared embedding space where semantically-similar texts and videos are much closer to each other. Despite its simplicity, it forgoes the exploitation of the syntactic structure of text queries, making it suboptimal to model the complex queries. To facilitate video retrieval with complex queries, we propose a Tree-augmented Cross-modal Encoding method by jointly learning the linguistic structure of queries and the temporal representation of videos. Specifically, given a complex user query, we first recursively compose a latent semantic tree to structurally describe the text query. We then design a tree-augmented query encoder to derive structure-aware query representation and a temporal attentive video encoder to model the temporal characteristics of videos. Finally, both the query and videos are mapped into a joint embedding space for matching and ranking. In this approach, we have a better understanding and modeling of the complex queries, thereby achieving a better video retrieval performance. Extensive experiments on large scale video retrieval benchmark datasets demonstrate the effectiveness of our approach.

cs.CV↗

arXiv2020

Anisotropy links cell shapes to tissue flow during convergent extension

Within developing embryos, tissues flow and reorganize dramatically on timescales as short as minutes. This includes epithelial tissues, which often narrow and elongate in convergent extension movements due to anisotropies in external forces or in internal cell-generated forces. However, the mechanisms that allow or prevent tissue reorganization, especially in the presence of strongly anisotropic forces, remain unclear. We study this question in the converging and extending Drosophila germband epithelium, which displays planar polarized myosin II and experiences anisotropic forces from neighboring tissues, and we show that in contrast to isotropic tissues, cell shape alone is not sufficient to predict the onset of rapid cell rearrangement. From theoretical considerations and vertex model simulations, we predict that in anisotropic tissues two experimentally accessible metrics of cell patterns, the cell shape index and a cell alignment index, are required to determine whether an anisotropic tissue is in a solid-like or fluid-like state. We show that changes in cell shape and alignment over time in the Drosophila germband predict the onset of rapid cell rearrangement in both wild-type and snail twist mutant embryos, where our theoretical prediction is further improved when we also account for cell packing disorder. These findings suggest that convergent extension is associated with a transition to more fluid-like tissue behavior, which may help accommodate tissue shape changes during rapid developmental events.

q-bio.TO↗