Author name cluster

Hong Zhao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

EAAI Journal 2025 Journal Article

A review of speaker verification: Methods, network architectures, tasks and challenges

Weijie Wang
Hong Zhao
Yikun Yang
Yongjuan Yang

Speaker verification is an important branch of biometric recognition, with wide applications in identity authentication, audio monitoring, and other fields. In recent years, deep learning and meta-learning have made remarkable advancements in the field of speaker verification. Therefore, it is necessary to update existing reviews of speaker verification to reflect the latest research developments. We review literature from the past decade to provide a timely and comprehensive survey of the field. First, we outline the concept and system process of speaker verification. Then, we analyze the speech preprocessing process and common acoustic features used in the systems. Next, we present an overview of speaker modeling approaches, covering traditional probabilistic methods, deep learning-based speaker methods, and meta-learning-based speaker methods, focusing on the latter two methods. We provide an in-depth analysis and summary of the characteristics and the latest network architectures of these methods, focusing on the development of Transformer and large-scale pre-trained Transformer. Furthermore, we introduce the datasets and evaluation metrics used in speaker verification systems, focusing on a detailed and fair comparison of the performance of text-dependent and text-independent speaker verification systems. Finally, we explore the challenges faced by speaker verification systems and discuss future research opportunities.

Details DOI

EAAI Journal 2024 Journal Article

Multi-scale features with temporal information guidance for video captioning

Hong Zhao
Zhiwen Chen
Yi Yang

Video captioning aims to automatically generate a textual description for a video, which is a challenging task and has drawn attention recently. Despite existing methods have achieved impressive performance, two challenging problems are remaining to be solved. (1) In the feature encoding stage, existing methods only focus on local features or global features to improve the accuracy or readability of sentences generated, resulting in the underutilization of useful information for the given video. (2) In the decoder stage, vanilla Transformer is usually used to reason about visual relations to generate the textual captions, which is not making good use of the inter-frame temporal information, leads to the relation ambiguity and bad readability for generated captions. To solve these problems, we propose a method of video captioning based on multi-scale feature with temporal information guidance for video captioning. Firstly, the pre-training model CLIP is employed to extract video features. Secondly, the global and local features are encoded separately to learn the overall and detailed information of the video and construct multi-scale features. Finally, the gating unit is used to alleviate the problem which cannot make good use of contextual temporal information in existing decoder module base Transformer. Extensive experiments on two publicly available datasets show that the proposed model improves 4. 7%, 2. 2%, 0. 6%, 2. 0% on the MSR-VTT dataset, and 5. 1%, 9. 0%, 5. 8%, 6. 7% on the MSVD dataset compared to the best model in the comparison method in the BLEU, METEOR, ROUGE-L, and CIDEr metrics, which demonstrates the ability of our method to achieve more competitive performance.

Details DOI

EAAI Journal 2023 Journal Article

Semantic attention and relative scene depth-guided network for underwater image enhancement

Tingkai Chen
Ning Wang
Yanzheng Chen
Xiangjun Kong
Yejin Lin
Hong Zhao
Hamid Reza Karimi

In this paper, to solve unique underwater degradation challenges covering low contrast, color deviation and blurring, etc. , a novel semantic attention and relative scene depth-guided network (SARSDN) for underwater image enhancement is proposed. Main contributions are as follows: (1) By combining with diverse characteristics of red–green–blue, hue-saturation-value and Lab spaces, the multi-color space feature representation network (MSFRN) is elaborately developed, such that domain shifting can be effectively alleviated; (2) By utilizing position attention and devising multi-dilated-convolution depth perception unit, the underwater relative scene depth estimation network (URSDEN) is proposed to adapt attention weights to regions with different degrees of degradation, thereby exclusively accommodating scene depth-dependent attenuation and scattering; (3) The underwater scene semantic segmentation network (USSSN) is devised to estimate semantic attention map for reducing artifacts and increasing integrity of foreground objects during underwater image enhancement by virtue of encoder–decoder framework with deformable convolution network; and (4) The entire SARSDN scheme is ultimately created in a modular manner by integrating MSFRN, URSDEN and USSSN modules. Comprehensive experiments and comparisons thoroughly illustrate that the developed SARSDN framework outperforms typical underwater image enhancement approaches from both subjective and objective aspects, where UIQM scores are 0. 8263, 0. 9393, 1. 1817, 0. 5289, 0. 6517, 0. 5393, 0. 7917 and 0. 4651 higher than those of IBLA, ULAP, HLRP, UCM, RGHS, MLLE, UGAN and FUnIE-GAN schemes, respectively.

Details DOI

JBHI Journal 2021 Journal Article

Deep Learning Methods for Lung Cancer Segmentation in Whole-Slide Histopathology Images—The ACDC@LungHP Challenge 2019

Zhang Li
Jiehua Zhang
Tao Tan
Xichao Teng
Xiaoliang Sun
Hong Zhao
Lihong Liu
Yang Xiao

Accurate segmentation of lung cancer in pathology slides is a critical step in improving patient care. We proposed the ACDC@LungHP (Automatic Cancer Detection and Classification in Whole-slide Lung Histopathology) challenge for evaluating different computer-aided diagnosis (CADs) methods on the automatic diagnosis of lung cancer. The ACDC@LungHP 2019 focused on segmentation (pixel-wise detection) of cancer tissue in whole slide imaging (WSI), using an annotated dataset of 150 training images and 50 test images from 200 patients. This paper reviews this challenge and summarizes the top 10 submitted methods for lung cancer segmentation. All methods were evaluated using metrics using the precision, accuracy, sensitivity, specificity, and DICE coefficient (DC). The DC ranged from 0. 7354 $\pm$ 0. 1149 to 0. 8372 $\pm$ 0. 0858. The DC of the best method was close to the inter-observer agreement (0. 8398 $\pm$ 0. 0890). All methods were based on deep learning and categorized into two groups: multi-model method and single model method. In general, multi-model methods were significantly better ( p $< $ 0. 01) than single model methods, with mean DC of 0. 7966 and 0. 7544, respectively. Deep learning based methods could potentially help pathologists find suspicious regions for further analysis of lung cancer in WSI.

Details DOI

IJCAI Conference 2017 Conference Paper

Hierarchical Feature Selection with Recursive Regularization

Hong Zhao
Pengfei Zhu
Ping Wang
Qinghua Hu

In the big data era, the sizes of datasets have increased dramatically in terms of the number of samples, features, and classes. In particular, there exists usually a hierarchical structure among the classes. This kind of task is called hierarchical classification. Various algorithms have been developed to select informative features for flat classification. However, these algorithms ignore the semantic hyponymy in the directory of hierarchical classes, and select a uniform subset of the features for all classes. In this paper, we propose a new technique for hierarchical feature selection based on recursive regularization. This algorithm takes the hierarchical information of the class structure into account. As opposed to flat feature selection, we select different feature subsets for each node in a hierarchical tree structure using the parent-children relationships and the sibling relationships for hierarchical regularization. By imposing $\ell_{2, 1}$-norm regularization to different parts of the hierarchical classes, we can learn a sparse matrix for the feature ranking of each node. Extensive experiments on public datasets demonstrate the effectiveness of the proposed algorithm.

PDF Details