arXiv subjects

Chao Zhu

Publications and source records attributed to Chao Zhu.

At least 37 records · Page 2Linked to original sources

arXiv2023

Boosting Multi-Modal E-commerce Attribute Value Extraction via Unified Learning Scheme and Dynamic Range Minimization

With the prosperity of e-commerce industry, various modalities, e.g., vision and language, are utilized to describe product items. It is an enormous challenge to understand such diversified data, especially via extracting the attribute-value pairs in text sequences with the aid of helpful image regions. Although a series of previous works have been dedicated to this task, there remain seldomly investigated obstacles that hinder further improvements: 1) Parameters from up-stream single-modal pretraining are inadequately applied, without proper jointly fine-tuning in a down-stream multi-modal task. 2) To select descriptive parts of images, a simple late fusion is widely applied, regardless of priori knowledge that language-related information should be encoded into a common linguistic embedding space by stronger encoders. 3) Due to diversity across products, their attribute sets tend to vary greatly, but current approaches predict with an unnecessary maximal range and lead to more potential false positives. To address these issues, we propose in this paper a novel approach to boost multi-modal e-commerce attribute value extraction via unified learning scheme and dynamic range minimization: 1) Firstly, a unified scheme is designed to jointly train a multi-modal task with pretrained single-modal parameters. 2) Secondly, a text-guided information range minimization method is proposed to adaptively encode descriptive parts of each modality into an identical space with a powerful pretrained linguistic model. 3) Moreover, a prototype-guided attribute range minimization method is proposed to first determine the proper attribute set of the current product, and then select prototypes to guide the prediction of the chosen attributes. Experiments on the popular multi-modal e-commerce benchmarks show that our approach achieves superior performance over the other state-of-the-art techniques.

cs.CV↗

arXiv2023

VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision

Detecting pedestrians accurately in urban scenes is significant for realistic applications like autonomous driving or video surveillance. However, confusing human-like objects often lead to wrong detections, and small scale or heavily occluded pedestrians are easily missed due to their unusual appearances. To address these challenges, only object regions are inadequate, thus how to fully utilize more explicit and semantic contexts becomes a key problem. Meanwhile, previous context-aware pedestrian detectors either only learn latent contexts with visual clues, or need laborious annotations to obtain explicit and semantic contexts. Therefore, we propose in this paper a novel approach via Vision-Language semantic self-supervision for context-aware Pedestrian Detection (VLPD) to model explicitly semantic contexts without any extra annotations. Firstly, we propose a self-supervised Vision-Language Semantic (VLS) segmentation method, which learns both fully-supervised pedestrian detection and contextual segmentation via self-generated explicit labels of semantic classes by vision-language models. Furthermore, a self-supervised Prototypical Semantic Contrastive (PSC) learning method is proposed to better discriminate pedestrians and other classes, based on more explicit and semantic contexts obtained from VLS. Extensive experiments on popular benchmarks show that our proposed VLPD achieves superior performances over the previous state-of-the-arts, particularly under challenging circumstances like small scale and heavy occlusion. Code is available at https://github.com/lmy98129/VLPD.

cs.CV↗

arXiv2023

Realization of multiple charge density waves in NbTe2 at the monolayer limit

Abstract: Layered transition-metal dichalcogenides (TMDCs) down to the monolayer (ML) limit provide a fertile platform for exploring charge-density waves (CDWs). Though bulk NbTe2 is known to harbor a single axis 3*1 CDW coexisting with non-trivial quantum properties, the scenario in the ML limit is still experimentally unknown. In this study, we unveil the richness of the CDW phases in ML NbTe2, where not only the theoretically predicted 4*4 and 4*1 phases, but also two unexpected sqrt(28)*sqrt(28) and sqrt(19)*sqrt(19) phases, can be realized. For such a complex CDW system, we establish an exhaustive growth phase diagram via systematic efforts in the material synthesis and scanning tunneling microscope characterization. Moreover, we report that the energetically stable phase is the larger scale order (sqrt(19)*sqrt(19)), which is surprisingly in contradiction to the prior prediction (4*4). These findings are confirmed using two different kinetic pathways, i.e., direct growth at proper growth temperatures (T), and low-T growth followed by high-T annealing. Our results provide a comprehensive diagram of the "zoo" of CDW orders in ML 1T-NbTe2 for the first time and offer a new material platform for studying novel quantum phases in the 2D limit.

