Search Results for author: Yuan Tian

Found 37 papers, 13 papers with code

AnANet: Modeling Association and Alignment for Cross-modal Correlation Classification

no code implementations2 Sep 2021 Nan Xu, Junyan Wang, Yuan Tian, Ruike Zhang, Wenji Mao

Thus researchers study the definition of cross-modal correlation category and construct various classification systems and predictive models.

Classification

Self-Conditioned Probabilistic Learning of Video Rescaling

no code implementations ICCV 2021 Yuan Tian, Guo Lu, Xiongkuo Min, Zhaohui Che, Guangtao Zhai, Guodong Guo, Zhiyong Gao

After optimization, the downscaled video by our framework preserves more meaningful information, which is beneficial for both the upscaling step and the downstream tasks, e. g., video action recognition task.

Action Recognition Video Compression

EAN: Event Adaptive Network for Enhanced Action Recognition

1 code implementation22 Jul 2021 Yuan Tian, Yichao Yan, Xiongkuo Min, Guo Lu, Guangtao Zhai, Guodong Guo, Zhiyong Gao

In this paper, we propose a unified action recognition framework to investigate the dynamic nature of video content by introducing the following designs.

Action Recognition

What and How long: Prediction of Mobile App Engagement

no code implementations2 Jun 2021 Yuan Tian, Ke Zhou, Dan Pelleg

Based on the analysis, we further investigate a novel mobile app engagement prediction problem -- can we predict simultaneously what app the user will use next and how long he/she will stay on that app?

CryptGPU: Fast Privacy-Preserving Machine Learning on the GPU

no code implementations22 Apr 2021 Sijun Tan, Brian Knott, Yuan Tian, David J. Wu

We then identify a sequence of "GPU-friendly" cryptographic protocols to enable privacy-preserving evaluation of both linear and non-linear operations on the GPU.

Privacy Preserving Deep Learning

Understanding and Mitigating Accuracy Disparity in Regression

1 code implementation24 Feb 2021 Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon, Han Zhao

With the widespread deployment of large-scale prediction systems in high-stakes domains, e. g., face recognition, criminal justice, etc., disparity in prediction accuracy between different demographic subgroups has called for fundamental understanding on the source of such disparity and algorithmic intervention to mitigate it.

Face Recognition

Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks

1 code implementation22 Feb 2021 Tingyu Xia, Yue Wang, Yuan Tian, Yi Chang

We study the problem of incorporating prior knowledge into a deep Transformer-based model, i. e., Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks.

Meta Federated Learning

no code implementations10 Feb 2021 Omid Aramoon, Pin-Yu Chen, Gang Qu, Yuan Tian

Due to its distributed methodology alongside its privacy-preserving features, Federated Learning (FL) is vulnerable to training time adversarial attacks.

Federated Learning

SkillBot: Identifying Risky Content for Children in Alexa Skills

no code implementations5 Feb 2021 Tu Le, Danny Yuxing Huang, Noah Apthorpe, Yuan Tian

Finally, we identify a new threat to users of VPA apps: confounding utterances, or voice commands shared by multiple apps that may cause a user to invoke or interact with a different app than intended.

Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning

no code implementations1 Feb 2021 Syed Zawad, Ahsan Ali, Pin-Yu Chen, Ali Anwar, Yi Zhou, Nathalie Baracaldo, Yuan Tian, Feng Yan

Data heterogeneity has been identified as one of the key features in federated learning but often overlooked in the lens of robustness to adversarial attacks.

Federated Learning

Intent Classification and Slot Filling for Privacy Policies

1 code implementation ACL 2021 Wasi Uddin Ahmad, Jianfeng Chi, Tu Le, Thomas Norton, Yuan Tian, Kai-Wei Chang

We refer to predicting the privacy practice explained in a sentence as intent classification and identifying the text spans sharing specific information as slot filling.

Classification General Classification +2

Battery Model Calibration with Deep Reinforcement Learning

no code implementations7 Dec 2020 Ajaykumar Unagar, Yuan Tian, Manuel Arias-Chao, Olga Fink

In this paper, we implement a Reinforcement Learning-based framework for reliably and efficiently inferring calibration parameters of battery models.

ToHRE: A Top-Down Classification Strategy with Hierarchical Bag Representation for Distantly Supervised Relation Extraction

no code implementations COLING 2020 Erxin Yu, Wenjuan Han, Yuan Tian, Yi Chang

Distantly Supervised Relation Extraction (DSRE) has proven to be effective to find relational facts from texts, but it still suffers from two main problems: the wrong labeling problem and the long-tail problem.

Classification Relation Extraction

Reinforcement Learning Control of Constrained Dynamic Systems with Uniformly Ultimate Boundedness Stability Guarantee

no code implementations13 Nov 2020 Minghao Han, Yuan Tian, Lixian Zhang, Jun Wang, Wei Pan

In comparison with the existing RL algorithms, the proposed method can achieve superior performance in terms of maintaining safety.

Continuous Control

PolicyQA: A Reading Comprehension Dataset for Privacy Policies

1 code implementation Findings of the Association for Computational Linguistics 2020 Wasi Uddin Ahmad, Jianfeng Chi, Yuan Tian, Kai-Wei Chang

Prior studies in this domain frame the QA task as retrieving the most relevant text segment or a list of sentences from the policy document given a question.

