FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2987661509> ?p ?o ?g. }

• W2987661509 abstract "Although automatic gaze estimation is very important to a large variety of application areas, it is difficult to train accurate and robust gaze models, in great part due to the difficulty in collecting large and diverse data (annotating 3D gaze is expensive and existing datasets use different setups). To address this issue, our main contribution in this paper is to propose an effective approach to learn a low dimensional gaze representation without gaze annotations, which to the best of our best knowledge, is the first work to do so. The main idea is to rely on a gaze redirection network and use the gaze representation difference of the input and target images (of the redirection network) as the redirection variable. A redirection loss in image domain allows the joint training of both the redirection network and the gaze representation network. In addition, we propose a warping field regularization which not only provides an explicit physical meaning to the gaze representations but also avoids redirection distortions. Promising results on few-shot gaze estimation (competitive results can be achieved with as few as <= 100 calibration samples), cross-dataset gaze estimation, gaze network pretraining, and another task (head pose estimation) demonstrate the validity of our framework." @default.
• W2987661509 created "2019-11-22" @default.
• W2987661509 creator A5053358969 @default.
• W2987661509 creator A5062170722 @default.
• W2987661509 date "2019-11-15" @default.
• W2987661509 modified "2023-10-11" @default.
• W2987661509 title "Unsupervised Representation Learning for Gaze Estimation" @default.
• W2987661509 cites W1589443630 @default.
• W2987661509 cites W1769933788 @default.
• W2987661509 cites W1946259682 @default.
• W2987661509 cites W1982091553 @default.
• W2987661509 cites W1988798713 @default.
• W2987661509 cites W1995694455 @default.
• W2987661509 cites W1997045063 @default.
• W2987661509 cites W2040336280 @default.
• W2987661509 cites W2042906110 @default.
• W2987661509 cites W2047875689 @default.
• W2987661509 cites W2056257735 @default.
• W2987661509 cites W2074840634 @default.
• W2987661509 cites W2077869260 @default.
• W2987661509 cites W2087862817 @default.
• W2987661509 cites W2136773441 @default.
• W2987661509 cites W2139196511 @default.
• W2987661509 cites W2155591525 @default.
• W2987661509 cites W2156972497 @default.
• W2987661509 cites W2167020116 @default.
• W2987661509 cites W2167084080 @default.
• W2987661509 cites W2184540135 @default.
• W2987661509 cites W2258333130 @default.
• W2987661509 cites W2299591120 @default.
• W2987661509 cites W2331128040 @default.
• W2987661509 cites W2397023066 @default.
• W2987661509 cites W2468114283 @default.
• W2987661509 cites W2508756538 @default.
• W2987661509 cites W2519247488 @default.
• W2987661509 cites W2523950919 @default.
• W2987661509 cites W2557669140 @default.
• W2987661509 cites W2567101557 @default.
• W2987661509 cites W2583387051 @default.
• W2987661509 cites W2607909683 @default.
• W2987661509 cites W2749038514 @default.
• W2987661509 cites W2757071000 @default.
• W2987661509 cites W2765629358 @default.
• W2987661509 cites W2776312359 @default.
• W2987661509 cites W2778268008 @default.
• W2987661509 cites W2799164693 @default.
• W2987661509 cites W2883284130 @default.
• W2987661509 cites W2884915206 @default.
• W2987661509 cites W2887595520 @default.
• W2987661509 cites W2895535699 @default.
• W2987661509 cites W2902615807 @default.
• W2987661509 cites W2939489045 @default.
• W2987661509 cites W2944075188 @default.
• W2987661509 cites W2944289193 @default.
• W2987661509 cites W2948303854 @default.
• W2987661509 cites W2961516132 @default.
• W2987661509 cites W2963530216 @default.
• W2987661509 cites W2964135029 @default.
• W2987661509 cites W2982029558 @default.
• W2987661509 cites W2987706603 @default.
• W2987661509 cites W2990900847 @default.
• W2987661509 cites W2994800813 @default.
• W2987661509 cites W3001625344 @default.
• W2987661509 cites W3106262690 @default.
• W2987661509 cites W3124693111 @default.
• W2987661509 cites W603908379 @default.
• W2987661509 doi "https://doi.org/10.48550/arxiv.1911.06939" @default.
• W2987661509 hasPublicationYear "2019" @default.
• W2987661509 type Work @default.
• W2987661509 sameAs 2987661509 @default.
• W2987661509 citedByCount "1" @default.
• W2987661509 countsByYear W29876615092020 @default.
• W2987661509 crossrefType "posted-content" @default.
• W2987661509 hasAuthorship W2987661509A5053358969 @default.
• W2987661509 hasAuthorship W2987661509A5062170722 @default.
• W2987661509 hasBestOaLocation W29876615091 @default.
• W2987661509 hasConcept C119857082 @default.
• W2987661509 hasConcept C154945302 @default.
• W2987661509 hasConcept C157202957 @default.
• W2987661509 hasConcept C162324750 @default.
• W2987661509 hasConcept C17744445 @default.
• W2987661509 hasConcept C187736073 @default.
• W2987661509 hasConcept C199539241 @default.
• W2987661509 hasConcept C2776135515 @default.
• W2987661509 hasConcept C2776359362 @default.
• W2987661509 hasConcept C2779916870 @default.
• W2987661509 hasConcept C2780451532 @default.
• W2987661509 hasConcept C31972630 @default.
• W2987661509 hasConcept C41008148 @default.
• W2987661509 hasConcept C94625758 @default.
• W2987661509 hasConceptScore W2987661509C119857082 @default.
• W2987661509 hasConceptScore W2987661509C154945302 @default.
• W2987661509 hasConceptScore W2987661509C157202957 @default.
• W2987661509 hasConceptScore W2987661509C162324750 @default.
• W2987661509 hasConceptScore W2987661509C17744445 @default.
• W2987661509 hasConceptScore W2987661509C187736073 @default.
• W2987661509 hasConceptScore W2987661509C199539241 @default.
• W2987661509 hasConceptScore W2987661509C2776135515 @default.
• W2987661509 hasConceptScore W2987661509C2776359362 @default.
• W2987661509 hasConceptScore W2987661509C2779916870 @default.

• next