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

Add to Chrome

Add to Firefox

Picture for Long Zhao

Long Zhao

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

Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

Jul 20, 2022
Yuxiao Chen, Long Zhao, Jianbo Yuan, Yu Tian, Zhaoyang Xia, Shijie Geng, Ligong Han, Dimitris N. Metaxas

Figure 1 for Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

* Accepted to ECCV 2022

Access Paper or Ask Questions

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Jul 18, 2022
Shiyu Zhao, Zhixing Zhang, Samuel Schulter, Long Zhao, Vijay Kumar B. G, Anastasis Stathopoulos, Manmohan Chandraker, Dimitris Metaxas

Figure 1 for Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Figure 2 for Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Figure 3 for Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Figure 4 for Exploiting Unlabeled Data with Vision and Language Models for Object Detection

* Accepted to ECCV 2022 (with the supplementary document)

Access Paper or Ask Questions

Are Multimodal Transformers Robust to Missing Modality?

Apr 12, 2022
Mengmeng Ma, Jian Ren, Long Zhao, Davide Testuggine, Xi Peng

Figure 1 for Are Multimodal Transformers Robust to Missing Modality?

Figure 2 for Are Multimodal Transformers Robust to Missing Modality?

Figure 3 for Are Multimodal Transformers Robust to Missing Modality?

Figure 4 for Are Multimodal Transformers Robust to Missing Modality?

* In CVPR 2022

Access Paper or Ask Questions

Global Matching with Overlapping Attention for Optical Flow Estimation

Mar 21, 2022
Shiyu Zhao, Long Zhao, Zhixing Zhang, Enyu Zhou, Dimitris Metaxas

Figure 1 for Global Matching with Overlapping Attention for Optical Flow Estimation

Figure 2 for Global Matching with Overlapping Attention for Optical Flow Estimation

Figure 3 for Global Matching with Overlapping Attention for Optical Flow Estimation

Figure 4 for Global Matching with Overlapping Attention for Optical Flow Estimation

* Accepted to CVPR 2022 (with additional figures)

Access Paper or Ask Questions

Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach

Aug 05, 2021
Xi Peng, Fengchun Qiao, Long Zhao

Figure 1 for Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach

Figure 2 for Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach

Figure 3 for Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach

Figure 4 for Out-of-domain Generalization from a Single Source: A Uncertainty Quantification Approach

* 14 pages, 12 figures, submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (under review)

Access Paper or Ask Questions

Improved Transformer for High-Resolution GANs

Jun 14, 2021
Long Zhao, Zizhao Zhang, Ting Chen, Dimitris N. Metaxas, Han Zhang

Figure 1 for Improved Transformer for High-Resolution GANs

Figure 2 for Improved Transformer for High-Resolution GANs

Figure 3 for Improved Transformer for High-Resolution GANs

Figure 4 for Improved Transformer for High-Resolution GANs

* Preprint

Access Paper or Ask Questions