cond-mat.mtrl-sci↗

arXiv2022

Boosting Video Super Resolution with Patch-Based Temporal Redundancy Optimization

The success of existing video super-resolution (VSR) algorithms stems mainly exploiting the temporal information from the neighboring frames. However, none of these methods have discussed the influence of the temporal redundancy in the patches with stationary objects and background and usually use all the information in the adjacent frames without any discrimination. In this paper, we observe that the temporal redundancy will bring adverse effect to the information propagation,which limits the performance of the most existing VSR methods. Motivated by this observation, we aim to improve existing VSR algorithms by handling the temporal redundancy patches in an optimized manner. We develop two simple yet effective plug and play methods to improve the performance of existing local and non-local propagation-based VSR algorithms on widely-used public videos. For more comprehensive evaluating the robustness and performance of existing VSR algorithms, we also collect a new dataset which contains a variety of public videos as testing set. Extensive evaluations show that the proposed methods can significantly improve the performance of existing VSR methods on the collected videos from wild scenarios while maintain their performance on existing commonly used datasets. The code is available at https://github.com/HYHsimon/Boosted-VSR.

cs.CV↗

arXiv2022

Strong Neel ordering and luminescence correlation in a two-dimensional antiferromagnet

Magneto-optical effect has been widely used in light modulation, optical sensing and information storage. Recently discovered two-dimensional (2D) van der Waals layered magnets are considered as promising platforms for investigating novel magneto-optical phenomena and devices, due to the long-range magnetic ordering down to atomically-thin thickness, rich species and tunable properties. However, majority 2D antiferromagnets suffer from low luminescence efficiency which hinders their magneto-optical investigations and applications. Here, we uncover strong light-magnetic ordering interactions in 2D antiferromagnetic MnPS3 utilizing a newly-emerged near-infrared photoluminescence (PL) mode far below its intrinsic bandgap. This ingap PL mode shows strong correlation with the Neel ordering and persists down to monolayer thickness. Combining the DFT, STEM and XPS, we illustrate the origin of the PL mode and its correlation with Neel ordering, which can be attributed to the oxygen ion-mediated states. Moreover, the PL strength can be further tuned and enhanced using ultraviolet-ozone treatment. Our studies offer an effective approach to investigate light-magnetic ordering interactions in 2D antiferromagnetic semiconductors.

physics.optics↗

arXiv2022

WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma

Lung cancer is the leading cause of cancer death worldwide, and adenocarcinoma (LUAD) is the most common subtype. Exploiting the potential value of the histopathology images can promote precision medicine in oncology. Tissue segmentation is the basic upstream task of histopathology image analysis. Existing deep learning models have achieved superior segmentation performance but require sufficient pixel-level annotations, which is time-consuming and expensive. To enrich the label resources of LUAD and to alleviate the annotation efforts, we organize this challenge WSSS4LUAD to call for the outstanding weakly-supervised semantic segmentation (WSSS) techniques for histopathology images of LUAD. Participants have to design the algorithm to segment tumor epithelial, tumor-associated stroma and normal tissue with only patch-level labels. This challenge includes 10,091 patch-level annotations (the training set) and over 130 million labeled pixels (the validation and test sets), from 87 WSIs (67 from GDPH, 20 from TCGA). All the labels were generated by a pathologist-in-the-loop pipeline with the help of AI models and checked by the label review board. Among 532 registrations, 28 teams submitted the results in the test phase with over 1,000 submissions. Finally, the first place team achieved mIoU of 0.8413 (tumor: 0.8389, stroma: 0.7931, normal: 0.8919). According to the technical reports of the top-tier teams, CAM is still the most popular approach in WSSS. Cutmix data augmentation has been widely adopted to generate more reliable samples. With the success of this challenge, we believe that WSSS approaches with patch-level annotations can be a complement to the traditional pixel annotations while reducing the annotation efforts. The entire dataset has been released to encourage more researches on computational pathology in LUAD and more novel WSSS techniques.

