no code implementations • 14 Jan 2025 • Chen Tang, Bo Lv, Zifan Zheng, Bohao Yang, Kun Zhao, Ning Liao, Xiaoxing Wang, Feiyu Xiong, Zhiyu Li, Nayu Liu, Jingchi Jiang
Additionally, this study explores a novel recurrent routing strategy that may inspire further advancements in enhancing the reasoning capabilities of language models.
no code implementations • 26 Sep 2024 • Harsh Yadav, Maximilian Schaefer, Kun Zhao, Tobias Meisen
Motion prediction is an important aspect for Autonomous Driving (AD) and Advance Driver Assistance Systems (ADAS).
no code implementations • 27 Jul 2024 • Tengyao Tu, Wei Zeng, Kun Zhao, Zhenyu Zhang
The result proves that adding a classifier to the model based on the random forest algorithm is very effective, and our model generally outperforms ordinary deep learning methods.
no code implementations • 19 Jul 2024 • Kun Zhao, Jakub Prokop, Javier Montalt Tordera, Sadegh Mohammadi
We aim to harness their capabilities for breast lesion segmentation in a panoptic setting, which encompasses both semantic and instance-level predictions.
no code implementations • 28 Jun 2024 • Chen Tang, Bohao Yang, Kun Zhao, Bo Lv, Chenghao Xiao, Frank Guerin, Chenghua Lin
Named entity recognition (NER) stands as a fundamental and pivotal task within the realm of Natural Language Processing.
1 code implementation • 25 Jun 2024 • Kun Zhao, Chenghao Xiao, Chen Tang, Bohao Yang, Kai Ye, Noura Al Moubayed, Liang Zhan, Chenghua Lin
Last, we show that training on the layman's terms dataset encourages models to focus on the semantics of the reports, as opposed to overfitting to learning the report templates.
1 code implementation • 25 Jun 2024 • Bohao Yang, Dong Liu, Chenghao Xiao, Kun Zhao, Chen Tang, Chao Li, Lin Yuan, Guang Yang, Lanxiao Huang, Chenghua Lin
Large Language Models (LLMs) demonstrate remarkable ability to comprehend instructions and generate human-like text, enabling sophisticated agent simulation beyond basic behavior replication.
1 code implementation • 24 May 2024 • Kun Zhao, Bohao Yang, Chen Tang, Chenghua Lin, Liang Zhan
Our approach introduces several techniques: (1) Contrastive learning to differentiate between robust and non-robust response embeddings; (2) A novel metric for semantic sensitivity that combines embedding cosine distances with similarity learned through neural networks, and (3) a strategy for incorporating the evaluation results from both the SLM and LLMs.
no code implementations • 21 May 2024 • Haoteng Tang, Guodong Liu, Siyuan Dai, Kai Ye, Kun Zhao, Wenlu Wang, Carl Yang, Lifang He, Alex Leow, Paul Thompson, Heng Huang, Liang Zhan
The MRI-derived brain network serves as a pivotal instrument in elucidating both the structural and functional aspects of the brain, encompassing the ramifications of diseases and developmental processes.
1 code implementation • 1 Apr 2024 • Bohao Yang, Kun Zhao, Chen Tang, Dong Liu, Liang Zhan, Chenghua Lin
Trainable evaluation metrics, typically trained with true positive and randomly selected negative responses, tend to assign higher scores to responses that share greater content similarity with a given context.
no code implementations • 6 Mar 2024 • Fredrik Rusek, Jose Flordelis, Kun Zhao, Erik Bengtsson, Olof Zander
The goal of this paper is to propose a RIS which \emph{only} reflects signals from the configured impinging direction.
no code implementations • 5 Feb 2024 • Siyuan Dai, Kai Ye, Kun Zhao, Ge Cui, Haoteng Tang, Liang Zhan
In this work, we introduce a novel approach predicated on representation distance-based mutual information (MI) maximization for measuring the significance of different views, aiming at conducting more efficient contrastive learning and representation disentanglement.
