Image-to-Markup Generation with Coarse-to-Fine Attention · HackerPapers discussions

Image-to-Markup Generation with Coarse-to-Fine Attention — mentioned by srush

Fri, 03 Nov 2023 15:42:11 GMT

Want to give proper credit to my former student for starting this: Yuntian Deng et al., 2016 (https://arxiv.org/abs/1609.04938). I believe this repo uses the dataset from that paper. Some recent cool work he's been doing: https://www.youtube.com/watch?v=lx1XcTdhalU.

Paper and discussion history. A mention is not an endorsement.

Image-to-Markup Generation with Coarse-to-Fine Attention — mentioned by yorwba

Sat, 30 Dec 2017 13:55:59 GMT

Are you sure that extracting document structure from a screenshot is a solved task? I'm aware of "What You Get Is What You See" [1], but they are nowhere close to 100% accuracy even for reconstructing the original markup, which does not even require making inferences about the meaning of the content. You seem to be overestimating how close to practicality neural-network approaches are for most problems. Very much of the potential application space is still firmly within the domain of research. That doesn't mean what you described is completely impossible, just that you could get a PhD for…

Paper and discussion history. A mention is not an endorsement.

Image-to-Markup Generation with Coarse-to-Fine Attention — mentioned by tanilama

Fri, 26 May 2017 03:53:01 GMT

If you somewhat familiar with DL literature, you will see this paper, while having a very interesting angle, the underlying architecture is a standard, enc-dec network, with encoder being CNN and decoding being LSTM. Such application, has been studied before: https://arxiv.org/pdf/1609.04938.pdf The above paper shows nice result that turns image to latex expression, and image to html.

Paper and discussion history. A mention is not an endorsement.