eess.IV↗

arXiv2022

On an Ergodic Two-Sided Singular Control Problem

Motivated by applications in natural resource management, risk management, and finance, this paper is focused on an ergodic two-sided singular control problem for a general one-dimensional diffusion process. The control is given by a bounded variation process. Under some mild conditions, the optimal reward value as well as an optimal control policy are derived by the vanishing discount method. Moreover, the Abelian and Cesàro limits are established. Then a direct solution approach is provided at the end of the paper.

math.OC↗

arXiv2022

1T-FeS$_2$$:$ a new type of two-dimensional metallic ferromagnet

Discovery of intrinsic two-dimensional (2D) magnetic materials is crucial for understanding the fundamentals of 2D magnetism and realizing next-generation magnetoelectronic and magneto-optical devices. Although significant efforts have been devoted to identifying 2D magnetism by exfoliating bulk magnetic layered materials, seldom studies are performed to synthesize ultra-thin magnetic materials directly for non-layered magnetic materials. Here, we report the successful synthesis of a new type of theoretically proposed 2D metallic ferromagnet 1T FeS2, through the molten-salt-assisted chemical vapor deposition (CVD) method. The long-range 2D ferromagnetic order is confirmed by the observation of a large anomalous Hall effect (AHE) and a hysteretic magnetoresistance. The experimentally detected out-of-plane ferromagnetic ordering is theoretically suported with Stoner criterion. Our findings open up new possibilities to search novel 2D ferromagnets in non-layered compounds and render opportunities for realizing realistic ultra-thin spintronic devices.

cond-mat.mtrl-sci↗

arXiv2021

Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring

The success of the state-of-the-art video deblurring methods stems mainly from implicit or explicit estimation of alignment among the adjacent frames for latent video restoration. However, due to the influence of the blur effect, estimating the alignment information from the blurry adjacent frames is not a trivial task. Inaccurate estimations will interfere the following frame restoration. Instead of estimating alignment information, we propose a simple and effective deep Recurrent Neural Network with Multi-scale Bi-directional Propagation (RNN-MBP) to effectively propagate and gather the information from unaligned neighboring frames for better video deblurring. Specifically, we build a Multi-scale Bi-directional Propagation~(MBP) module with two U-Net RNN cells which can directly exploit the inter-frame information from unaligned neighboring hidden states by integrating them in different scales. Moreover, to better evaluate the proposed algorithm and existing state-of-the-art methods on real-world blurry scenes, we also create a Real-World Blurry Video Dataset (RBVD) by a well-designed Digital Video Acquisition System (DVAS) and use it as the training and evaluation dataset. Extensive experimental results demonstrate that the proposed RBVD dataset effectively improves the performance of existing algorithms on real-world blurry videos, and the proposed algorithm performs favorably against the state-of-the-art methods on three typical benchmarks. The code is available at https://github.com/XJTU-CVLAB-LOWLEVEL/RNN-MBP.

eess.IV↗

arXiv2021

Semantic Bilinear Pooling for Fine-Grained Recognition

Naturally, fine-grained recognition, e.g., vehicle identification or bird classification, has specific hierarchical labels, where fine categories are always harder to be classified than coarse categories. However, most of the recent deep learning based methods neglect the semantic structure of fine-grained objects and do not take advantage of the traditional fine-grained recognition techniques (e.g. coarse-to-fine classification). In this paper, we propose a novel framework with a two-branch network (coarse branch and fine branch), i.e., semantic bilinear pooling, for fine-grained recognition with a hierarchical label tree. This framework can adaptively learn the semantic information from the hierarchical levels. Specifically, we design a generalized cross-entropy loss for the training of the proposed framework to fully exploit the semantic priors via considering the relevance between adjacent levels and enlarge the distance between samples of different coarse classes. Furthermore, our method leverages only the fine branch when testing so that it adds no overhead to the testing time. Experimental results show that our proposed method achieves state-of-the-art performance on four public datasets.

cs.CV↗

arXiv2021

SiamPolar: Semi-supervised Realtime Video Object Segmentation with Polar Representation

