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

Add to Chrome

Add to Firefox

Picture for Tao Wang

Tao Wang

The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Jul 26, 2020
Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Junhao Liew, Sheng Tang, Steven Hoi, Jiashi Feng

Figure 1 for The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Figure 2 for The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Figure 3 for The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

Figure 4 for The Devil is in Classification: A Simple Framework for Long-tail Instance Segmentation

* LVIS 2019 challenge winner, performance significantly improved after challenge submission, accepted at ECCV 2019

Access Paper or Ask Questions

A Multi-Level Approach to Waste Object Segmentation

Jul 08, 2020
Tao Wang, Yuanzheng Cai, Lingyu Liang, Dongyi Ye

Figure 1 for A Multi-Level Approach to Waste Object Segmentation

Figure 2 for A Multi-Level Approach to Waste Object Segmentation

Figure 3 for A Multi-Level Approach to Waste Object Segmentation

Figure 4 for A Multi-Level Approach to Waste Object Segmentation

* Paper appears in Sensors 2020, 20(14), 3816

Access Paper or Ask Questions

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

Jun 18, 2020
Yu Li, Tao Wang, Bingyi Kang, Sheng Tang, Chunfeng Wang, Jintao Li, Jiashi Feng

Figure 1 for Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

Figure 2 for Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

Figure 3 for Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

Figure 4 for Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

* CVPR 2020 (Oral). Code is available at https://github.com/FishYuLi/BalancedGroupSoftmax

Access Paper or Ask Questions

Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

May 19, 2020
Weiyao Lin, Huabin Liu, Shizhan Liu, Yuxi Li, Guo-Jun Qi, Rui Qian, Tao Wang, Nicu Sebe, Ning Xu, Hongkai Xiong, Mubarak Shah

Figure 1 for Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

Figure 2 for Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

Figure 3 for Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

Figure 4 for Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events

* Dataset for ACM MM'20 Grand Challenge on Large-scale Human-centric Video Analysis in Complex Events (http://humaninevents.org)

Access Paper or Ask Questions

Making Robots Draw A Vivid Portrait In Two Minutes

May 12, 2020
Fei Gao, Jingjie Zhu, Zeyuan Yu, Peng Li, Tao Wang

Figure 1 for Making Robots Draw A Vivid Portrait In Two Minutes

Figure 2 for Making Robots Draw A Vivid Portrait In Two Minutes

Figure 3 for Making Robots Draw A Vivid Portrait In Two Minutes

Figure 4 for Making Robots Draw A Vivid Portrait In Two Minutes

* 7 pages, 7 figures

Access Paper or Ask Questions

Structure-Level Knowledge Distillation For Multilingual Sequence Labeling

Apr 29, 2020
Xinyu Wang, Yong Jiang, Nguyen Bach, Tao Wang, Fei Huang, Kewei Tu

Figure 1 for Structure-Level Knowledge Distillation For Multilingual Sequence Labeling

Figure 2 for Structure-Level Knowledge Distillation For Multilingual Sequence Labeling

Figure 3 for Structure-Level Knowledge Distillation For Multilingual Sequence Labeling

Figure 4 for Structure-Level Knowledge Distillation For Multilingual Sequence Labeling

* Accepted to ACL 2020, camera-ready. 14 pages

Access Paper or Ask Questions

Automatic low-bit hybrid quantization of neural networks through meta learning

Apr 24, 2020
Tao Wang, Junsong Wang, Chang Xu, Chao Xue

Figure 1 for Automatic low-bit hybrid quantization of neural networks through meta learning

Figure 2 for Automatic low-bit hybrid quantization of neural networks through meta learning

Figure 3 for Automatic low-bit hybrid quantization of neural networks through meta learning

Figure 4 for Automatic low-bit hybrid quantization of neural networks through meta learning

* 7 pages, 3 figures

Access Paper or Ask Questions