Yuqi Zhang

Yuqi Zhang

Auto-generated profile, based on publicly available information

Yuqi Zhang

Baidu Inc

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
10 July 2019 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YZYuqi Zhang
Yuqi Zhang
YHYongzhen Huang
Yongzhen Huang
SYShiqi Yu
Shiqi Yu
LWLiang Wang
Liang Wang
Recently, deep learning based cross-view gait recognition becomes popular owing to the strong capacity of convolutional neural networks (CNNs). Current deep learning methods often rely on loss functions used widely in the task of face recognition, e.g., contrastive loss and triplet loss. These loss functions have the problem of hard negative mining. In this paper, a robust, effective and gait-related loss function, called angle center loss (ACL), is proposed to learn discriminative gait features. The proposed loss function is robust to different local parts and temporal window sizes. Different from center loss which learns a center for each identity, the proposed loss function learns multiple sub-centers for each angle of the same identity. Only the largest distance between the anchor feature and the corresponding crossview sub-centers is penalized, which achieves better intra-subject compactness. We also propose to extract discriminative spatialtemporal features by local feature extractors and a temporal attention model. A simplified spatial transformer network is proposed to localize the suitable horizontal parts of the human body. Local gait features for each horizontal part are extracted and then concatenated as the descriptor. We introduce long-short term memory (LSTM) units as the temporal attention model to learn the attention score for each frame, e.g., focusing more on discriminative frames and less on frames with bad quality. The temporal attention model shows better performance than the temporal average pooling or gait energy images (GEI). By combing the three aspects, we achieve the state-of-the-art results on several cross-view gait recognition benchmarks.

20 June 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
CLChong Liu
Chong Liu
YZYuqi Zhang
Yuqi Zhang
HWHongsong Wang
Hongsong Wang
WCWeihua Chen
Weihua Chen
FWFan Wang
Fan Wang
LWLiang Wang
Liang Wang
Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words. However, the close relations between coarse- and fine-grained representations for each modality are important for image-text retrieval but almost neglected. As a result, such previous works inevitably suffer from low retrieval accuracy or heavy computational cost. In this work, we address image-text retrieval from a novel perspective by combining coarse- and fine-grained representation learning into a unified framework. This framework is consistent with human cognition, as humans simultaneously pay attention to the entire sample and regional elements to understand the semantic content. To this end, a Token-Guided Dual Transformer (TGDT) architecture which consists of two homogeneous branches for image and text modalities, respectively, is proposed for image-text retrieval. The TGDT incorporates both coarse- and fine-grained retrievals into a unified framework and beneficially leverages the advantages of both retrieval approaches. A novel training objective called Consistent Multimodal Contrastive (CMC) loss is proposed accordingly to ensure the intra- and inter-modal semantic consistencies between images and texts in the common embedding space. Equipped with a two-stage inference method based on the mixed global and local cross-modal similarity, the proposed method achieves state-of-the-art retrieval performances with extremely low inference time when compared with representative recent approaches. Code is publicly available: github.com/LCFractal/TGDT.


1 January 2021
Verified
Conference Paper
Open access
YZYuqi Zhang
Yuqi Zhang
YXYuyang Xie
Yuyang Xie
LLLinfeng Luo
Linfeng Luo
FCFengming Cao
Fengming Cao

1 June 2023
Verified
Conference Paper
Closed access
YZYudian Zhang
Yudian Zhang
CXChenhao Xu
Chenhao Xu
YHYonghao Huang
Yonghao Huang
XLXinying Li
Xinying Li
YZYuqi Zhang
Yuqi Zhang
Quan YuanQuan Yuan
Quan Yuan
An accurate, stable, small size and self-powered triboelectric sensor has been made and an algorithm based on Convolutional Neural Network (CNN) and Support Vector Machine (SVM) has been proposed to realize the intelligent analysis of the data collected from the triboelectric sensor. By simulating the practical application of triboelectric sensors in different environments and analyzing the collected data, th e good performance of triboelectric sensors and the rationality and feasibility of the algorithm are verified.

29 April 2022 in arXiv
Verified
Preprint
Open access
PDF file
YZYuqi Zhang
Yuqi Zhang
YHYu Huang
Yu Huang
HWHengfeng Wei
Hengfeng Wei
XMXiaoxing Ma
Xiaoxing Ma
Internet-scale distributed systems often replicate data at multiple geographic locations to provide low latency and high availability. The Conflict-free Replicated Data Type (CRDT) is a framework that provides a principled approach to maintaining eventual consistency among data replicas. CRDTs have been notoriously difficult to design and implement correctly. Subtle deep bugs lie in the complex and tedious handling of all possible cases of conflicting data updates. We argue that the CRDT design should be formally specified and model-checked to uncover deep bugs. The implementation further needs to be systematically tested. On the one hand, the testing needs to inherit the exhaustive nature of the model checking and ensures the coverage of testing. On the other hand, the testing is expected to find coding errors which cannot be detected by design level verification. Towards the challenges above, we propose the Model Checking-driven Explorative Testing (MET) framework. At the design level, MET uses TLA+ to specify and model check CRDT designs. At the implementation level, MET conducts model checking-driven explorative testing, in the sense that the test cases are automatically generated from the model checking traces. The system execution is controlled to proceed deterministically, following the model checking trace. The explorative testing systematically controls and permutes all nondeterministic message reorderings. We apply MET in our practical development of CRDTs. The bugs in both designs and implementations of CRDTs are found. As for bugs which can be found by traditional testing techniques, MET greatly reduces the cost of fixing the bugs. Moreover, MET can find subtle deep bugs which cannot be found by existing techniques at a reasonable cost. We further discuss how MET provides us with sufficient confidence in the correctness of our CRDT designs and implementations.