Video object segmentation (VOS) is an essential part of autonomous vehicle navigation. The real-time speed is very important for the autonomous vehicle algorithms along with the accuracy metric. In this paper, we propose a semi-supervised real-time method based on the Siamese network using a new polar representation. The input of bounding boxes is initialized rather than the object masks, which are applied to the video object detection tasks. The polar representation could reduce the parameters for encoding masks with subtle accuracy loss so that the algorithm speed can be improved significantly. An asymmetric siamese network is also developed to extract the features from different spatial scales. Moreover, the peeling convolution is proposed to reduce the antagonism among the branches of the polar head. The repeated cross-correlation and semi-FPN are designed based on this idea. The experimental results on the DAVIS-2016 dataset and other public datasets demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2021

Controlled synthesis of MoxW1-xTe2 atomic layers with emergent quantum states

Recently, new states of matter like superconducting or topological quantum states were found in transition metal dichalcogenides (TMDs) and manifested themselves in a series of exotic physical behaviors. Such phenomena have been demonstrated to exist in a series of transition metal tellurides including MoTe2, WTe2 and alloyed MoxW1-xTe2. However, the behaviors in the alloy system have been rarely addressed due to their difficulty in obtaining atomic layers with controlled composition, albeit the alloy offers a great platform to tune the quantum states. Here, we report a facile CVD method to synthesize the MoxW1-xTe2 with controllable thickness and chemical composition ratios. The atomic structure of monolayer MoxW1-xTe2 alloy was experimentally confirmed by scanning transmission electron microscopy (STEM). Importantly, two different transport behaviors including superconducting and Weyl semimetal (WSM) states were observed in Mo-rich Mo0.8W0.2Te2 and W-rich Mo0.2W0.8Te2 samples respectively. Our results show that the electrical properties of MoxW1-xTe2 can be tuned by controlling the chemical composition, demonstrating our controllable CVD growth method is an efficient strategy to manipulate the physical properties of TMDCs. Meanwhile, it provides a perspective on further comprehension and shed light on the design of device with topological multicomponent TMDCs materials.

cond-mat.mtrl-sci↗

arXiv2020

Dimensionality-dependent type-II Weyl semimetal state in Mo$_{0.25}$W$_{0.75}$Te$_{2}$

Weyl nodes and Fermi arcs in type-II Weyl semimetals (WSMs) have led to lots of exotic transport phenomena. Recently, Mo$_{0.25}$W$_{0.75}$Te$_{2}$ has been established as a type-II WSM with Weyl points located near Fermi level, which offers an opportunity to study its intriguing band structure by electrical transport measurements. Here, by selecting a special sample with the thickness gradient across two- (2D) and three-dimensional (3D) regime, we show strong evidences that Mo$_{0.25}$W$_{0.75}$Te$_{2}$ is a type-II Weyl semimetal by observing the following two dimensionality-dependent transport features: 1) A chiral-anomaly-induced anisotropic magneto-conductivity enhancement, proportional to the square of in-plane magnetic field (B$_{in}$$^{2}$); 2) An additional quantum oscillation with thickness-dependent phase shift. Our theoretical calculations show that the observed quantum oscillation originates from a Weyl-orbit-like scenario due to the unique band structure of Mo$_{0.25}$W$_{0.75}$Te$_{2}$. The in situ dimensionality-tuned transport experiment offers a new strategy to search for type-II WSMs.

cond-mat.mes-hall↗

arXiv2020

Mutual-Supervised Feature Modulation Network for Occluded Pedestrian Detection

State-of-the-art pedestrian detectors have achieved significant progress on non-occluded pedestrians, yet they are still struggling under heavy occlusions. The recent occlusion handling strategy of popular two-stage approaches is to build a two-branch architecture with the help of additional visible body annotations. Nonetheless, these methods still have some weaknesses. Either the two branches are trained independently with only score-level fusion, which cannot guarantee the detectors to learn robust enough pedestrian features. Or the attention mechanisms are exploited to only emphasize on the visible body features. However, the visible body features of heavily occluded pedestrians are concentrated on a relatively small area, which will easily cause missing detections. To address the above issues, we propose in this paper a novel Mutual-Supervised Feature Modulation (MSFM) network, to better handle occluded pedestrian detection. The key MSFM module in our network calculates the similarity loss of full body boxes and visible body boxes corresponding to the same pedestrian so that the full-body detector could learn more complete and robust pedestrian features with the assist of contextual features from the occluding parts. To facilitate the MSFM module, we also propose a novel two-branch architecture, consisting of a standard full body detection branch and an extra visible body classification branch. These two branches are trained in a mutual-supervised way with full body annotations and visible body annotations, respectively. To verify the effectiveness of our proposed method, extensive experiments are conducted on two challenging pedestrian datasets: Caltech and CityPersons, and our approach achieves superior performance compared to other state-of-the-art methods on both datasets, especially in heavy occlusion case.

