Meta tags:

Headings (most frequently used words):

-

Text of the page (most frequently used words):
and (15), models (7), transfer (5), for (5), cross (4), modal (4), rescaling (4), physical (4), attributes (4), real (4), world (4), attribute (3), webpages (3), shapes (3), dimensions (3), university (3), shao (2), lin (2), chang (2), angel (2), hao (2), savva (2), manolis (2), guibas (2), leonidas (2), international (2), conference (2), vision (2), 3dv (2), 2017 (2), between (2), with (2), objects (2), images (2), level (2), linking (2), our (2), approach (2), dataset (2), that (2), model (2), inproceedings, lin2017crossmodal, title, author, booktitle, proceedings, the, year, present, algorithm, transferring, crawl, product, catalogues, other, structured, metadata, containing, such, weights, then, using, joint, embedding, view, based, weighting, aspect, ratio, filtering, scheme, instance, counterpart, evaluate, large, scale, unscaled, show, outperform, prior, work, considers, only, category, size, priors, data, paper, abstract, figure, left, connect, transfers, through, text, purple, orange, links, correspondingly, right, rectify, physically, implausible, scales, california, san, diego, princeton, stanford,

Text of the page (random words):
cross modal attribute transfer for rescaling 3d models cross modal attribute transfer for rescaling 3d models lin shao angel x chang hao su manolis savva leonidas j guibas stanford university princeton university university of california san diego international conference on 3d vision 3dv 2017 figure 1 left we connect 3d models to webpages with physical attributes our approach transfers real world dimensions by cross modal linking through text or images purple and orange links correspondingly right we transfer real world dimensions to a 3d model dataset and rectify physically implausible model scales abstract we present an algorithm for transferring physical attributes between webpages and 3d shapes we crawl product catalogues and other webpages with structured metadata containing physical attributes such as dimensions and weights then we transfer physical attributes between shapes and real world objects using a joint embedding of images and 3d shapes and a view based weighting and aspect ratio filtering scheme for instance level linking of 3d models and real world counterpart objects we evaluate our approach on a large scale dataset of unscaled 3d models and show that we outperform prior work on rescaling 3d models that considers only category level size priors paper data inproceedings lin2017crossmodal title cross modal attribute transfer for rescaling 3d models author shao lin and chang angel x and su hao and savva manolis and guibas leonidas booktitle proceedings of the international conference on 3d vision 3dv year 2017