Tao Kong

ByteDance Research

Email: kongtao@bytedance.com

Google Scholar • arXiv • Github • Zhihu

Intro

I am a research scientist in ByteDance Research.
At ByteDance, I lead research programs on developing next-generation robot techniques and systems to perform intelligent perception, action, and interaction in the real world. I received my Ph.D. from Tsinghua University, advised by Fuchun Sun. I visited the University of Pennsylvania, working with Jianbo Shi. I also spent great internship time at Intel Labs, Microsoft Research Asia and ByteDance. I am the recipient of the CAAI Excellent Doctoral Dissertation Nomination Award 2020, IROS Robotic Grasping and Manipulation Competition Winner Award 2016, and Habitat ObjectNav Challenge Winner Award 2022.
We are recruiting interns / full-time researchers and engineers in robotics. If you are interested in these positions, please drop me an email.

[11/2022] We won the first place in Habitat ObjectNav Challenge 2022. Congratulations!
[10/2022] One paper about reference expression generation and comprehension got accepted by EMNLP 2022.
[09/2022] One paper about category-level shape and pose estimation got accepted by CoRL 2022.
[06/2022] We have two papers accepted by IROS 2022, and one paper accepted by RAL. Congratulations!
[04/2022] Our journal extention of SA-AutoAug got accepted by TPAMI!
[01/2022] iBOT got accepted by ICLR 2022, setting new SOTAs on ImageNet linear acc (82.3%), fine-tuning acc (87.8%), as well as unsupervised ARI (32.8%)!

Navigating to Objects in Unseen Environments by Distance Prediction
Minzhao Zhu, Binglei Zhao, Tao Kong
IROS 2022. (Oral) [Paper]
Our base method to win the Habitat ObjectNav Challenge 2022.
iBOT: Image BERT Pre-Training with Online Tokenizer
Jinghao Zhou*, Chen Wei, Huiyu Wang, Wei Shen, Cihang Xie, Alan Yuille and Tao Kong
ICLR 2022. [Paper][Code]
New SOTAs on ImageNet-1k linear-probing, fine-tuning, as well as unsupervised classification protocols.
SOLOv2: Dynamic and Fast Instance Segmentation
Xinlong Wang*, Rufeng Zhang*, Tao Kong, Lei Li and Chunhua Shen
NeurIPS 2020. [Paper][Code]
SOLO: Segmenting Objects by Locations
Xinlong Wang*, Tao Kong, Chunhua Shen, Yuning Jiang and Lei Li
ECCV 2020. [Project][Paper][Code]
Among the Most Influential ECCV Papers in Google Scholar Metrics
FoveaBox: Beyond Anchor-based Object Detector
Tao Kong, Fuchun Sun, Huaping Liu, Yuning Jiang, Lei Li, Jianbo Shi
IEEE Trans. on Image Processing 2020. [Project][Paper][Code]
ESI Highly Cited Paper (Top 1%)
RON: Reverse Connection with Objectness Prior Networks for Object Detection
Tao Kong, Fuchun Sun, Anbang Yao, Huaping Liu, Yurong Chen, Ming Lu
CVPR 2017. [Paper][Code]
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
Tao Kong, Anbang Yao, Yurong Chen, Fuchun Sun
CVPR 2016. (Spotlight) [Paper]
Among the Most Influential CVPR Papers in Google Scholar Metrics

Last update: Nov, 2022