cs.CV↗

arXiv2020

Stem-leaf segmentation and phenotypic trait extraction of maize shoots from three-dimensional point cloud

Nowadays, there are many approaches to acquire three-dimensional (3D) point clouds of maize plants. However, automatic stem-leaf segmentation of maize shoots from three-dimensional (3D) point clouds remains challenging, especially for new emerging leaves that are very close and wrapped together during the seedling stage. To address this issue, we propose an automatic segmentation method consisting of three main steps: skeleton extraction, coarse segmentation based on the skeleton, fine segmentation based on stem-leaf classification. The segmentation method was tested on 30 maize seedlings and compared with manually obtained ground truth. The mean precision, mean recall, mean micro F1 score and mean over accuracy of our segmentation algorithm were 0.964, 0.966, 0.963 and 0.969. Using the segmentation results, two applications were also developed in this paper, including phenotypic trait extraction and skeleton optimization. Six phenotypic parameters can be accurately and automatically measured, including plant height, crown diameter, stem height and diameter, leaf width and length. Furthermore, the values of R2 for the six phenotypic traits were all above 0.94. The results indicated that the proposed algorithm could automatically and precisely segment not only the fully expanded leaves, but also the new leaves wrapped together and close together. The proposed approach may play an important role in further maize research and applications, such as genotype-to-phenotype study, geometric reconstruction and dynamic growth animation. We released the source code and test data at the web site https://github.com/syau-miao/seg4maize.git

cs.CV↗

arXiv2020

On Feller and Strong Feller Properties and Irreducibility of Regime-Switching Jump Diffusion Processes with Countable Regimes

This work focuses on a class of regime-switching jump diffusion processes with a countably infinite state space for the discrete component. Such processes can be used to model complex hybrid systems in which both structural changes, small fluctuations as well as big spikes coexist and are intertwined. The paper provides weak sufficient conditions for Feller and strong Feller properties and irreducibility for such processes. The conditions are presented in terms of the coefficients of the associated stochastic differential equations.

math.PR↗

arXiv2020

On Strong Feller Property, Exponential Ergodicity and Large Deviations Principle for Stochastic Damping Hamiltonian Systems with State-Dependent Switching

This work focuses on a class of stochastic damping Hamiltonian systems with state-dependent switching, where the switching process has a countably infinite state space. After establishing the existence and uniqueness of a global weak solution via the martingale approach under very mild conditions, the paper next proves the strong Feller property for regime-switching stochastic damping Hamiltonian systems by the killing technique together with some resolvent and transition probability identities. The commonly used continuity assumption for the switching rates $q_{kl}(\cdot)$ in the literature is relaxed to measurability in this paper. Finally the paper provides sufficient conditions for exponential ergodicity and large deviations principle for regime-switching stochastic damping Hamiltonian systems. Several examples on regime-switching van der Pol and (overdamped) Langevin systems are studied in detail for illustration.

math.PR↗

arXiv2020

Closed-loop Equilibrium for Time-Inconsistent McKean-Vlasov Controlled Problem

The paper deals with a class of time-inconsistent control problems for McKean-Vlasov dynamics. By solving a backward time-inconsistent Hamilton-Jacobi-Bellman (HJB for short) equation coupled with a forward distribution-dependent stochastic differential equation, we investigate the existence and uniqueness of a closed-loop equilibrium for such time-inconsistent distribution-dependent control problem. Moreover, a special case of semi-linear McKean-Vlasov dynamics with a quadratic-type cost functional is considered due to its special structure.

math.OC↗