no code implementations • ECCV 2020 • Yuan Tian, Zhaohui Che, Wenbo Bao, Guangtao Zhai, Zhiyong Gao
Motion representation is key to many computer vision problems but has never been well studied in the literature.
no code implementations • 20 Dec 2022 • Jianfeng Chi, Wasi Uddin Ahmad, Yuan Tian, Kai-Wei Chang
To this end, we introduce the Privacy Policy Language Understanding Evaluation (PLUE) benchmark, a multi-task benchmark for evaluating the privacy policy language understanding across various tasks.
1 code implementation • 11 Dec 2022 • Tingyu Xia, Yue Wang, Yuan Tian, Yi Chang
Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data.
1 code implementation • 7 Aug 2022 • Tongyi Luo, Jia Xiao, Chuncao Zhang, Siheng Chen, Yuan Tian, Guangjun Yu, Kang Dang, Xiaowei Ding
Although general movements assessment(GMA) has shown promising results in early CP detection, it is laborious.
1 code implementation • 23 May 2022 • Jianfeng Chi, William Shand, Yaodong Yu, Kai-Wei Chang, Han Zhao, Yuan Tian
Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data.
no code implementations • 5 May 2022 • Pan Ji, Yuan Tian, Qingan Yan, Yuxin Ma, Yi Xu
The CNN depth effectively bootstraps the back-end optimization of SLAM and meanwhile the CNN uncertainty adaptively weighs the contribution of each feature point to the back-end optimization.
no code implementations • 5 May 2022 • Qingan Yan, Pan Ji, Nitin Bansal, Yuxin Ma, Yuan Tian, Yi Xu
In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner.
no code implementations • 19 Apr 2022 • Md Rizwan Parvez, Jianfeng Chi, Wasi Uddin Ahmad, Yuan Tian, Kai-Wei Chang
Prior studies in privacy policies frame the question answering (QA) tasks as identifying the most relevant text segment or a list of sentences from the policy document for a user query.
no code implementations • 12 Apr 2022 • Yuan Tian, Klaus-Rudolf Kladny, Qin Wang, Zhiwu Huang, Olga Fink
In this paper, we propose to exploit the fact that the agents seek to improve their expected cumulative reward and introduce a novel \textit{Time Dynamical Opponent Model} (TDOM) to encode the knowledge that the opponent policies tend to improve over time.
no code implementations • 6 Feb 2022 • Yuan Tian, Guo Lu, Yichao Yan, Guangtao Zhai, Li Chen, Zhiyong Gao
However, in real-world scenarios, the videos are first compressed before the transportation and then decompressed for understanding.
no code implementations • 20 Jan 2022 • Yuan Tian, Minghao Han, Chetan Kulkarni, Olga Fink
Moreover, we demonstrate the applicability of the proposed algorithm on a prescriptive operation case, where we propose the Dirichlet power allocation policy and evaluate the performance on a case study of a set of multiple lithium-ion (Li-I) battery systems.
1 code implementation • 19 Nov 2021 • Jianfeng Chi, Jian Shen, Xinyi Dai, Weinan Zhang, Yuan Tian, Han Zhao
We first provide a decomposition theorem for return disparity, which decomposes the return disparity of any two MDPs sharing the same state and action spaces into the distance between group-wise reward functions, the discrepancy of group policies, and the discrepancy between state visitation distributions induced by the group policies.
no code implementations • 8 Nov 2021 • Tamjid Al Rahat, Tu Le, Yuan Tian
Since GDPR came into force in May 2018, companies have worked on their data practices to comply with this privacy law.
no code implementations • 2 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.
1 code implementation • 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.
1 code implementation • 22 Jul 2021 • Yuan Tian, Yichao Yan, 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.
