About Me

I'm a third-year Ph.D. student at Nanyang Technological University MReaL Lab, supervised by Hanwang Zhang.

I got my Bachelor's degree from IEEE honor class at Shanghai Jiao Tong University, and dual-master degrees from both Shanghai Jiao Tong University and Waseda University.

My research interests are scene understanding, long-tailed recognition, visual reasoning and causal inference in computer vision.

Publications

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect

Kaihua Tang, Jianqiang Huang, Hanwang Zhang

NeurIPS 2020

Counterfactual VQA: A Cause-Effect Look at Language Bias

Yulei Niu, Kaihua Tang, Hanwang Zhang, Zhiwu Lu, Xian-Sheng Hua, Ji-Rong Wen

preprint

Unbiased Scene Graph Generation from Biased Training

Kaihua Tang, Yulei Niu, Jianqiang Huang, Jiaxin Shi, Hanwang Zhang

CVPR 2020 (oral)

Learning to Segment the Tail

Xinting Hu, Yi Jiang, Kaihua Tang, Hanwang Zhang, Chunyan Miao, Jingyuan Chen

CVPR 2020

Learning to Compose Dynamic Tree Structures for Visual Contexts

Kaihua Tang, Hanwang Zhang, Baoyuan Wu, Wenhan Luo, Wei Liu

CVPR 2019 (oral & appears on the Best Paper Finalists [accept rate: 0.87% = 45/5160])

Auto-Encoding Scene Graphs for Image Captioning

Xu Yang, Kaihua Tang, Hanwang Zhang, Jianfei Cai

CVPR 2019 (oral)

Eigen-Aging Reference Coding for Cross-Age Face Verification and Retrieval

Kaihua Tang, Sei-ichiro Kamata, Xiaonan Hou, Shouhong Ding, Lizhuang Ma

ACCV 2016

Awards

PREMIA Best Student Paper, Silver Award (2nd Place), PREMIA, 2019

Honorable Judge Award, The 5th Cloud Programming World Cup, FORUM8 Tokyo, 2017

Waseda Partial Tuition-Waiver Scholarship for International Students (10/300), Waseda University, 2015

IPS special scholarship for international students, Waseda University, 2014

Monbukagakusho Honors Scholarship for International Students, JASSO, 2014

Emerging Talent Award, The 1st Cloud Programming World Cup, FORUM8 Tokyo, 2013

Educations

Nanyang Technological University, Singapore

Ph.D Candidate of Computer Science and Engineering (2018.7 - Now)

Working with Asst Prof.Zhang Hanwang.

Waseda University, Japan; Shanghai Jiao Tong University, China

Dual Master Program of Science (2015.9 - 2018.3)

Primary major in Computer Science. Working with Prof.Ma Lizhuang & Prof.Kamata Sei-ichiro.

Shanghai Jiao Tong University, China

Bachelor of Science (2011.9 - 2015.8)

Primary major in Computer Science, Second major in Chinese Traditional Painting

Projects

Scene Graph Benchmark in Pytorch

This project aims to build a new CODEBASE for Scene Graph Generation (SGG), and it is also a Pytorch implementation of the paper "Unbiased Scene Graph Generation from Biased Training". It is built on top of the well-known maskrcnn-benchmark and defines relationship prediction as an additional roi_head. Moreover, I included all the exsiting metrics: R@K, mR@K, ngR@K, zR@K, to benchmark the SGG.

VQA2.0 Recent Approachs 2018 in Pytorch

An open-source visual question answering (VQA) CODEBASE built on top of the bottom-up-attention-vqa. It integrates several popular VQA papers published in 2018, which includes: bottom-up top-down, bilinear attention network, learning to count, learning conditioned graph structures, intra- and inter-modality attention.

Indie Game Development

Out of interest, I independently developed several mobile games on Iphone. They have been downloaded over 10k times on Apple store in half a year.

Experience

Tencent, AI Lab, Research Intern (2018.3 - 2018.6)

Major topic: Scene Graph Generation
Mentor: Wenhan Luo, Baoyuan Wu

Mihoyo, Software Engineer Intern (2017.4 - 2017.12)

Mobile Game Development Using Unity 3D.

Toshiba, Research & Development Intern (2015.8 - 2015.9)

Major Project: Scenery Image Stitching and Inpainting.
Mentor: Kaoru Matsuoka

YAPM Summer Volunteer, Yunnan Province, China (2014.7 - 2014.8)

Youth Ambassador Program for Minorities (TECC Organization) is determined to help the youth generation of minorities in remote area of China to inherit and protect their cultures.