Picture for Liangzhe Yuan

Liangzhe Yuan

Unified Visual Relationship Detection with Vision and Language Models

Mar 16, 2023
Long Zhao, Liangzhe Yuan, Boqing Gong, Yin Cui, Florian Schroff, Ming-Hsuan Yang, Hartwig Adam, Ting Liu

Figure 1 for Unified Visual Relationship Detection with Vision and Language Models

Figure 2 for Unified Visual Relationship Detection with Vision and Language Models

Figure 3 for Unified Visual Relationship Detection with Vision and Language Models

Figure 4 for Unified Visual Relationship Detection with Vision and Language Models

* Technical report (14 pages)

Access Paper or Ask Questions

Surrogate Gap Minimization Improves Sharpness-Aware Training

Mar 19, 2022
Juntang Zhuang, Boqing Gong, Liangzhe Yuan, Yin Cui, Hartwig Adam, Nicha Dvornek, Sekhar Tatikonda, James Duncan, Ting Liu

Figure 1 for Surrogate Gap Minimization Improves Sharpness-Aware Training

Figure 2 for Surrogate Gap Minimization Improves Sharpness-Aware Training

Figure 3 for Surrogate Gap Minimization Improves Sharpness-Aware Training

Figure 4 for Surrogate Gap Minimization Improves Sharpness-Aware Training

* Paper accepted by ICLR22, https://openreview.net/forum?id=edONMAnhLu-

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

Figure 1 for DeepLab2: A TensorFlow Library for Deep Labeling

Figure 2 for DeepLab2: A TensorFlow Library for Deep Labeling

Figure 3 for DeepLab2: A TensorFlow Library for Deep Labeling

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

Access Paper or Ask Questions

MoViNets: Mobile Video Networks for Efficient Video Recognition

Apr 18, 2021
Dan Kondratyuk, Liangzhe Yuan, Yandong Li, Li Zhang, Mingxing Tan, Matthew Brown, Boqing Gong

Figure 1 for MoViNets: Mobile Video Networks for Efficient Video Recognition

Figure 2 for MoViNets: Mobile Video Networks for Efficient Video Recognition

Figure 3 for MoViNets: Mobile Video Networks for Efficient Video Recognition

Figure 4 for MoViNets: Mobile Video Networks for Efficient Video Recognition

* Accepted to CVPR 2021

Access Paper or Ask Questions

View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

Oct 23, 2020
Ting Liu, Jennifer J. Sun, Long Zhao, Jiaping Zhao, Liangzhe Yuan, Yuxiao Wang, Liang-Chieh Chen, Florian Schroff, Hartwig Adam

Figure 1 for View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

Figure 2 for View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

Figure 3 for View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

Figure 4 for View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose

* Code is available at https://github.com/google-research/google-research/tree/master/poem . Video synchronization results are available at https://drive.google.com/corp/drive/folders/1nhPuEcX4Lhe6iK3nv84cvSCov2eJ52Xy. arXiv admin note: text overlap with arXiv:1912.01001

Access Paper or Ask Questions