Zhenbo Xu

Zhenbo Xu

Auto-generated profile, based on publicly available information

Zhenbo Xu

Beijing University of Posts and Telecommunications

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
6 October 2018
Verified
Book Chapter
Closed access
PDF file
ZXZhenbo Xu
Zhenbo Xu
WYWei Yang
Wei Yang
AMAjin Meng
Ajin Meng
NLNanxue Lu
Nanxue Lu
HHHuan Huang
Huan Huang
LHLiusheng Huang
Liusheng Huang

3 November 2020
Verified
Book Chapter
Closed access
PDF file
ZXZhenbo Xu
Zhenbo Xu
WZWei Zhang
Wei Zhang
XTXiao Tan
Xiao Tan
WYWei Yang
Wei Yang
HHHuan Huang
Huan Huang
LHLiusheng Huang
Liusheng Huang

9 June 2021 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ZXZhenbo Xu
Zhenbo Xu
WYWei Yang
Wei Yang
WZWei Zhang
Wei Zhang
XTXiao Tan
Xiao Tan
HHHuan Huang
Huan Huang
LHLiusheng Huang
Liusheng Huang
Current multi-object tracking and segmentation (MOTS) methods follow the tracking-by-detection paradigm and adopt 2D or 3D convolutions to extract instance embeddings for instance association. However, due to the large receptive field of deep convolutional neural networks, the foreground areas of the current instance and the surrounding areas containing the nearby instances or environments are usually mixed up in the learned instance embeddings, resulting in ambiguities in tracking. In this paper, we propose a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation. In this way, the non-overlapping nature of instance segments can be fully exploited by strictly separating the foreground point cloud and the background point cloud. Moreover, multiple informative data modalities are formulated as point-wise representations to enrich point-wise features. For each instance, the embedding is learned on the foreground 2D point cloud, the environment 2D point cloud, and the smallest circumscribed bounding box. Then, similarities between instance embeddings are measured for the inter-frame association. In addition, to enable the practical utility of MOTS, we modify the one-stage instance segmentation method SpatialEmbedding for instance segmentation. The resulting efficient and effective framework, named PointTrackV2, outperforms all the state-of-the-art methods including 3D tracking methods by large margins (4.8 percent higher sMOTSA for pedestrians over MOTSFusion) with the near real-time speed (20 FPS evaluated on a single 2080Ti). Extensive evaluations on three datasets demonstrate both the effectiveness and efficiency of our method. Furthermore, as crowded scenes for cars are insufficient in current MOTS datasets, we provide a more challenging dataset named APOLLO MOTS with a much higher instance density.

11 August 2025 in Computers and Electronics in Agriculture
Verified
Journal Article
Closed access
GHGong Huang
Gong Huang
ZXZhenbo Xu
Zhenbo Xu
LLLiu Liu
Liu Liu
JCJiawei Chen
Jiawei Chen
He ZhaofengHe Zhaofeng
He Zhaofeng
FLFei Liu
Fei Liu

26 October 2023
Verified
Conference Paper
Open access
Zhenbo ShiZhenbo Shi
Zhenbo Shi
WYWei Yang
Wei Yang
ZXZhenbo Xu
Zhenbo Xu
ZYZhidong Yu
Zhidong Yu
LHLiusheng Huang
Liusheng Huang
In the field of object detector attacks, previous methods primarily rely on fixed gradient optimization or patch-based cover techniques, often leading to suboptimal attack performance and excessive distortions. To address these limitations, we propose a novel attack method, Interactive Reinforcement-based Sparse Attack (IRSA), which employs Reinforcement Learning (RL) to discover the vulnerabilities of object detectors and systematically generate erroneous results. Specifically, we formulate the process of seeking optimal margins for adversarial examples as a Markov Decision Process (MDP). We tackle the RL convergence difficulty through innovative reward functions and a composite optimization method for effective and efficient policy training. Moreover, the perturbations generated by IRSA are more subtle and difficult to detect while requiring less computational effort. Our method also demonstrates strong generalization capabilities against various object detectors. In summary, IRSA is a refined, efficient, and scalable interactive, iterative, end-to-end algorithm.

24 August 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
ZXZhenbo Xu
Zhenbo Xu
HHHai-Miao Hu
Hai-Miao Hu
LLLiu Liu
Liu Liu
DZDongping Zhang
Dongping Zhang
SZShifeng Zhang
Shifeng Zhang
WTWenming Tan
Wenming Tan
Real-time learning on real-world data streams with temporal relations is essential for intelligent agents. However, current online Continual Learning (CL) benchmarks adopt the mini-batch setting and are composed of temporally unrelated and disjoint tasks as well as pre-set class boundaries. In this paper, we delve into a real-world CL scenario for fresh recognition where algorithms are required to recognize a huge variety of products to facilitate the checkout speed. Products mainly consists of packaged cereals, seasonal fruits, and vegetables from local farms or shipped from overseas. Since algorithms process instance streams consisting of sequential images, we name this real-world CL problem as Instance-Based Continual Learning (IBCL) . Different from the current online CL setting, algorithms are required to perform instant testing and learning upon each incoming instance. Moreover, IBCL has no task boundaries or class boundaries and allows the evolution and the forgetting of old samples within each class. To promote the researches on real CL challenges, we propose the first real-world CL dataset coined the Continual Fresh Recognition (CFR) dataset, which consists of fresh recognition data streams (766 K labelled images in total) collected from 30 supermarkets. Based on the CFR dataset, we extensively evaluate the performance of current online CL methods under various settings and find that current prominent online CL methods operate at high latency and demand significant memory consumption to cache old samples for replaying. Therefore, we make the first attempt to design an efficient and effective Instant Training-Free Learning (ITFL) framework for IBCL. ITFL consists of feature extractors trained in the metric learning manner and reformulates CL as a temporal classification problem among several most similar classes. Unlike current online CL methods that cache image samples (150 KB per image) and rely on training to learn new knowledge, our framework only caches features (2 KB per image) and is free of training in deployment. Extensive evaluations across three datasets demonstrate that our method achieves comparable recognition accuracy to current methods with lower latency and less resource consumption. Our codes and datasets will be publicly available at https://github.com/detectRecog/IBCL .