YGYanchao Gong

Yanchao Gong

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yanchao Gong has a total of 32 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Inter-Frame Reference Dependency Motivated Initial Quantization Parameter Selection for Screen Content Video Rate Control Using VVC

    by Yanchao Gong, Yinghua Li, Hong Guo, Kaifang Yang, Nam Ling

    Rate control (RC) plays a crucial role in video services, with the aim of improving video quality while meeting the channel bandwidth constraint. Initial quantization parameter selection (IQS) is one of the key techniques in RC, which significantly affects the performance of RC. The IQS recommended by the state-of-the-art VVC standard ignores the important influence of inter-frame reference dependency (IRD), resulting in low coding efficiency. To address this issue, an IRD motivated IQS method for screen content videos (SCVs) using VVC, referred to as IRD-IQS-SCV, is proposed in this paper. First, the theoretical analysis and experimental verification are conducted to prove that the IRD is a key factor influencing the IQS. Then, a novel bit allocation model considering the IRD is created. Furthermore, the bit allocation model is effectively solved through the interior point method and the designed SCV classification method, upon which the IRD-IQS-SCV is formulated. Compared with the IQS method recommended by VVC, the average BD-rate corresponding to the IRD-IQS-SCV is -7.13% for all test sequences, with BE savings of 2.59%, quality fluctuation degree reduction of 3.58%, and computational complexity savings of 4.78%.

  • Rate-Distortion-Optimization-Driven Quantization Parameter Cascading for Screen Content Video Coding Using VVC

    by Yanchao Gong, Yinghua Li, Baogui Li, Kaifang Yang, Nam Ling

    Screen content videos (SCVs) have been widely used in television broadcasting, video conferencing, online education, and other fields. VVC is a new generation video coding standard for SCVs, where the quantization parameter (QP) is one of the key coding parameters that significantly affects the coding efficiency of SCVs. The method of selecting optimal QPs for pictures located at different temporal layers is called quantization parameter cascading (QPC). The QPC method recommended by VVC test model, i.e., VTM, does not take into account the impact of video content characteristics on QP selection, resulting in lower coding efficiency of SCVs. To address this issue, a QPC method driven by the rate-distortion (R-D) optimization for SCVs (QPC-SCV), was proposed. Combining experiments and the hybrid coding framework principles of VVC, a novel R-D cost function applicable to the SCV coding characteristics was first established and validated, where the spatiotemporal content characteristics of SCVs were evaluated to predict the model parameters. Then, a video motion form classification and particle swarm optimization were further proposed to effectively solve the R-D cost function and obtain optimized QPs. Compared with the QPC recommended by VTM, the QPC-SCV improves the coding efficiency of SCVs while reducing the coding time. For all test sequences, the average BD-rate corresponding to the QPC-SCV is −6.90%, and the average coding time is reduced by 4.56%.


  • Open Access

    Deep Active Learning Image Classification Algorithm Based on Class-Wise Self-Knowledge Distillation

    by Yuliang Pang, Ying Liu, Yu Hao, Yanchao Gong, Daxiang Li, Zhijie Xu

    The success of image classification techniques based on deep learning relies heavily on a large amount of labeled data. However, the cost of data annotation is often expensive. This paper investigates active learning algorithms for image classification to reduce the cost of data annotation. However, traditional active learning algorithms for image classification suffer from overfitting issues due to training deep neural networks with millions of parameters using a small amount of labeled data. This makes it difficult for the model to effectively assess the information richness of unknown unlabeled samples and is detrimental to the selection of high-value samples. To alleviate these issues, this paper proposes a deep active learning-based image classification algorithm with class-wise self-knowledge distillation. This algorithm reduces overfitting and class-wise variations by matching or distilling the predictive distribution between different samples with the same label during training, thereby enabling a more accurate evaluation of the informativeness of unlabeled data by the active learning algorithm and improving the performance of the classification model. Additionally, an efficient Shuffle Attention mechanism is introduced to improve the sample selection strategy by combining spatial and channel feature information of the images. The proposed algorithm is compared with five active learning baselines on CIFAR10, CIFAR100, SVHN, and FashionMNIST datasets. Experimental results demonstrate the proposed algorithm exhibits superior classification performance.