Ranked #8 on
Action Recognition
on Something-Something V1
no code implementations • 2 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?
no code implementations • 17 May 2021 • Andrey Ignatov, Grigory Malivenko, Radu Timofte, Sheng Chen, Xin Xia, Zhaoyan Liu, Yuwei Zhang, Feng Zhu, Jiashi Li, Xuefeng Xiao, Yuan Tian, Xinglong Wu, Christos Kyrkou, Yixin Chen, Zexin Zhang, Yunbo Peng, Yue Lin, Saikat Dutta, Sourya Dipta Das, Nisarg A. Shah, Himanshu Kumar, Chao Ge, Pei-Lin Wu, Jin-Hua Du, Andrew Batutin, Juan Pablo Federico, Konrad Lyda, Levon Khojoyan, Abhishek Thanki, Sayak Paul, Shahid Siddiqui
To address this problem, we introduce the first Mobile AI challenge, where the target is to develop quantized deep learning-based camera scene classification solutions that can demonstrate a real-time performance on smartphones and IoT platforms.
1 code implementation • 22 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.
1 code implementation • 24 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.
1 code implementation • 22 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.
no code implementations • 10 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.
no code implementations • 5 Feb 2021 • Tu Le, Danny Yuxing Huang, Noah Apthorpe, Yuan Tian
Finally, we identify a novel risk in the VPA ecosystem: confounding utterances, or voice commands shared by multiple apps that may cause a user to interact with a different app than intended.
no code implementations • 1 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.
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.
no code implementations • 7 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.
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.
no code implementations • 13 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.
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.
1 code implementation • 20 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.
no code implementations • 15 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.
no code implementations • 22 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.
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.
Ranked #12 on
Image Generation
on STL-10
1 code implementation • 30 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.
no code implementations • 7 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.
2 code implementations • 17 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.
1 code implementation • 7 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.
no code implementations • 19 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.
no code implementations • 25 Sep 2019 • Minghao Han, Yuan Tian, Lixian Zhang, Jun Wang, Wei Pan
Reinforcement learning (RL) offers a principled way to achieve the optimal cumulative performance index in discrete-time nonlinear stochastic systems, which are modeled as Markov decision processes.
no code implementations • 25 Sep 2019 • Han Zhao, Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon
With the prevalence of machine learning services, crowdsourced data containing sensitive information poses substantial privacy challenges.
no code implementations • 25 Sep 2019 • Yuan Tian, Minghao Han, Lixian Zhang, Wulong Liu, Jun Wang, Wei Pan
In this paper, we combine variational learning and constrained reinforcement learning to simultaneously learn a Conditional Representation Model (CRM) to encode the states into safe and unsafe distributions respectively as well as to learn the corresponding safe policy.
5 code implementations • ACL 2020 • Zhepei Wei, Jianlin Su, Yue Wang, Yuan Tian, Yi Chang
Extracting relational triples from unstructured text is crucial for large-scale knowledge graph construction.
Ranked #6 on
Relation Extraction
on NYT11-HRL
no code implementations • 23 Aug 2019 • Zhepei Wei, Yantao Jia, Yuan Tian, Mohammad Javad Hosseini, Sujian Li, Mark Steedman, Yi Chang
In this work, we first introduce the hierarchical dependency and horizontal commonality between the two levels, and then propose an entity-enhanced dual tagging framework that enables the triple extraction (TE) task to utilize such interactions with self-learned entity features through an auxiliary entity extraction (EE) task, without breaking the joint decoding of relational triples.
1 code implementation • 19 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
no code implementations • NeurIPS 2020 • Han Zhao, Jianfeng Chi, Yuan Tian, Geoffrey J. Gordon
Meanwhile, it is clear that in general there is a tension between minimizing information leakage and maximizing task accuracy.
1 code implementation • 16 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.
no code implementations • 7 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.
no code implementations • 3 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
1 code implementation • 23 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.
no code implementations • 1 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.
no code implementations • 28 Mar 2017 • Nan Zhang, Soteris Demetriou, Xianghang Mi, Wenrui Diao, Kan Yuan, Peiyuan Zong, Feng Qian, Xiao-Feng Wang, Kai Chen, Yuan Tian, Carl A. Gunter, Kehuan Zhang, Patrick Tague, Yue-Hsun Lin
We systemize this process, by proposing a taxonomy for the IoT ecosystem and organizing IoT security into five problem areas.
Cryptography and Security
no code implementations • CVPR 2015 • Bo Xin, Yuan Tian, Yizhou Wang, Wen Gao
Background Subtraction (BS) is one of the key steps in video analysis.