FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3113159821> ?p ?o ?g. }

• W3113159821 abstract "The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be accessed and scanned might be limited; even given sufficient data, acquiring 3D labels (e.g. instance masks) requires intensive human labor. In this paper, we explore data-efficient learning for 3D point cloud. As a first step towards this direction, we propose Contrastive Scene Contexts, a 3D pre-training method that makes use of both point-level correspondences and spatial contexts in a scene. Our method achieves state-of-the-art results on a suite of benchmarks where training data or labels are scarce. Our study reveals that exhaustive labelling of 3D point clouds might be unnecessary; and remarkably, on ScanNet, even using 0.1% of point labels, we still achieve 89% (instance segmentation) and 96% (semantic segmentation) of the baseline performance that uses full annotations." @default.
• W3113159821 created "2020-12-21" @default.
• W3113159821 creator A5024785349 @default.
• W3113159821 creator A5048723240 @default.
• W3113159821 creator A5056640262 @default.
• W3113159821 creator A5088583491 @default.
• W3113159821 date "2020-12-16" @default.
• W3113159821 modified "2023-10-17" @default.
• W3113159821 title "Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts" @default.
• W3113159821 cites W116751493 @default.
• W3113159821 cites W125693051 @default.
• W3113159821 cites W1861492603 @default.
• W3113159821 cites W1901129140 @default.
• W3113159821 cites W1923184257 @default.
• W3113159821 cites W1985238052 @default.
• W3113159821 cites W2057175746 @default.
• W3113159821 cites W2102605133 @default.
• W3113159821 cites W2108598243 @default.
• W3113159821 cites W2150066425 @default.
• W3113159821 cites W2156406284 @default.
• W3113159821 cites W2163922914 @default.
• W3113159821 cites W2190691619 @default.
• W3113159821 cites W2397854647 @default.
• W3113159821 cites W2460657278 @default.
• W3113159821 cites W2560609797 @default.
• W3113159821 cites W2594519801 @default.
• W3113159821 cites W2769312834 @default.
• W3113159821 cites W2784996692 @default.
• W3113159821 cites W2796426482 @default.
• W3113159821 cites W2798270772 @default.
• W3113159821 cites W2798991696 @default.
• W3113159821 cites W2842511635 @default.
• W3113159821 cites W2850910281 @default.
• W3113159821 cites W2885317998 @default.
• W3113159821 cites W2887997457 @default.
• W3113159821 cites W2904332125 @default.
• W3113159821 cites W2948672349 @default.
• W3113159821 cites W2959771705 @default.
• W3113159821 cites W2961368225 @default.
• W3113159821 cites W2962731536 @default.
• W3113159821 cites W2962759414 @default.
• W3113159821 cites W2963121255 @default.
• W3113159821 cites W2963125977 @default.
• W3113159821 cites W2963182550 @default.
• W3113159821 cites W2963226018 @default.
• W3113159821 cites W2963231572 @default.
• W3113159821 cites W2964062501 @default.
• W3113159821 cites W2964074439 @default.
• W3113159821 cites W2970160935 @default.
• W3113159821 cites W2971155163 @default.
• W3113159821 cites W2971230666 @default.
• W3113159821 cites W2986382673 @default.
• W3113159821 cites W2988715931 @default.
• W3113159821 cites W2989673842 @default.
• W3113159821 cites W2990613095 @default.
• W3113159821 cites W2991485494 @default.
• W3113159821 cites W2995182785 @default.
• W3113159821 cites W3005680577 @default.
• W3113159821 cites W3033437302 @default.
• W3113159821 cites W3034429258 @default.
• W3113159821 cites W3034430142 @default.
• W3113159821 cites W3034550906 @default.
• W3113159821 cites W3034577798 @default.
• W3113159821 cites W3034626012 @default.
• W3113159821 cites W3034781633 @default.
• W3113159821 cites W3034949383 @default.
• W3113159821 cites W3035058308 @default.
• W3113159821 cites W3035172746 @default.
• W3113159821 cites W3035429765 @default.
• W3113159821 cites W3035524453 @default.
• W3113159821 cites W3035739565 @default.
• W3113159821 cites W3037078045 @default.
• W3113159821 cites W3045125647 @default.
• W3113159821 cites W3095121901 @default.
• W3113159821 cites W3098903812 @default.
• W3113159821 cites W3101821705 @default.
• W3113159821 cites W3108655343 @default.
• W3113159821 cites W3110047846 @default.
• W3113159821 cites W52592340 @default.
• W3113159821 doi "https://doi.org/10.48550/arxiv.2012.09165" @default.
• W3113159821 hasPublicationYear "2020" @default.
• W3113159821 type Work @default.
• W3113159821 sameAs 3113159821 @default.
• W3113159821 citedByCount "0" @default.
• W3113159821 crossrefType "posted-content" @default.
• W3113159821 hasAuthorship W3113159821A5024785349 @default.
• W3113159821 hasAuthorship W3113159821A5048723240 @default.
• W3113159821 hasAuthorship W3113159821A5056640262 @default.
• W3113159821 hasAuthorship W3113159821A5088583491 @default.
• W3113159821 hasBestOaLocation W31131598211 @default.
• W3113159821 hasConcept C131979681 @default.
• W3113159821 hasConcept C154945302 @default.
• W3113159821 hasConcept C166957645 @default.
• W3113159821 hasConcept C205649164 @default.
• W3113159821 hasConcept C2524010 @default.
• W3113159821 hasConcept C28719098 @default.
• W3113159821 hasConcept C31972630 @default.
• W3113159821 hasConcept C33923547 @default.
• W3113159821 hasConcept C41008148 @default.
• W3113159821 hasConcept C79581498 @default.

• next