no code implementations • 22 Nov 2022 • Dongli Wu, Bufan Zhang, Xiao Lin
Thus, the model will deliver the reliable prices to the exotic options in the daily trading activities.
no code implementations • 6 May 2022 • Xiao Lin, Ce Liu
We propose a new notion of credibility for Bayesian persuasion problems.
no code implementations • 11 Jan 2022 • Zhaohui Wang, Xiao Lin, Abhinav Mishra, Ram Sriharsha
In this paper, we are interested in changepoint detection algorithms which operate in an online setting in the sense that both its storage requirements and worst-case computational complexity per observation are independent of the number of previous observations.
no code implementations • ICLR 2022 • Xiaoling Hu, Xiao Lin, Michael Cogswell, Yi Yao, Susmit Jha, Chao Chen
Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks.
no code implementations • 13 Oct 2021 • Kamran Alipour, Arijit Ray, Xiao Lin, Michael Cogswell, Jurgen P. Schulze, Yi Yao, Giedrius T. Burachas
In the domain of Visual Question Answering (VQA), studies have shown improvement in users' mental model of the VQA system when they are exposed to examples of how these systems answer certain Image-Question (IQ) pairs.
no code implementations • 31 May 2021 • Henrique de Oliveira, Yuhta Ishii, Xiao Lin
If information about this correlation is lacking, an agent may find it desirable to make a decision that is robust to possible correlations.
1 code implementation • 1 Apr 2021 • Xiao Lin, Meng Ye, Yunye Gong, Giedrius Buracas, Nikoletta Basiou, Ajay Divakaran, Yi Yao
Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples.
no code implementations • ICCV 2021 • Yunye Gong, Xiao Lin, Yi Yao, Thomas G. Dietterich, Ajay Divakaran, Melinda Gervasio
Existing calibration algorithms address the problem of covariate shift via unsupervised domain adaptation.
no code implementations • 26 Mar 2021 • Arijit Ray, Michael Cogswell, Xiao Lin, Kamran Alipour, Ajay Divakaran, Yi Yao, Giedrius Burachas
Hence, we propose Error Maps that clarify the error by highlighting image regions where the model is prone to err.
no code implementations • 17 Dec 2020 • Hao Hu, Xiao Lin, Liang Jie Wong, Qianru Yang, Baile Zhang, Yu Luo
Recent advances in engineered material technologies (e. g., photonic crystals, metamaterials, plasmonics, etc) provide valuable tools to control Cherenkov radiation.
no code implementations • 19 Nov 2020 • Meng Ye, Xiao Lin, Giedrius Burachas, Ajay Divakaran, Yi Yao
Few-Shot Learning (FSL) aims to improve a model's generalization capability in low data regimes.
no code implementations • 15 Oct 2020 • S. Nageeb Ali, Nima Haghpanah, Xiao Lin, Ron Siegel
The seller of an asset has the option to buy hard information about the value of the asset from an intermediary.
no code implementations • 2 Jul 2020 • Kamran Alipour, Arijit Ray, Xiao Lin, Jurgen P. Schulze, Yi Yao, Giedrius T. Burachas
In this paper, we evaluate the impact of explanations on the user's mental model of AI agent competency within the task of visual question answering (VQA).
1 code implementation • 28 Jun 2020 • Wenhui Yu, Xiao Lin, Junfeng Ge, Wenwu Ou, Zheng Qin
This causes two difficulties in designing effective algorithms: first, the majority of users only have a few interactions with the system and there is no enough data for learning; second, there are no negative samples in the implicit feedbacks and it is a common practice to perform negative sampling to generate negative samples.
no code implementations • 25 Sep 2019 • Xiao Lin, Indranil Sur, Samuel A. Nastase, Uri Hasson, Ajay Divakaran, Mohamed R. Amer
Measuring Mutual Information (MI) between high-dimensional, continuous, random variables from observed samples has wide theoretical and practical applications.
1 code implementation • 21 Jul 2019 • Boris Knyazev, Xiao Lin, Mohamed R. Amer, Graham W. Taylor
Graph Convolutional Networks (GCNs) are a class of general models that can learn from graph structured data.
no code implementations • 8 May 2019 • Xiao Lin, Indranil Sur, Samuel A. Nastase, Ajay Divakaran, Uri Hasson, Mohamed R. Amer
We demonstrate the effectiveness of our estimators on synthetic benchmarks and a real world fMRI data, with application of inter-subject correlation analysis.
