no code implementations • 7 May 2024 • Zhibo Zhang, Ximing Yang, Weizhong Zhang, Cheng Jin
Cross-modal knowledge transfer enhances point cloud representation learning in LiDAR semantic segmentation.
no code implementations • 25 Apr 2024 • Zhibo Zhang, Ximing Yang, Weizhong Zhang, Cheng Jin
We apply this robust fine-tuning method to mainstream 3D point cloud pre-trained models and evaluate the quality of model parameters and the degradation of downstream task performance.
no code implementations • 16 Feb 2024 • Zhangjie Peng, Zhibo Zhang, Cunhua Pan, Marco Di Renzo, Octavia A. Dobre, Jiangzhou Wang
Specifically, by exploiting the majorization-minimization approach, each subproblem is reformulated into a tractable surrogate problem, whose closed-form solutions are obtained by Lagrange dual decomposition approach and element-wise alternating sequential optimization method.
no code implementations • 1 Feb 2024 • Xueting Huang, Zhibo Zhang, Fusen Guo, Xianghao Wang, Kun Chi, Kexin Wu
This paper proposed a comprehensive mixed-methods framework with varied samples of older adults, including user experience, usability assessments, and in-depth interviews with the integration of Explainable Artificial Intelligence (XAI) methods.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
no code implementations • 22 Oct 2023 • Zhibo Zhang, Pengfei Li, Ahmed Y. Al Hammadi, Fusen Guo, Ernesto Damiani, Chan Yeob Yeun
This paper presents a reputation-based threat mitigation framework that defends potential security threats in electroencephalogram (EEG) signal classification during model aggregation of Federated Learning.
no code implementations • 21 Oct 2023 • Pengfei Li, Zhibo Zhang, Ameena S. Al-Sumaiti, Naoufel Werghi, Chan Yeob Yeun
Metaverse is trending to create a digital circumstance that can transfer the real world to an online platform supported by large quantities of real-time interactions.
no code implementations • 8 Feb 2023 • Zhibo Zhang, Ahmed Y. Al Hammadi, Ernesto Damiani, Chan Yeob Yeun
This paper's main goal is to provide an attacker's point of view on data poisoning assaults that use label-flipping during the training phase of systems that use electroencephalogram (EEG) signals to evaluate human emotion.
no code implementations • 8 Feb 2023 • Zhibo Zhang, Sani Umar, Ahmed Y. Al Hammadi, Sangyoung Yoon, Ernesto Damiani, Chan Yeob Yeun
Industrial insider risk assessment using electroencephalogram (EEG) signals has consistently attracted a lot of research attention.
no code implementations • 31 Jan 2023 • Prince Aduama, Zhibo Zhang, Ameena S. Al Sumaiti
This prediction error was lower than initial prediction results by the LSTM model.
no code implementations • 17 Jan 2023 • Zhibo Zhang, Sani Umar, Ahmed Y. Al Hammadi, Sangyoung Yoon, Ernesto Damiani, Claudio Agostino Ardagna, Nicola Bena, Chan Yeob Yeun
The major aim of this paper is to explain the data poisoning attacks using label-flipping during the training stage of the electroencephalogram (EEG) signal-based human emotion evaluation systems deploying Machine Learning models from the attackers' perspective.
no code implementations • 26 Oct 2022 • Zhibo Zhang, Ernesto Damiani, Hussam Al Hamadi, Chan Yeob Yeun, Fatma Taher
In recent years, spammers are now trying to obfuscate their intents by introducing hybrid spam e-mail combining both image and text parts, which is more challenging to detect in comparison to e-mails containing text or image only.
Optical Character Recognition Optical Character Recognition (OCR)
no code implementations • 7 Sep 2022 • Zhibo Zhang, Ernesto Damiani, Hussam Al Hamadi, Chan Yeob Yeun, Fatma Taher
Image spam threat detection has continually been a popular area of research with the internet's phenomenal expansion.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI)
1 code implementation • 2 Sep 2022 • Zhibo Zhang, Omar Alremeithi, Maryam Almheiri, Marwa Albeshr, Xiaoxiong Zhang, Sajid Javed, Naoufel Werghi
The dataset was generated in four different scenarios where mainly the target was moving alongside the crowd, sometimes occluding with them, and other times the camera's view of the target is blocked by the crowd for a short period.
no code implementations • 13 Jul 2022 • Xiaoyu Yuan, Zhibo Zhang, Yabo Sun, Zekai Xue, Xiuyan Shao, Xiaohua Huang
This paper proposes a new database of Houma Alliance Book ancient handwritten characters and a multi-modal fusion method to recognize ancient handwritten characters.
1 code implementation • 14 Mar 2022 • Ruiwen Li, Zheda Mai, Chiheb Trabelsi, Zhibo Zhang, Jongseong Jang, Scott Sanner
In this paper, we propose TransCAM, a Conformer-based solution to WSSS that explicitly leverages the attention weights from the transformer branch of the Conformer to refine the CAM generated from the CNN branch.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
no code implementations • 13 Dec 2021 • Ximing Yang, Zhibo Zhang, Zhengfu He, Cheng Jin
As details are missing in most representations of structures, the lack of controllability to more information is one of the major weaknesses in structure-based controllable point cloud generation.
1 code implementation • 28 Nov 2021 • Zhibo Zhang, Jongseong Jang, Chiheb Trabelsi, Ruiwen Li, Scott Sanner, Yeonjeong Jeong, Dongsub Shim
Contrastive learning has led to substantial improvements in the quality of learned embedding representations for tasks such as image classification.
no code implementations • 29 May 2021 • Ruiwen Li, Zhibo Zhang, Jiani Li, Chiheb Trabelsi, Scott Sanner, Jongseong Jang, Yeonjeong Jeong, Dongsub Shim
Recent years have seen the introduction of a range of methods for post-hoc explainability of image classifier predictions.
no code implementations • 8 Dec 2020 • Zhibo Zhang, Chen Zeng, Maulikkumar Dhameliya, Souma Chowdhury, Rahul Rai
The thermal data is processed through a thresholding and Kalman filter approach to detect and track the bounding box.
no code implementations • 24 Aug 2018 • Wenbin Zhang, Jianwu Wang, Daeho Jin, Lazaros Oreopoulos, Zhibo Zhang
A self-organizing map (SOM) is a type of competitive artificial neural network, which projects the high-dimensional input space of the training samples into a low-dimensional space with the topology relations preserved.
2 code implementations • KDD 2018 • Jizhe Wang, Pipei Huang, Huan Zhao, Zhibo Zhang, Binqiang Zhao, Dik Lun Lee
Using online A/B test, we show that the online Click-Through-Rate (CTRs) are improved comparing to the previous recommendation methods widely used in Taobao, further demonstrating the effectiveness and feasibility of our proposed methods in Taobao's live production environment.