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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Hexiang Hu

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation


Jul 05, 2021
Tai-Yu Pan, Cheng Zhang, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao


  Access Paper or Ask Questions

A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection


Feb 17, 2021
Cheng Zhang, Tai-Yu Pan, Yandong Li, Hexiang Hu, Dong Xuan, Soravit Changpinyo, Boqing Gong, Wei-Lun Chao


  Access Paper or Ask Questions

A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus


Nov 24, 2020
Bowen Zhang, Hexiang Hu, Joonseok Lee, Ming Zhao, Sheide Chammas, Vihan Jain, Eugene Ie, Fei Sha


  Access Paper or Ask Questions

Learning the Best Pooling Strategy for Visual Semantic Embedding


Nov 09, 2020
Jiacheng Chen, Hexiang Hu, Hao Wu, Yuning Jiang, Changhu Wang


  Access Paper or Ask Questions

Learning to Represent Image and Text with Denotation Graph


Oct 06, 2020
Bowen Zhang, Hexiang Hu, Vihan Jain, Eugene Ie, Fei Sha

* to appear at EMNLP 2020 

  Access Paper or Ask Questions

Drinking from a Firehose: Continual Learning with Web-scale Natural Language


Jul 18, 2020
Hexiang Hu, Ozan Sener, Fei Sha, Vladlen Koltun

* Source Code: https://github.com/firehose-dataset/congrad 

  Access Paper or Ask Questions

BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps


Jun 14, 2020
Wang Zhu, Hexiang Hu, Jiacheng Chen, Zhiwei Deng, Vihan Jain, Eugene Ie, Fei Sha

* Accepted by ACL 2020 

  Access Paper or Ask Questions

Visual Storytelling via Predicting Anchor Word Embeddings in the Stories


Jan 13, 2020
Bowen Zhang, Hexiang Hu, Fei Sha

* Accepted by ICCV19 CLVL workshop: 3rd Workshop on Closing the Loop Between Vision and Language 

  Access Paper or Ask Questions

Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation


Oct 30, 2019
Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim


  Access Paper or Ask Questions

Learning Classifier Synthesis for Generalized Few-Shot Learning


Jun 07, 2019
Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, Fei Sha


  Access Paper or Ask Questions

Synthesized Policies for Transfer and Adaptation across Tasks and Environments


Apr 05, 2019
Hexiang Hu, Liyu Chen, Boqing Gong, Fei Sha

* presented at NeurIPS 2019 as a Spotlight 

  Access Paper or Ask Questions

Binary Image Selection (BISON): Interpretable Evaluation of Visual Grounding


Jan 19, 2019
Hexiang Hu, Ishan Misra, Laurens van der Maaten


  Access Paper or Ask Questions

Toward Multimodal Model-Agnostic Meta-Learning


Dec 18, 2018
Risto Vuorio, Shao-Hua Sun, Hexiang Hu, Joseph J. Lim


  Access Paper or Ask Questions

Learning Embedding Adaptation for Few-Shot Learning


Dec 16, 2018
Han-Jia Ye, Hexiang Hu, De-Chuan Zhan, Fei Sha


  Access Paper or Ask Questions

Engaging Image Captioning Via Personality


Oct 25, 2018
Kurt Shuster, Samuel Humeau, Hexiang Hu, Antoine Bordes, Jason Weston


  Access Paper or Ask Questions

Cross-Modal and Hierarchical Modeling of Video and Text


Oct 16, 2018
Bowen Zhang, Hexiang Hu, Fei Sha

* Accepted by ECCV 2018 

  Access Paper or Ask Questions

Multi-Task Learning for Sequence Tagging: An Empirical Study


Aug 13, 2018
Soravit Changpinyo, Hexiang Hu, Fei Sha

* In Proceedings of the 27th International Conference on Computational Linguistics (COLING 2018) 

  Access Paper or Ask Questions

Cross-Dataset Adaptation for Visual Question Answering


Jun 10, 2018
Wei-Lun Chao, Hexiang Hu, Fei Sha

* Accepted at CVPR 2018 

  Access Paper or Ask Questions

Learning Answer Embeddings for Visual Question Answering


Jun 10, 2018
Hexiang Hu, Wei-Lun Chao, Fei Sha

* Accepted at CVPR 2018 

  Access Paper or Ask Questions

Being Negative but Constructively: Lessons Learnt from Creating Better Visual Question Answering Datasets


Jun 10, 2018
Wei-Lun Chao, Hexiang Hu, Fei Sha

* Accepted for Oral Presentation at NAACL-HLT 2018 

  Access Paper or Ask Questions

Compressed Video Action Recognition


Mar 29, 2018
Chao-Yuan Wu, Manzil Zaheer, Hexiang Hu, R. Manmatha, Alexander J. Smola, Philipp Krähenbühl

* CVPR 2018 (Selected for spotlight presentation) 

  Access Paper or Ask Questions

Structured Label Inference for Visual Understanding


Feb 18, 2018
Nelson Nauata, Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori


  Access Paper or Ask Questions

FastMask: Segment Multi-scale Object Candidates in One Shot


Apr 11, 2017
Hexiang Hu, Shiyi Lan, Yuning Jiang, Zhimin Cao, Fei Sha

* Accepted as CVPR 2017 

  Access Paper or Ask Questions

LabelBank: Revisiting Global Perspectives for Semantic Segmentation


Mar 29, 2017
Hexiang Hu, Zhiwei Deng, Guang-Tong Zhou, Fei Sha, Greg Mori

* Pre-prints 

  Access Paper or Ask Questions

Recalling Holistic Information for Semantic Segmentation


Nov 24, 2016
Hexiang Hu, Zhiwei Deng, Guang-tong Zhou, Fei Sha, Greg Mori


  Access Paper or Ask Questions

Learning Structured Inference Neural Networks with Label Relations


Oct 24, 2016
Hexiang Hu, Guang-Tong Zhou, Zhiwei Deng, Zicheng Liao, Greg Mori

* Conference on Computer Vision and Pattern Recognition(CVPR) 2016 

  Access Paper or Ask Questions

Structure Inference Machines: Recurrent Neural Networks for Analyzing Relations in Group Activity Recognition


Apr 12, 2016
Zhiwei Deng, Arash Vahdat, Hexiang Hu, Greg Mori

* CVPR 2016 

  Access Paper or Ask Questions