Home /
Research
Showing 559 - 564 / 904
Expertise and confidence explain how social influence evolves along intellective tasks
OmidAskarisichani, ElizabethY.Huang, KekoaS.Sato....
Published date-11/13/2020
Discovering the antecedents of individuals' influence in collaborative environments is an important, practical, and challenging problem. In this paper, we study interpersonal influence in small groups of individuals who collectively …
RethinkCWS: Is Chinese Word Segmentation a Solved Task?
JinlanFu, PengFeiLiu, QiZhang....
Published date-11/13/2020
ChineseWordSegmentation
The performance of the Chinese Word Segmentation (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks, especially the successful use of large pre-trained models. …
Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis
DanielSeichter, MonaKöhler, BenjaminLewandowski....
Published date-11/13/2020
SemanticSegmentation
Analyzing scenes thoroughly is crucial for mobile robots acting in different environments. Semantic segmentation can enhance various subsequent tasks, such as (semantically assisted) person perception, (semantic) free space detection, (semantic) …
Image Animation with Perturbed Masks
YoavShalev, LiorWolf....
Published date-11/13/2020
ImageAnimation
We present a novel approach for image-animation of a source image by a driving video, both depicting the same type of object. We do not assume the existence of pose …
Investigating Learning in Deep Neural Networks using Layer-Wise Weight Change
AyushManishAgrawal, AtharvaTendle, HarshvardhanSikka....
Published date-11/13/2020
Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. …
diagNNose: A Library for Neural Activation Analysis
JaapJumelet....
Published date-11/13/2020
In this paper we introduce diagNNose, an open source library for analysing the activations of deep neural networks. diagNNose contains a wide array of interpretability techniques that provide fundamental insights …