DensePhysNet: Learning Dense Physical Object Representations Via Multi-Step Dynamic Interactions
We study the problem of learning physical object representations for robot manipulation. Understanding object physics is critical for successful object manipulation, but also challenging because physical object properties can rarely be inferred from the object's static appearance. In this paper...
Main Authors: | Xu, Zhenjia (Author), Wu, Jiajun (Author), Zeng, Andy (Author), Tenenbaum, Joshua (Author), Song, Shuran (Author) |
---|---|
Format: | Article |
Language: | English |
Published: |
Robotics: Science and Systems Foundation,
2021-12-07T13:49:46Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Automatic DenseNet Sparsification
by: Tao Li, et al.
Published: (2020-01-01) -
S-DenseNet: A DenseNet Compression Model Based on Convolution Grouping Strategy Using Skyline Method
by: Changyong Yu, et al.
Published: (2019-01-01) -
Quiver representations and their dense orbits
by: Lara, Danny
Published: (2019) -
Effective Combination of DenseNet and BiLSTM for Keyword Spotting
by: Mengjun Zeng, et al.
Published: (2019-01-01) -
DENSE IMAGE MATCHING WITH TWO STEPS OF EXPANSION
by: Z. Zhang, et al.
Published: (2016-06-01)