no code implementations • 8 Apr 2024 • Yu Qin, Brittany Terese Fasy, Carola Wenk, Brian Summa
To address this challenge, we introduce the merge tree neural networks (MTNN), a learned neural network model designed for merge tree comparison.
1 code implementation • 5 Apr 2024 • Ye Wei, Bo Peng, Ruiwen Xie, Yangtao Chen, Yu Qin, Peng Wen, Stefan Bauer, Po-Yen Tung
Our method demonstrates wide applicability to a wide range of real-world complex systems spanning materials, physics, and biology, considerably outperforming state-of-the-art algorithms.
no code implementations • 19 Mar 2024 • Zhichao Feng, Junjiie Xie, Kaiyuan Li, Yu Qin, Pengfei Wang, Qianzhong Li, Bin Yin, Xiang Li, Wei Lin, Shangguang Wang
We first identify contexts that share similar user preferences with the target context and then locate the corresponding PoIs based on these identified contexts.
no code implementations • 29 Feb 2024 • Qiao Han, Yong Huang, xinling Guo, Yiteng Zhai, Yu Qin, Yao Yang
Recent studies have revealed the vulnerability of Deep Neural Networks (DNNs) to adversarial examples, which can easily fool DNNs into making incorrect predictions.
1 code implementation • 27 Dec 2023 • Xiao Fang, Xin Gao, Baofeng Li, Feng Zhai, Yu Qin, Zhihang Meng, Jiansheng Lu, Chun Xiao
Low-light image enhancement aims to improve the perception of images collected in dim environments and provide high-quality data support for image recognition tasks.
no code implementations • 22 Sep 2023 • Yu Qin, Brittany Terese Fasy, Carola Wenk, Brian Summa
This paper presents the first approach to visualize the importance of topological features that define classes of data.
no code implementations • 7 Aug 2023 • Bin Yin, Junjie Xie, Yu Qin, Zixiang Ding, Zhichao Feng, Xiang Li, Wei Lin
The analysis and mining of user heterogeneous behavior are of paramount importance in recommendation systems.
no code implementations • 26 Jul 2023 • Duo Zhang, Yuren Pang, Yu Qin
The current framework for climate change negotiation models presents several limitations that warrant further research and development.
no code implementations • 26 Jul 2023 • Yu Qin, Duo Zhang, Yuren Pang
We demonstrate our negotiation model within the RICE-N framework, illustrating a promising approach for facilitating international cooperation on climate change mitigation.
no code implementations • 6 Jul 2022 • Yu Qin, Alex Sheremet
Because the brain is a multi-scale system too, a similar mechanism must be active in the brain.
no code implementations • 16 Jun 2022 • Yu Qin, Alex Sheremet
An ensemble average over a cell population then produces a closed system of equations involving two mesoscopic state variables: the density of kinetic energy J, carried by sodium ionic currents, and the excitability H of the neural field, which could be described as the average state of gating variable h. The resulting model is represented as essentially a subthreshold process; and the dynamical role of the firing rate is naturally reassessed as describing energy transfers.
no code implementations • 31 Dec 2021 • Jianqiang Huang, Yu Qin, Jiaxin Qi, Qianru Sun, Hanwang Zhang
We focus on the confounding bias between language and location in the visual grounding pipeline, where we find that the bias is the major visual reasoning bottleneck.
no code implementations • 31 Oct 2021 • Xiaoshuang Chen, Yiru Zhao, Yu Qin, Fei Jiang, Mingyuan Tao, Xiansheng Hua, Hongtao Lu
Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e. g. persons) in images.
no code implementations • 25 May 2021 • Yu Qin, Brittany Terese Fasy, Carola Wenk, Brian Summa
In this paper, we propose a persistence diagram hashing framework that learns a binary code representation of persistence diagrams, which allows for fast computation of distances.
no code implementations • NeurIPS Workshop TDA_and_Beyond 2020 • Brittany Fasy, Yu Qin, Brian Summa, Carola Wenk
Different vectorizations of PD summary are commonly used in machine learning applications, however distances between vectorized persistence summaries may differ greatly from the distances between the original PDs.
no code implementations • 24 Oct 2019 • Yu Qin, Yuxing Li, Zhiwen Liu, Chuyang Ye
Then, the interpolated signals are used together with the high-quality tissue microstructure computed from the source dataset to train deep networks that perform tissue microstructure estimation for the target dataset.
1 code implementation • ACL 2019 • Yu Qin, Yi Yang
Prior research has shown that textual information in a firm{'}s financial statement can be used to predict its stock{'}s risk level.
no code implementations • CVPR 2019 • Yu Qin, Jiajun Du, Yonghua Zhang, Hongtao Lu
Most existing attention-based methods on image captioning focus on the current word and visual information in one time step and generate the next word, without considering the visual and linguistic coherence.
no code implementations • 8 Dec 2018 • Jiajun Du, Yu Qin, Hongtao Lu, Yonghua Zhang
Most attention-based image captioning models attend to the image once per word.