Question Answering Reading Comprehension

Dual-path CNN with Max Gated block for Text-Based Person Re-identification

no code implementations20 Sep 2020 Tinghuai Ma, Mingming Yang, Huan Rong, Yurong Qian, Yuan Tian, NajlaAl-Nabhan

With that in mind, a novel Dual-path CNN with Max Gated block (DCMG) is proposed to extract discriminative word embeddings and make visual-textual association concern more on remarkable features of both modalities.

Language Modelling Person Re-Identification +1

Object Detection in the Context of Mobile Augmented Reality

no code implementations15 Aug 2020 Xiang Li, Yuan Tian, Fuyao Zhang, Shuxue Quan, Yi Xu

Ordinary object detection approaches process information from the images only, and they are oblivious to the camera pose with regard to the environment and the scale of the environment.

Real-Time Object Detection

Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos

no code implementations22 Jul 2020 Yuan Tian, Guangtao Zhai, Zhiyong Gao

More specifically, an \textit{action perceptron synthesizer} is proposed to generate the kernels from a bag of fixed-size kernels that are interacted by dense routing paths.

Action Recognition Video Understanding

Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search

1 code implementation ECCV 2020 Yuan Tian, Qin Wang, Zhiwu Huang, Wen Li, Dengxin Dai, Minghao Yang, Jun Wang, Olga Fink

In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search.

Image Generation Neural Architecture Search

Model-Targeted Poisoning Attacks with Provable Convergence

1 code implementation30 Jun 2020 Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans, Yuan Tian

Our attack is the first model-targeted poisoning attack that provides provable convergence for convex models, and in our experiments, it either exceeds or matches state-of-the-art attacks in terms of attack success rate and distance to the target model.

Real-Time Model Calibration with Deep Reinforcement Learning

no code implementations7 Jun 2020 Yuan Tian, Manuel Arias Chao, Chetan Kulkarni, Kai Goebel, Olga Fink

The dynamic, real-time, and accurate inference of model parameters from empirical data is of great importance in many scientific and engineering disciplines that use computational models (such as a digital twin) for the analysis and prediction of complex physical processes.

GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks

2 code implementations17 Jan 2020 Qiang Huang, Makoto Yamada, Yuan Tian, Dinesh Singh, Dawei Yin, Yi Chang

In this paper, we propose GraphLIME, a local interpretable model explanation for graphs using the Hilbert-Schmidt Independence Criterion (HSIC) Lasso, which is a nonlinear feature selection method.

Feature Selection

$H_\infty$ Model-free Reinforcement Learning with Robust Stability Guarantee

1 code implementation7 Nov 2019 Minghao Han, Yuan Tian, Lixian Zhang, Jun Wang, Wei Pan

In this paper, we introduce and extend the idea of robust stability and $H_\infty$ control to design policies with both stability and robustness guarantee.

Autonomous Driving

Convex Reconstruction of Structured Matrix Signals from Linear Measurements (I): Theoretical Results

no code implementations19 Oct 2019 Yuan Tian

The first part is about conditions for stability and robustness in signal reconstruction via solving the convex programming from noise-free or noisy measurements. We establish uniform sufficient conditions which are very close to necessary conditions and non-uniform conditions are also discussed.

Compressive Sensing

Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries

1 code implementation19 Aug 2019 Fnu Suya, Jianfeng Chi, David Evans, Yuan Tian

In a black-box setting, the adversary only has API access to the target model and each query is expensive.

Cryptography and Security

PatchNet: A Tool for Deep Patch Classification

1 code implementation16 Feb 2019 Thong Hoang, Julia Lawall, Richard J. Oentaryo, Yuan Tian, David Lo

This work proposes PatchNet, an automated tool based on hierarchical deep learning for classifying patches by extracting features from commit messages and code changes.

Classification General Classification +1

Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase

no code implementations7 Dec 2018 Jianfeng Chi, Emmanuel Owusu, Xuwang Yin, Tong Yu, William Chan, Patrick Tague, Yuan Tian

We present a practical method for protecting data during the inference phase of deep learning based on bipartite topology threat modeling and an interactive adversarial deep network construction.

Face Identification General Classification

Understanding and Mitigating the Security Risks of Voice-Controlled Third-Party Skills on Amazon Alexa and Google Home

no code implementations3 May 2018 Nan Zhang, Xianghang Mi, Xuan Feng, Xiao-Feng Wang, Yuan Tian, Feng Qian

The significance of our findings have already been acknowledged by Amazon and Google, and further evidenced by the risky skills discovered on Alexa and Google markets by the new detection systems we built.

Cryptography and Security

Query-limited Black-box Attacks to Classifiers

1 code implementation23 Dec 2017 Fnu Suya, Yuan Tian, David Evans, Paolo Papotti

Specifically, we consider the problem of attacking machine learning classifiers subject to a budget of feature modification cost while minimizing the number of queries, where each query returns only a class and confidence score.

WebAPIRec: Recommending Web APIs to Software Projects via Personalized Ranking

no code implementations1 May 2017 Ferdian Thung, Richard J. Oentaryo, David Lo, Yuan Tian

In this light, we propose a new, automated approach called WebAPIRec that takes as input a project profile and outputs a ranked list of {web} APIs that can be used to implement the project.

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