1 code implementation • 22 Sep 2023 • Bohao Yang, Chen Tang, Kun Zhao, Chenghao Xiao, Chenghua Lin
Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of natural language processing tasks.
no code implementations • 15 Aug 2023 • Maximilian Schäfer, Kun Zhao, Anton Kummert
In this work, we focus on further enhancing the interaction modeling and scene understanding to support the joint prediction of all road users in a scene using spatiotemporal grids to model future occupancy.
Ranked #3 on
Trajectory Prediction
on nuScenes
1 code implementation • 26 May 2023 • Kun Zhao, Bohao Yang, Chenghua Lin, Wenge Rong, Aline Villavicencio, Xiaohui Cui
The long-standing one-to-many issue of the open-domain dialogues poses significant challenges for automatic evaluation methods, i. e., there may be multiple suitable responses which differ in semantics for a given conversational context.
1 code implementation • 2 Jan 2023 • Kun Zhao, Qian Gao, Siyuan Hao, Jie Sun, Lijian Zhou
Based on this uncertainty, a novel decision-level fusion strategy is proposed to ensure that the view with lower risk obtains more weight, making the classification more credible.
1 code implementation • 4 Aug 2022 • Yongkun Liu, Kesong Ni, Yuhan Zhang, Lijian Zhou, Kun Zhao
First, the label co-occurrence graph is obtained according to the statistical information of the data set.
1 code implementation • 30 Jul 2022 • Can Peng, Kun Zhao, Tianren Wang, Meng Li, Brian C. Lovell
The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments.
no code implementations • 7 Apr 2022 • Yutian Wang, Yuankun Xie, Kun Zhao, Hui Wang, Qin Zhang
In this paper, we propose a novel prosody disentangle method for prosodic Text-to-Speech (TTS) model, which introduces the vector quantization (VQ) method to the auxiliary prosody encoder to obtain the decomposed prosody representations in an unsupervised manner.
no code implementations • 18 Jan 2022 • Maximilian Schäfer, Kun Zhao, Markus Bühren, Anton Kummert
Predicting the future motion of surrounding road users is a crucial and challenging task for autonomous driving (AD) and various advanced driver-assistance systems (ADAS).
Ranked #7 on
Trajectory Prediction
on nuScenes
no code implementations • 12 Aug 2021 • Can Peng, Kun Zhao, Sam Maksoud, Tianren Wang, Brian C. Lovell
In this paper, we aim to alleviate this performance decay on multi-step incremental detection tasks by proposing a dilatable incremental object detector (DIODE).
no code implementations • 29 Jul 2021 • Kun Zhao, Luchuan Song, Bin Liu, Qi Chu, Nenghai Yu
Crowd counting is a challenging task due to the issues such as scale variation and perspective variation in real crowd scenes.
no code implementations • 30 Apr 2021 • Chi-Man Wong, Fan Feng, Wen Zhang, Chi-Man Vong, Hui Chen, Yichi Zhang, Peng He, Huan Chen, Kun Zhao, Huajun Chen
We first construct a billion-scale conversation knowledge graph (CKG) from information about users, items and conversations, and then pretrain CKG by introducing knowledge graph embedding method and graph convolution network to encode semantic and structural information respectively. To make the CTR prediction model sensible of current state of users and the relationship between dialogues and items, we introduce user-state and dialogue-interaction representations based on pre-trained CKG and propose K-DCN. In K-DCN, we fuse the user-state representation, dialogue-interaction representation and other normal feature representations via deep cross network, which will give the rank of candidate items to be recommended. We experimentally prove that our proposal significantly outperforms baselines and show it's real application in Alime.
