Search Results for author: Xiao Lin

Found 45 papers, 9 papers with code

Human Body Model based ID using Shape and Pose Parameters

no code implementations6 Dec 2023 Aravind Sundaresan, Brian Burns, Indranil Sur, Yi Yao, Xiao Lin, Sujeong Kim

We show that when our HMID network is trained using additional shape and pose losses, it shows a significant improvement in biometric identification performance when compared to an identical model that does not use such losses.

Human Mesh Recovery

TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer

no code implementations25 Oct 2023 Xiao Lin, Deming Wang, Guangliang Zhou, Chengju Liu, Qijun Chen

To improve robustness to occlusion, we adopt Transformer to perform the exchange of global information, making each local feature contains global information.

6D Pose Estimation using RGB Object

Confidence Calibration for Systems with Cascaded Predictive Modules

no code implementations21 Sep 2023 Yunye Gong, Yi Yao, Xiao Lin, Ajay Divakaran, Melinda Gervasio

Existing conformal prediction algorithms estimate prediction intervals at target confidence levels to characterize the performance of a regression model on new test samples.

Conformal Prediction Prediction Intervals +1

SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments

no code implementations8 Sep 2023 Abhinav Rajvanshi, Karan Sikka, Xiao Lin, Bhoram Lee, Han-Pang Chiu, Alvaro Velasquez

We present SayNav, a new approach that leverages human knowledge from Large Language Models (LLMs) for efficient generalization to complex navigation tasks in unknown large-scale environments.

Common Sense Reasoning Navigate

Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning

1 code implementation1 Sep 2023 Minghao Zhu, Xiao Lin, Ronghao Dang, Chengju Liu, Qijun Chen

As the most essential property in a video, motion information is critical to a robust and generalized video representation.

Contrastive Learning Representation Learning

Discrete Conditional Diffusion for Reranking in Recommendation

no code implementations14 Aug 2023 Xiao Lin, Xiaokai Chen, Chenyang Wang, Hantao Shu, Linfeng Song, Biao Li, Peng Jiang

To overcome these challenges, we propose a novel Discrete Conditional Diffusion Reranking (DCDR) framework for recommendation.

Recommendation Systems

BeMap: Balanced Message Passing for Fair Graph Neural Network

no code implementations7 Jun 2023 Xiao Lin, Jian Kang, Weilin Cong, Hanghang Tong

Graph Neural Network (GNN) has shown strong empirical performance in many downstream tasks by iteratively aggregating information from the local neighborhood of each node, i. e., message passing.

Fairness Node Classification

Efficient and Accurate Calibration to FX Market Skew with Fully Parameterized Local Volatility Model

no code implementations22 Nov 2022 Dongli Wu, Bufan Zhang, Xiao Lin

When trading American and Asian options in the FX derivatives market, banks must calculate prices using a complex mathematical model.

Management

Credible Persuasion

no code implementations6 May 2022 Xiao Lin, Ce Liu

We propose a new notion of credibility for Bayesian persuasion problems.

Online Changepoint Detection on a Budget

no code implementations11 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.

Trigger Hunting with a Topological Prior for Trojan Detection

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.

Improving Users' Mental Model with Attention-directed Counterfactual Edits

no code implementations13 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.

counterfactual Question Answering +2

Robust Merging of Information

no code implementations31 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.

Modular Adaptation for Cross-Domain Few-Shot Learning

1 code implementation1 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.

cross-domain few-shot learning Representation Learning

Surface Dyakonov-Cherenkov Radiation

no code implementations17 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.

Optics

How to Sell Hard Information

no code implementations15 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.

Test

The Impact of Explanations on AI Competency Prediction in VQA

no code implementations2 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).

Language Modelling Question Answering +1

Semi-supervised Collaborative Filtering by Text-enhanced Domain Adaptation

1 code implementation28 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.

Collaborative Filtering Domain Adaptation +1

A Data-Efficient Mutual Information Neural Estimator for Statistical Dependency Testing

no code implementations25 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.

Meta-Learning

Image Classification with Hierarchical Multigraph Networks

1 code implementation21 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.

Classification General Classification +3

Data-Efficient Mutual Information Neural Estimator

no code implementations8 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.

Meta-Learning

Integrating Text and Image: Determining Multimodal Document Intent in Instagram Posts

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.

Intent Detection

Graph based Dynamic Segmentation of Generic Objects in 3D

no code implementations17 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.

Object Segmentation +1

Personalized Re-ranking for Recommendation

1 code implementation15 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.

Recommendation Systems Re-Ranking

BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer

7 code implementations14 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.

Sequential Recommendation

Value-aware Recommendation based on Reinforced Profit Maximization in E-commerce Systems

no code implementations3 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.

Recommendation Systems reinforcement-learning +1

Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules

1 code implementation23 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.

General Classification Graph Classification +1

Human Motion Modeling using DVGANs

no code implementations27 Apr 2018 Xiao Lin, Mohamed R. Amer

We present a novel generative model for human motion modeling using Generative Adversarial Networks (GANs).

Translation

Online Compact Convexified Factorization Machine

no code implementations5 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.

Binary Classification Feature Engineering

An Approximate Bayesian Long Short-Term Memory Algorithm for Outlier Detection

no code implementations23 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.

Outlier Detection

Active Learning for Visual Question Answering: An Empirical Study

1 code implementation6 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.

Active Learning Visual Question Answering

EnLLVM: Ensemble Based Nonlinear Bayesian Filtering Using Linear Latent Variable Models

no code implementations8 Aug 2017 Xiao Lin, Gabriel Terejanu

Real-time nonlinear Bayesian filtering algorithms are overwhelmed by data volume, velocity and increasing complexity of computational models.

Approximate Computational Approaches for Bayesian Sensor Placement in High Dimensions

no code implementations1 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.

Bayesian Optimization Vocal Bursts Intensity Prediction

The Zero-Coupon Rate Model for Derivatives Pricing

no code implementations4 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.

Leveraging Visual Question Answering for Image-Caption Ranking

no code implementations4 May 2016 Xiao Lin, Devi Parikh

This allows the model to interpret images and captions from a wide variety of perspectives.

Image Retrieval Question Answering +2

Don't Just Listen, Use Your Imagination: Leveraging Visual Common Sense for Non-Visual Tasks

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.

Common Sense Reasoning

Combining the Best of Graphical Models and ConvNets for Semantic Segmentation

no code implementations14 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.

Segmentation Semantic Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.