no code implementations • 29 Apr 2024 • Skand Peri, Iain Lee, Chanho Kim, Li Fuxin, Tucker Hermans, Stefan Lee
In this work, we examine robustness to a suite of these types of visual changes for RGB-D and point cloud based visual control policies.
no code implementations • 9 Apr 2024 • Chanho Kim, Li Fuxin
Modeling object dynamics with a neural network is an important problem with numerous applications.
no code implementations • 26 Sep 2023 • Yixuan Huang, Jialin Yuan, Chanho Kim, Pupul Pradhan, Bryan Chen, Li Fuxin, Tucker Hermans
Robots need to have a memory of previously observed, but currently occluded objects to work reliably in realistic environments.
no code implementations • 29 Jan 2023 • Jialin Yuan, Jay Patravali, Hung Nguyen, Chanho Kim, Li Fuxin
On the related problem of video instance segmentation, our method shows competitive performance with the previous best algorithm that requires joint training with the VOS algorithm.
no code implementations • 14 Sep 2021 • Hung Nguyen, Chanho Kim, Fuxin Li
We propose a novel visual memory network architecture for the learning and inference problem in the spatial-temporal domain.
1 code implementation • CVPR 2021 • Chanho Kim, Li Fuxin, Mazen Alotaibi, James M. Rehg
Many approaches model each target in isolation and lack the ability to use all the targets in the scene to jointly update the memory.
3 code implementations • 30 Jan 2020 • Max Allan, Satoshi Kondo, Sebastian Bodenstedt, Stefan Leger, Rahim Kadkhodamohammadi, Imanol Luengo, Felix Fuentes, Evangello Flouty, Ahmed Mohammed, Marius Pedersen, Avinash Kori, Varghese Alex, Ganapathy Krishnamurthi, David Rauber, Robert Mendel, Christoph Palm, Sophia Bano, Guinther Saibro, Chi-Sheng Shih, Hsun-An Chiang, Juntang Zhuang, Junlin Yang, Vladimir Iglovikov, Anton Dobrenkii, Madhu Reddiboina, Anubhav Reddy, Xingtong Liu, Cong Gao, Mathias Unberath, Myeonghyeon Kim, Chanho Kim, Chaewon Kim, Hye-Jin Kim, Gyeongmin Lee, Ihsan Ullah, Miguel Luna, Sang Hyun Park, Mahdi Azizian, Danail Stoyanov, Lena Maier-Hein, Stefanie Speidel
In 2015 we began a sub-challenge at the EndoVis workshop at MICCAI in Munich using endoscope images of ex-vivo tissue with automatically generated annotations from robot forward kinematics and instrument CAD models.
no code implementations • ECCV 2018 • Chanho Kim, Fuxin Li, James M. Rehg
We also propose novel data augmentation approaches to efficiently train recurrent models that score object tracks on both appearance and motion.
no code implementations • ICCV 2015 • Chanho Kim, Fuxin Li, Arridhana Ciptadi, James M. Rehg
This paper revisits the classical multiple hypotheses tracking (MHT) algorithm in a tracking-by-detection framework.