Click-Through Rate Prediction
Conversational Recommendation
+3
no code implementations • 19 Apr 2021 • Sam Maksoud, Kun Zhao, Can Peng, Brian C. Lovell
To address this problem we present a method for performing BDL, namely Kernel Seed Networks (KSN), which does not require a 2-fold increase in the number of parameters.
no code implementations • 16 Mar 2021 • Hongjie He, Ke Yang, Yuwei Cai, Zijian Jiang, Qiutong Yu, Kun Zhao, JunBo Wang, Sarah Narges Fatholahi, Yan Liu, Hasti Andon Petrosians, Bingxu Hu, Liyuan Qing, Zhehan Zhang, Hongzhang Xu, Siyu Li, Kyle Gao, Linlin Xu, Jonathan Li
Building rooftop data are of importance in several urban applications and in natural disaster management.
no code implementations • 26 Feb 2021 • Chen Li, JinZhe Jiang, YaQian Zhao, RenGang Li, EnDong Wang, Xin Zhang, Kun Zhao
Decision of transfer layers and trainable layers is a major task for design of the transfer convolutional neural networks (CNN).
no code implementations • 29 Jan 2021 • Ido Freeman, Kun Zhao, Anton Kummert
The rising demand for Active Safety systems in automotive applications stresses the need for a reliable short to mid-term trajectory prediction.
no code implementations • 31 Dec 2020 • Can Peng, Kun Zhao, Sam Maksoud, Meng Li, Brian C. Lovell
Incremental learning requires a model to continually learn new tasks from streaming data.
2 code implementations • 20 Oct 2020 • Zhiping Jiang, Tom H. Luan, Han Hao, Jing Wang, Xincheng Ren, Kun Zhao, Wei Xi, Yueshen Xu, Rui Li
Three barriers always hamper the research: unknown baseband design and its influence, inadequate hardware, and the lack of versatile and flexible measurement software.
Hardware Architecture
1 code implementation • 3 Oct 2020 • Kun Zhao, Yongkun Liu, Siyuan Hao, Shaoxing Lu, Hongbin Liu, Lijian Zhou
Instead of using visual features of the whole image directly as common image-level models based on convolutional neural networks (CNNs) do, the proposed framework firstly obtains the bounding boxes of buildings in street view images from a detector.
no code implementations • 2 Oct 2020 • Thomas Kurbiel, Akash Sachdeva, Kun Zhao, Markus Buehren
Most of the current state-of-the-art Deep Learning approaches are trained on trajectory data to achieve this task.
no code implementations • 12 May 2020 • Takayuki Katsuki, Kun Zhao, Takayuki Yoshizumi
To deal with this difficulty, we formulate the task as a weakly supervised learning.
1 code implementation • CVPR 2020 • Sam Maksoud, Kun Zhao, Peter Hobson, Anthony Jennings, Brian Lovell
The difficulty of processing gigapixel whole slide images (WSIs) in clinical microscopy has been a long-standing barrier to implementing computer aided diagnostic systems.
1 code implementation • 9 Mar 2020 • Can Peng, Kun Zhao, Brian C. Lovell
To address this problem, incremental learning methods have been explored which preserve the old knowledge of deep learning models.
no code implementations • 22 Sep 2019 • Can Peng, Kun Zhao, Arnold Wiliem, Teng Zhang, Peter Hobson, Anthony Jennings, Brian C. Lovell
Critical findings are observed: (1) The best balance between detection accuracy, detection speed and file size is achieved at 8 times downsampling captured with a $40\times$ objective; (2) compression which reduces the file size dramatically, does not necessarily have an adverse effect on overall accuracy; (3) reducing the amount of training data to some extents causes a drop in precision but has a negligible impact on the recall; (4) in most cases, Faster R-CNN achieves the best accuracy in the glomerulus detection task.
no code implementations • 16 Jul 2019 • Liangchen Liu, Teng Zhang, Kun Zhao, Arnold Wiliem, Kieren Astin-Walmsley, Brian Lovell
We propose a novel two-stage zoom-in detection method to gradually focus on the object of interest.
no code implementations • 2 Jul 2019 • Kun Zhao, Takayuki Osogami, Tetsuro Morimura
To solve this problem, we consider a whole match as a Markov chain of significant events, so that event values can be estimated with a continuous parameter space by solving the Markov chain with a machine learning model.
no code implementations • 24 Jun 2019 • Sam Maksoud, Arnold Wiliem, Kun Zhao, Teng Zhang, Lin Wu, Brian C. Lovell
This is because the system can ignore the attention mechanism by assigning equal weights for all members.
