Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition

Oct 23, 2020
Qiujia Li, David Qiu, Yu Zhang, Bo Li, Yanzhang He, Philip C. Woodland, Liangliang Cao, Trevor Strohman

* Submitted to ICASSP 2021 

  Access Paper or Ask Questions

Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data

Oct 22, 2020
Thibault Doutre, Wei Han, Min Ma, Zhiyun Lu, Chung-Cheng Chiu, Ruoming Pang, Arun Narayanan, Ananya Misra, Yu Zhang, Liangliang Cao


  Access Paper or Ask Questions

Zero-shot Entity Linking with Efficient Long Range Sequence Modeling

Oct 12, 2020
Zonghai Yao, Liangliang Cao, Huapu Pan

* 6 pages, 6 figures, Findings of EMNLP2020 

  Access Paper or Ask Questions

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions

May 17, 2020
Chung-Cheng Chiu, Arun Narayanan, Wei Han, Rohit Prabhavalkar, Yu Zhang, Navdeep Jaitly, Ruoming Pang, Tara N. Sainath, Patrick Nguyen, Liangliang Cao, Yonghui Wu

* Submitted to Interspeech 2020 

  Access Paper or Ask Questions

Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

Mar 30, 2020
Matheus Gadelha, Aruni RoyChowdhury, Gopal Sharma, Evangelos Kalogerakis, Liangliang Cao, Erik Learned-Miller, Rui Wang, Subhransu Maji

* 18 pages, 5 figures 

  Access Paper or Ask Questions

Speech Sentiment Analysis via Pre-trained Features from End-to-end ASR Models

Nov 21, 2019
Zhiyun Lu, Liangliang Cao, Yu Zhang, Chung-Cheng Chiu, James Fan


  Access Paper or Ask Questions

Product Image Recognition with Guidance Learning and Noisy Supervision

Jul 26, 2019
Qing Li, Xiaojiang Peng, Liangliang Cao, Wenbin Du, Hao Xing, Yu Qiao

* 10 pages 

  Access Paper or Ask Questions

Accurate and Robust Pulmonary Nodule Detection by 3D Feature Pyramid Network with Self-supervised Feature Learning

Jul 25, 2019
Jingya Liu, Liangliang Cao, Oguz Akin, Yingli Tian

* 15 pages, 8 figures, 5 tables, under review by Medical Image Analysis. arXiv admin note: substantial text overlap with arXiv:1906.03467 

  Access Paper or Ask Questions

3DFPN-HS$^2$: 3D Feature Pyramid Network Based High Sensitivity and Specificity Pulmonary Nodule Detection

Jun 11, 2019
Jingya Liu, Liangliang Cao, Oguz Akin, Yingli Tian

* 8 pages, 3 figures. Accepted to MICCAI 2019 

  Access Paper or Ask Questions

Automatic adaptation of object detectors to new domains using self-training

Apr 15, 2019
Aruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin, Huaizu Jiang, Liangliang Cao, Erik Learned-Miller

* Accepted at CVPR 2019 

  Access Paper or Ask Questions

Learning Deterministic Policy with Target for Power Control in Wireless Networks

Feb 21, 2019
Yujiao Lu, Hancheng Lu, Liangliang Cao, Feng Wu, Daren Zhu

* 7 pages, 7 figures, GlobeCom2018 

  Access Paper or Ask Questions

Matrix Factorization on GPUs with Memory Optimization and Approximate Computing

Aug 11, 2018
Wei Tan, Shiyu Chang, Liana Fong, Cheng Li, Zijun Wang, Liangliang Cao


  Access Paper or Ask Questions

Focal Visual-Text Attention for Visual Question Answering

Jun 05, 2018
Junwei Liang, Lu Jiang, Liangliang Cao, Li-Jia Li, Alexander Hauptmann


  Access Paper or Ask Questions

Learning Object Detectors from Scratch with Gated Recurrent Feature Pyramids

Dec 04, 2017
Zhiqiang Shen, Honghui Shi, Rogerio Feris, Liangliang Cao, Shuicheng Yan, Ding Liu, Xinchao Wang, Xiangyang Xue, Thomas S. Huang


  Access Paper or Ask Questions

Lip2AudSpec: Speech reconstruction from silent lip movements video

Oct 26, 2017
Hassan Akbari, Himani Arora, Liangliang Cao, Nima Mesgarani


  Access Paper or Ask Questions

MemexQA: Visual Memex Question Answering

Aug 04, 2017
Lu Jiang, Junwei Liang, Liangliang Cao, Yannis Kalantidis, Sachin Farfade, Alexander Hauptmann

* https://memexqa.cs.cmu.edu/ 

  Access Paper or Ask Questions

Image Based Appraisal of Real Estate Properties

Jul 27, 2017
Quanzeng You, Ran Pang, Liangliang Cao, Jiebo Luo

* 8 pages, 8 figures 

  Access Paper or Ask Questions

Learning from Noisy Labels with Distillation

Apr 07, 2017
Yuncheng Li, Jianchao Yang, Yale Song, Liangliang Cao, Jiebo Luo, Li-Jia Li


  Access Paper or Ask Questions

Detecting Sarcasm in Multimodal Social Platforms

Aug 08, 2016
Rossano Schifanella, Paloma de Juan, Joel Tetreault, Liangliang Cao

* 10 pages, 3 figures, final version published in the Proceedings of ACM Multimedia 2016 

  Access Paper or Ask Questions

Video2GIF: Automatic Generation of Animated GIFs from Video

May 16, 2016
Michael Gygli, Yale Song, Liangliang Cao

* Accepted to CVPR 2016 

  Access Paper or Ask Questions

GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring

Apr 12, 2016
Wenying Ma, Liangliang Cao, Lei Yu, Guoping Long, Yucheng Li

* accepted by ICMR 2016 

  Access Paper or Ask Questions

TGIF: A New Dataset and Benchmark on Animated GIF Description

Apr 12, 2016
Yuncheng Li, Yale Song, Liangliang Cao, Joel Tetreault, Larry Goldberg, Alejandro Jaimes, Jiebo Luo

* CVPR 2016 Camera Ready 

  Access Paper or Ask Questions

Poker-CNN: A Pattern Learning Strategy for Making Draws and Bets in Poker Games

Sep 22, 2015
Nikolai Yakovenko, Liangliang Cao, Colin Raffel, James Fan

* 8 pages 

  Access Paper or Ask Questions

Practice in Synonym Extraction at Large Scale

Jun 01, 2015
Liangliang Cao, Chang Wang

* This paper has been withdrawn by the author since the experimental results are not good enough 

  Access Paper or Ask Questions

Medical Synonym Extraction with Concept Space Models

Jun 01, 2015
Chang Wang, Liangliang Cao, Bowen Zhou

* 7 pages, to appear in IJCAI 2015 

  Access Paper or Ask Questions

Learning Latent Spatio-Temporal Compositional Model for Human Action Recognition

Feb 01, 2015
Xiaodan Liang, Liang Lin, Liangliang Cao

* This manuscript has 10 pages with 7 figures, and a preliminary version was published in ACM MM'13 

  Access Paper or Ask Questions