  • Quantization Parameter Cascading for Surveillance Video Coding Considering All Inter Reference Frames

    by Yanchao Gong, Kaifang Yang, Ying Liu, Keng-Pang Lim, Nam Ling, Hong Ren Wu

    Video surveillance and its applications have become increasingly ubiquitous in modern daily life. In video surveillance system, video coding as a critical enabling technology determines the effective transmission and storage of surveillance videos. In order to meet the real-time or time-critical transmission requirements of video surveillance systems, the low-delay (LD) configuration of the advanced high efficiency video coding (HEVC) standard is usually used to encode surveillance videos. The coding efficiency of the LD configuration is closely related to the quantization parameter (QP) cascading technique which selects or determines the QPs for encoding. However, the quantization parameter cascading (QPC) technique currently adopted for the LD configuration in HEVC test model (i.e., HM) is not optimized since it has not taken full account of the reference dependency in coding. In this paper, an efficient QPC technique for surveillance video coding, referred to as QPC-SV, is proposed, considering all inter reference frames under the LD configuration. Experimental results demonstrate the efficacy of the proposed QPC-SV. Compared with the default configuration of QPC in the HM, the QPC-SV achieves significant rate-distortion performance gain with average BD-rates of -9.35% and -9.76% for the LDP and LDB configurations, respectively.


  • Wavelet-Energy-Weighted Local Binary Pattern Analysis for Tire Tread Pattern Classification

    by Ying Liu, Shuai Zhang, Fuping Wang, Kengpang Lim, Qiqi Liu, Yanbo Lei, Yanchao Gong, Jin Lu

    Tire tread pattern image classification plays an important role in crime scene and traffic accident investigation. Due to the lack of standard test dataset, there is little work done in this area. For efficient texture feature description, inherent characteristic of tire patterns need to be considered. Leveraging on the directionality characteristics of tread patterns, a novel texture feature extraction algorithm is proposed based on adaptive weighted feature fusion with the weights defined by sub-band energy ratio. The proposed approach consists of: (1) discrete wavelet decomposition of tire tread image to obtain low frequency, horizontal, vertical and diagonal sub-bands; (2) extraction of rotation-invariant uniform local binary pattern features from the sub-band images; (3) concatenating the tread pattern directional features, weighted by their corresponding sub-band energies. Applying SVM for tire tread pattern classification, experimental results on real-world tire tread patterns show that the proposed texture feature extraction algorithm is outperforms other prior methods.


  • Temporal-Layer-Motivated Lambda Domain Picture Level Rate Control for Random-Access Configuration in H.265/HEVC

    by Yanchao Gong, Shuai Wan, Kaifang Yang, Hong Ren Wu, Ying Liu

    Rate control is a key technique for video communication systems. The aim of rate control is to transmit the best possible quality video sequences under various restrictions, such as channel bandwidth, buffer capacity, maximum time delay allowed for a given service, and so on. The λ domain rate control technique ( λ -RC) has been integrated into the latest high efficiency video coding standard (H.265/HEVC) test model, due to its accurate bit estimation and high rate-distortion performance. However, it is found that the λ -RC is not the optimal choice under the random-access configuration. When the random-access configuration is used, pictures are organized into temporal layers, where pictures in different layers are of different importance in terms of prediction. In this paper, a picture level lambda domain rate control technique for the random-access configuration in H.265/HEVC is proposed. The influence of temporal layers is effectively considered in the proposed algorithm referred to as TL- λ -PRC. Experimental results verify that the proposed TL-λ -PRC is efficient in coding performance and accurate in bit estimation. Compared with the λ -RC with the fixed ration bit allocation which has been implemented in the test model of H.265/HEVC (HM 14.0), TL- λ -PRC achieves an average reduction of 4.10% and 3.49% for slow motion and fast motion sequences, respectively, in BD-rate (Bjøntegaard-Delta bitrate) with more accurate bit estimation. The performance of different algorithms in terms of algorithm complexity and quality fluctuation are also carefully analyzed in this contribution.


  • Rate-Distortion-Optimization-Based Quantization Parameter Cascading Technique for Random-Access Configuration in H.265/HEVC

    by Yanchao Gong, Shuai Wan, Kaifang Yang, Yuan Yang, Bo Li

    The random-access configuration is employed in H.265/HEVC video coding to make inter-frame prediction more efficient. The coding efficiency under the random-access configuration is closely related to the quantization parameter cascading (QPC) technique which determines the QP for encoding pictures in different temporal layers. The present QPC technique for the random-access configuration in H.265/HEVC is not optimized. In this paper, first, a rate-distortion-optimization-based technique for QPC, referred to as RDO-QPC, is proposed for the random-access configuration in H.265/HEVC. Based on the results from RDO-QPC, a simplified QPC technique, referred to as SRDO-QPC, is proposed. The experimental results verify the efficiency of the proposed two QPC techniques. Compared with the original configuration of QPC in H.265/HEVC, RDO-QPC achieves an average gain of 0.19 dB in APSNR and an average reduction of 4.87% in ABR, while SRDO-QPC achieves an average gain of 0.17 dB in APSNR and an average reduction of 4.32% in ABR. These two QPC techniques can both be used in practical situations, meeting different requirements of computational complexity.