1 code implementation • 24 Jun 2019 • Meng Li, Lin Wu, Arnold Wiliem, Kun Zhao, Teng Zhang, Brian C. Lovell
Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i. e, patches) and the task is to predict a single class label to the WSI.
no code implementations • 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) 2019 • Dan Jin, Jian Xu, Kun Zhao, Fangzhou Hu, Zhengyi Yang, Bing Liu, Tianzi Jiang, Yong liu
Modern advancements in deep learning provide a powerful framework for disease classification based on neuroimaging data.
no code implementations • 23 Feb 2019 • Rong Zhu, Kun Zhao, Hongxia Yang, Wei. Lin, Chang Zhou, Baole Ai, Yong Li, Jingren Zhou
An increasing number of machine learning tasks require dealing with large graph datasets, which capture rich and complex relationship among potentially billions of elements.
Distributed, Parallel, and Cluster Computing
no code implementations • 14 Jun 2018 • Kun Zhao, Arnold Wiliem, Shaokang Chen, Brian C. Lovell
Our proposed framework, named Manifold Convex Class Model, represents each class on SPD manifolds using a convex model, and classification can be performed by computing distances to the convex models.
no code implementations • 20 Mar 2018 • Teng Zhang, Johanna Carvajal, Daniel F. Smith, Kun Zhao, Arnold Wiliem, Peter Hobson, Anthony Jennings, Brian C. Lovell
In order to address the quality assessment problem, we propose a deep neural network based framework to automatically assess the slide quality in a semantic way.
1 code implementation • 14 Dec 2017 • Karl Zhanghao, Xingye Chen, Wenhui Liu, Meiqi Li, Chunyan Shan, Xiao Wang, Kun Zhao, Amit Lai, Hao Xie, Qionghai Dai, Peng Xi
The dipole nature of chromophore is important for both super-resolution microscopy and imaging molecular structure, which is nevertheless neglected in most microscopies, even including structured illumination microscopy (SIM) with polarized excitations.
Optics
no code implementations • 19 Nov 2017 • Masaharu Sakamoto, Hiroki Nakano, Kun Zhao, Taro Sekiyama
In this paper, we propose Fusion classifier in conjunction with the cascaded convolutional neural network models.
no code implementations • 1 Mar 2017 • Masaharu Sakamoto, Hiroki Nakano, Kun Zhao, Taro Sekiyama
Lung nodule classification is a class imbalanced problem because nodules are found with much lower frequency than non-nodules.
no code implementations • 2 Feb 2017 • Colin Allen, Hongliang Luo, Jaimie Murdock, Jianghuai Pu, XiaoHong Wang, Yanjie Zhai, Kun Zhao
In this paper we describe a collaborative effort between Indiana University and Xi'an Jiaotong University to support exploration and interpretation of a digital corpus of over 18, 000 ancient Chinese documents, which we refer to as the "Handian" ancient classics corpus (H\`an di\u{a}n g\u{u} j\'i, i. e, the "Han canon" or "Chinese classics").
no code implementations • 21 Feb 2016 • Liangchen Liu, Arnold Wiliem, Shaokang Chen, Kun Zhao, Brian C. Lovell
In this paper, we propose a novel approach, based on the shared structure exhibited amongst meaningful attributes, that enables us to compare between different automatic attribute discovery approaches. We then validate our approach by comparing various attribute discovery methods such as PiCoDeS on two attribute datasets.
no code implementations • 18 Sep 2015 • Kun Zhao, Azadeh Alavi, Arnold Wiliem, Brian C. Lovell
We then validate our framework on several computer vision applications by comparing against popular clustering methods on Riemannian manifolds.
no code implementations • 18 Feb 2015 • Jiajun Liu, Kun Zhao, Brano Kusy, Ji-Rong Wen, Raja Jurdak
The prediction of periodical time-series remains challenging due to various types of data distortions and misalignments.
no code implementations • 4 Mar 2014 • Azadeh Alavi, Arnold Wiliem, Kun Zhao, Brian C. Lovell, Conrad Sanderson
Recent advances suggest that encoding images through Symmetric Positive Definite (SPD) matrices and then interpreting such matrices as points on Riemannian manifolds can lead to increased classification performance.