Home /

Research

Showing 517 - 522 / 897

Privacy-Preserving Pose Estimation for Human-Robot Interaction


Authors:  YouyaXia, YifanTang, YuhanHu....
Published date-11/14/2020
Tasks:  Humanrobotinteraction, ImageEnhancement, PoseEstimation

Abstract: Pose estimation is an important technique for nonverbal human-robot interaction. That said, the presence of a camera in a person's space raises privacy concerns and could lead to distrust of …

Solving Physics Puzzles by Reasoning about Paths


Authors:  AugustinHarter, AndrewMelnik, GauravKumar....
Published date-11/14/2020

Abstract: We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal. Its modular structure is …

Deep Spatial Learning with Molecular Vibration


Authors:  ZiyangZhang, YingtaoLuo....
Published date-11/14/2020

Abstract: Machine learning over-fitting caused by data scarcity greatly limits the application of machine learning for molecules. Due to manufacturing processes difference, big data is not always rendered available through computational …

SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation


Authors:  XingyuLin, YuFeiWang, JakeOlkin....
Published date-11/14/2020
Tasks:  DeformableObjectManipulation, OpenAIGym

Abstract: Manipulating deformable objects has long been a challenge in robotics due to its high dimensional state representation and complex dynamics. Recent success in deep reinforcement learning provides a promising direction …

DebateSum: A large-scale argument mining and summarization dataset


Authors:  AllenRoush, ArvindBalaji....
Published date-11/14/2020
Tasks:  AbstractiveTextSummarization, ArgumentMining, DocumentSummarization, ExtractiveDocumentSummarization, InformationRetrieval, Query-BasedExtractiveSummarization, TextSummarization

Abstract: Prior work in Argument Mining frequently alludes to its potential applications in automatic debating systems. Despite this focus, almost no datasets or models exist which apply natural language processing techniques …

Deep Interpretable Classification and Weakly-Supervised Segmentation of Histology Images via Max-Min Uncertainty


Authors:  SoufianeBelharbi, JérômeRony, JoseDolz....
Published date-11/14/2020

Abstract: Weakly supervised learning (WSL) has recently triggered substantial interest as it mitigates the lack of pixel-wise annotations, while enabling interpretable models. Given global image labels, WSL methods yield pixel-level predictions …

Filter by

Categories

Tags