Fugu-MT 論文翻訳(概要): LNSMM: Eye Gaze Estimation With Local Network Share Multiview Multitask

論文の概要: LNSMM: Eye Gaze Estimation With Local Network Share Multiview Multitask

arxiv url: http://arxiv.org/abs/2101.07116v1
Date: Mon, 18 Jan 2021 15:14:24 GMT
ステータス: 処理完了
システム内更新日: 2021-03-27 06:07:14.563106
Title: LNSMM: Eye Gaze Estimation With Local Network Share Multiview Multitask
Title（参考訳）: LNSMM:ローカルネットワーク共有マルチビューマルチタスクによる眼球運動推定
Authors: Yong Huang, Ben Chen, Daiming Qu
Abstract要約: 本稿では,視線点と視線方向を同時に推定する新しい手法を提案する。本手法は,視線点と視線方向の2つの指標について,現在主流の手法であることを示す。
参考スコア（独自算出の注目度）: 7.065909514483728
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Eye gaze estimation has become increasingly significant in computer vision.In this paper,we systematically study the mainstream of eye gaze estimation methods,propose a novel methodology to estimate eye gaze points and eye gaze directions simultaneously.First,we construct a local sharing network for feature extraction of gaze points and gaze directions estimation,which can reduce network computational parameters and converge quickly;Second,we propose a Multiview Multitask Learning (MTL) framework,for gaze directions,a coplanar constraint is proposed for the left and right eyes,for gaze points,three views data input indirectly introduces eye position information,a cross-view pooling module is designed, propose joint loss which handle both gaze points and gaze directions estimation.Eventually,we collect a dataset to use of gaze points,which have three views to exist public dataset.The experiment show our method is state-of-the-art the current mainstream methods on two indicators of gaze points and gaze directions.
Abstract（参考訳）: Eye gaze estimation has become increasingly significant in computer vision.In this paper,we systematically study the mainstream of eye gaze estimation methods,propose a novel methodology to estimate eye gaze points and eye gaze directions simultaneously.First,we construct a local sharing network for feature extraction of gaze points and gaze directions estimation,which can reduce network computational parameters and converge quickly;Second,we propose a Multiview Multitask Learning (MTL) framework,for gaze directions,a coplanar constraint is proposed for the left and right eyes,for gaze points,three views data input indirectly introduces eye position information,a cross-view pooling module is designed, propose joint loss which handle both gaze points and gaze directions estimation.Eventually,we collect a dataset to use of gaze points,which have three views to exist public dataset.The experiment show our method is state-of-the-art the current mainstream methods on two indicators of gaze points and gaze directions.