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 Yukun Zhu

Federated Multi-Target Domain Adaptation


Aug 17, 2021
Chun-Han Yao, Boqing Gong, Yin Cui, Hang Qi, Yukun Zhu, Ming-Hsuan Yang


  Access Paper or Ask Questions

DeepLab2: A TensorFlow Library for Deep Labeling


Jun 17, 2021
Mark Weber, Huiyu Wang, Siyuan Qiao, Jun Xie, Maxwell D. Collins, Yukun Zhu, Liangzhe Yuan, Dahun Kim, Qihang Yu, Daniel Cremers, Laura Leal-Taixe, Alan L. Yuille, Florian Schroff, Hartwig Adam, Liang-Chieh Chen

* 4-page technical report. The first three authors contributed equally to this work 

  Access Paper or Ask Questions

BasisNet: Two-stage Model Synthesis for Efficient Inference


May 07, 2021
Mingda Zhang, Chun-Te Chu, Andrey Zhmoginov, Andrew Howard, Brendan Jou, Yukun Zhu, Li Zhang, Rebecca Hwa, Adriana Kovashka

* To appear, 4th Workshop on Efficient Deep Learning for Computer Vision (ECV2021), CVPR2021 Workshop 

  Access Paper or Ask Questions

Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data


Apr 27, 2021
Xuhui Jia, Kai Han, Yukun Zhu, Bradley Green


  Access Paper or Ask Questions

STEP: Segmenting and Tracking Every Pixel


Feb 23, 2021
Mark Weber, Jun Xie, Maxwell Collins, Yukun Zhu, Paul Voigtlaender, Hartwig Adam, Bradley Green, Andreas Geiger, Bastian Leibe, Daniel Cremers, Aljosa Osep, Laura Leal-Taixe, Liang-Chieh Chen

* Datasets, metric, and baselines will be made publicly available soon 

  Access Paper or Ask Questions

ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation


Dec 09, 2020
Siyuan Qiao, Yukun Zhu, Hartwig Adam, Alan Yuille, Liang-Chieh Chen

* Video: https://youtu.be/XR4HFiwwao0 GitHub: https://github.com/joe-siyuan-qiao/ViP-DeepLab 

  Access Paper or Ask Questions

MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers


Dec 01, 2020
Huiyu Wang, Yukun Zhu, Hartwig Adam, Alan Yuille, Liang-Chieh Chen


  Access Paper or Ask Questions

Ranking Neural Checkpoints


Nov 23, 2020
Yandong Li, Xuhui Jia, Ruoxin Sang, Yukun Zhu, Bradley Green, Liqiang Wang, Boqing Gong


  Access Paper or Ask Questions

Boosting Image-based Mutual Gaze Detection using Pseudo 3D Gaze


Oct 15, 2020
Bardia Doosti, Ching-Hui Chen, Raviteja Vemulapalli, Xuhui Jia, Yukun Zhu, Bradley Green


  Access Paper or Ask Questions

Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation


Mar 17, 2020
Huiyu Wang, Yukun Zhu, Bradley Green, Hartwig Adam, Alan Yuille, Liang-Chieh Chen


  Access Paper or Ask Questions

Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation


Dec 06, 2019
Bowen Cheng, Maxwell D. Collins, Yukun Zhu, Ting Liu, Thomas S. Huang, Hartwig Adam, Liang-Chieh Chen

* 16-page detailed technical report of arXiv:1910.04751 

  Access Paper or Ask Questions

Search to Distill: Pearls are Everywhere but not the Eyes


Nov 20, 2019
Yu Liu, Xuhui Jia, Mingxing Tan, Raviteja Vemulapalli, Yukun Zhu, Bradley Green, Xiaogang Wang


  Access Paper or Ask Questions

Panoptic-DeepLab


Oct 24, 2019
Bowen Cheng, Maxwell D. Collins, Yukun Zhu, Ting Liu, Thomas S. Huang, Hartwig Adam, Liang-Chieh Chen

* This work is presented at ICCV 2019 Joint COCO and Mapillary Recognition Challenge Workshop 

  Access Paper or Ask Questions

SPGNet: Semantic Prediction Guidance for Scene Parsing


Aug 26, 2019
Bowen Cheng, Liang-Chieh Chen, Yunchao Wei, Yukun Zhu, Zilong Huang, Jinjun Xiong, Thomas Huang, Wen-Mei Hwu, Honghui Shi

* ICCV 2019 

  Access Paper or Ask Questions

Searching for MobileNetV3


May 14, 2019
Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, Hartwig Adam


  Access Paper or Ask Questions

DeeperLab: Single-Shot Image Parser


Mar 12, 2019
Tien-Ju Yang, Maxwell D. Collins, Yukun Zhu, Jyh-Jing Hwang, Ting Liu, Xiao Zhang, Vivienne Sze, George Papandreou, Liang-Chieh Chen

* 20 pages. The code of the proposed Parsing Covering metric is available at http://deeperlab.mit.edu 

  Access Paper or Ask Questions

Searching for Efficient Multi-Scale Architectures for Dense Image Prediction


Sep 11, 2018
Liang-Chieh Chen, Maxwell D. Collins, Yukun Zhu, George Papandreou, Barret Zoph, Florian Schroff, Hartwig Adam, Jonathon Shlens

* Accepted by NIPS 2018 

  Access Paper or Ask Questions

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation


Aug 22, 2018
Liang-Chieh Chen, Yukun Zhu, George Papandreou, Florian Schroff, Hartwig Adam

* ECCV 2018 camera ready 

  Access Paper or Ask Questions

Spatially Adaptive Computation Time for Residual Networks


Jul 02, 2017
Michael Figurnov, Maxwell D. Collins, Yukun Zhu, Li Zhang, Jonathan Huang, Dmitry Vetrov, Ruslan Salakhutdinov

* CVPR 2017 

  Access Paper or Ask Questions

3D Object Proposals using Stereo Imagery for Accurate Object Class Detection


Apr 25, 2017
Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Huimin Ma, Sanja Fidler, Raquel Urtasun

* 14 pages, 12 figures 

  Access Paper or Ask Questions

MovieQA: Understanding Stories in Movies through Question-Answering


Sep 21, 2016
Makarand Tapaswi, Yukun Zhu, Rainer Stiefelhagen, Antonio Torralba, Raquel Urtasun, Sanja Fidler

* CVPR 2016, Spotlight presentation. Benchmark @ http://movieqa.cs.toronto.edu/ Code @ https://github.com/makarandtapaswi/MovieQA_CVPR2016/ 

  Access Paper or Ask Questions

Skip-Thought Vectors


Jun 22, 2015
Ryan Kiros, Yukun Zhu, Ruslan Salakhutdinov, Richard S. Zemel, Antonio Torralba, Raquel Urtasun, Sanja Fidler

* 11 pages 

  Access Paper or Ask Questions

Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books


Jun 22, 2015
Yukun Zhu, Ryan Kiros, Richard Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler


  Access Paper or Ask Questions

segDeepM: Exploiting Segmentation and Context in Deep Neural Networks for Object Detection


Feb 15, 2015
Yukun Zhu, Raquel Urtasun, Ruslan Salakhutdinov, Sanja Fidler


  Access Paper or Ask Questions