Zao Zhang

Zao Zhang

Auto-generated profile, based on publicly available information

Zao Zhang

Univerisy of Sydney

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 March 2020 in Complexity
Verified
Journal Article
Open access
PDF file
ZZZao Zhang
Zao Zhang
YDYuan Dong
Yuan Dong
Today, artificial intelligence and deep neural networks have been successfully used in many applications that have fundamentally changed people’s lives in many areas. However, very limited research has been done in the meteorology area, where meteorological forecasts still rely on simulations via extensive computing resources. In this paper, we propose an approach to using the neural network to forecast the future temperature according to the past temperature values. Specifically, we design a convolutional recurrent neural network (CRNN) model that is composed of convolution neural network (CNN) portion and recurrent neural network (RNN) portion. The model can learn the time correlation and space correlation of temperature changes from historical data through neural networks. To evaluate the proposed CRNN model, we use the daily temperature data of mainland China from 1952 to 2018 as training data. The results show that our model can predict future temperature with an error around 0.907°C.

27 November 2023
Verified
Book Chapter
Closed access
PDF file
YZYu Zhang
Yu Zhang
HCHuaming Chen
Huaming Chen
ZLZhongzheng Lai
Zhongzheng Lai
ZZZao Zhang
Zao Zhang
DYDong Yuan
Dong Yuan

16 March 2024 in Future Generation Computer Systems
Verified
Journal Article
Open access
ZZZao Zhang
Zao Zhang
YZYuning Zhang
Yuning Zhang
WBWei Bao
Wei Bao
CLChangyang Li
Changyang Li
DYDong Yuan
Dong Yuan

7 August 2023
Verified
Conference Paper
Open access
YZYuning Zhang
Yuning Zhang
ZZZao Zhang
Zao Zhang
WBWei Bao
Wei Bao
DYDong Yuan
Dong Yuan
Transformer models, which have gained prominence in recent years, serve as the backbone for a wide range of deep learning applications, from natural language processing to computer vision. These models have become indispensable for various inference tasks, but their implementation often faces challenges related to GPU utilization and system throughput. Current GPU-based inference frameworks typically treat each model individually, leading to suboptimal resource management and reduced performance. In response to these limitations, we introduce ITIF: Integrated Transformers Inference Framework for multi-tenants with a shared backbone. By allowing multiple tenants to share a single backbone Transformer model on a single GPU, ITIF consolidates operators from diverse multi-tenant inference models, which in turn optimizes GPU utilization and system throughput. Our proposed framework, ITIF, represents a significant step towards improving the efficiency of deep learning, particularly for large-scale cloud providers hosting numerous models with a shared backbone. In our experiments, ITIF improved performance by up to 2.40 × compared with the baselines.

31 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
YZYu Zhang
Yu Zhang
HCHuaming Chen
Huaming Chen
WBWei Bao
Wei Bao
ZLZhongzheng Lai
Zhongzheng Lai
ZZZao Zhang
Zao Zhang
DYDong Yuan
Dong Yuan
With the rapid development of deep learning, object detection and tracking play a vital role in today's society. Being able to identify and track all the pedestrians in the dense crowd scene with computer vision approaches is a typical challenge in this field, also known as the Multiple Object Tracking (MOT) challenge. Modern trackers are required to operate on more and more complicated scenes. According to the MOT20 challenge result, the pedestrian is 4 times denser than the MOT17 challenge. Hence, improving the ability to detect and track in extremely crowded scenes is the aim of this work. In light of the occlusion issue with the human body, the heads are usually easier to identify. In this work, we have designed a joint head and body detector in an anchor-free style to boost the detection recall and precision performance of pedestrians in both small and medium sizes. Innovatively, our model does not require information on the statistical head-body ratio for common pedestrians detection for training. Instead, the proposed model learns the ratio dynamically. To verify the effectiveness of the proposed model, we evaluate the model with extensive experiments on different datasets, including MOT20, Crowdhuman, and HT21 datasets. As a result, our proposed method significantly improves both the recall and precision rate on small & medium sized pedestrians and achieves state-of-the-art results in these challenging datasets.