1 code implementation • IJCNLP 2019 • Julia Kruk, Jonah Lubin, Karan Sikka, Xiao Lin, Dan Jurafsky, Ajay Divakaran
Computing author intent from multimodal data like Instagram posts requires modeling a complex relationship between text and image.
no code implementations • 17 Apr 2019 • Xiao Lin, Josep R. Casas, Montse Pardàs
We propose a novel 3D segmentation method for RBGD stream data to deal with 3D object segmentation task in a generic scenario with frequent object interactions.
1 code implementation • 15 Apr 2019 • Changhua Pei, Yi Zhang, Yongfeng Zhang, Fei Sun, Xiao Lin, Hanxiao Sun, Jian Wu, Peng Jiang, Wenwu Ou
Ranking is a core task in recommender systems, which aims at providing an ordered list of items to users.
7 code implementations • 14 Apr 2019 • Fei Sun, Jun Liu, Jian Wu, Changhua Pei, Xiao Lin, Wenwu Ou, Peng Jiang
To address this problem, we train the bidirectional model using the Cloze task, predicting the masked items in the sequence by jointly conditioning on their left and right context.
no code implementations • 3 Feb 2019 • Changhua Pei, Xinru Yang, Qing Cui, Xiao Lin, Fei Sun, Peng Jiang, Wenwu Ou, Yongfeng Zhang
Existing recommendation algorithms mostly focus on optimizing traditional recommendation measures, such as the accuracy of rating prediction in terms of RMSE or the quality of top-$k$ recommendation lists in terms of precision, recall, MAP, etc.
1 code implementation • 23 Nov 2018 • Boris Knyazev, Xiao Lin, Mohamed R. Amer, Graham W. Taylor
Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data.
Ranked #10 on Graph Classification on NCI109
no code implementations • 27 Apr 2018 • Xiao Lin, Mohamed R. Amer
We present a novel generative model for human motion modeling using Generative Adversarial Networks (GANs).
no code implementations • 5 Feb 2018 • Wenpeng Zhang, Xiao Lin, Peilin Zhao
To address this subsequent challenge, we follow the general projection-free algorithmic framework of Online Conditional Gradient and propose an Online Compact Convex Factorization Machine (OCCFM) algorithm that eschews the projection operation with efficient linear optimization steps.
no code implementations • 23 Dec 2017 • Chao Chen, Xiao Lin, Gabriel Terejanu
In this study, we propose an approximate estimation of the weights uncertainty using Ensemble Kalman Filter, which is easily scalable to a large number of weights.
1 code implementation • 6 Nov 2017 • Xiao Lin, Devi Parikh
We present an empirical study of active learning for Visual Question Answering, where a deep VQA model selects informative question-image pairs from a pool and queries an oracle for answers to maximally improve its performance under a limited query budget.
no code implementations • 8 Aug 2017 • Xiao Lin, Gabriel Terejanu
Real-time nonlinear Bayesian filtering algorithms are overwhelmed by data volume, velocity and increasing complexity of computational models.
no code implementations • 1 Mar 2017 • Xiao Lin, Asif Chowdhury, Xiaofan Wang, Gabriel Terejanu
Then, sensors are placed where highest mutual information (lower bound) is achieved and QoI is inferred via Bayes rule given sensor measurements.
no code implementations • 4 Jun 2016 • Xiao Lin
The aim of this paper is to present a dual-term structure model of interest rate derivatives in order to solve the two hardest problems in financial modeling: the exact volatility calibration of the entire swaption matrix, and the calculation of bucket vegas for structured products.
no code implementations • 4 May 2016 • Xiao Lin, Devi Parikh
This allows the model to interpret images and captions from a wide variety of perspectives.
no code implementations • ICCV 2015 • Ramakrishna Vedantam, Xiao Lin, Tanmay Batra, C. Lawrence Zitnick, Devi Parikh
We show that the commonsense knowledge we learn is complementary to what can be learnt from sources of text.
no code implementations • CVPR 2015 • Xiao Lin, Devi Parikh
But much of common sense knowledge is unwritten - partly because it tends not to be interesting enough to talk about, and partly because some common sense is unnatural to articulate in text.
no code implementations • 14 Dec 2014 • Michael Cogswell, Xiao Lin, Senthil Purushwalkam, Dhruv Batra
We present a two-module approach to semantic segmentation that incorporates Convolutional Networks (CNNs) and Graphical Models.