Pith. sign in

REVIEW

Scene Graph based Image Retrieval -- A case study on the CLEVR Dataset

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1911.00850 v1 pith:47XOU6JZ submitted 2019-11-03 cs.AI cs.CLcs.CV

classification cs.AIcs.CLcs.CV
keywords retrievalcatalogmodelcaptiongraphimageinteractivelarge
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

With the prolification of multimodal interaction in various domains, recently there has been much interest in text based image retrieval in the computer vision community. However most of the state of the art techniques model this problem in a purely neural way, which makes it difficult to incorporate pragmatic strategies in searching a large scale catalog especially when the search requirements are insufficient and the model needs to resort to an interactive retrieval process through multiple iterations of question-answering. Motivated by this, we propose a neural-symbolic approach for a one-shot retrieval of images from a large scale catalog, given the caption description. To facilitate this, we represent the catalog and caption as scene-graphs and model the retrieval task as a learnable graph matching problem, trained end-to-end with a REINFORCE algorithm. Further, we briefly describe an extension of this pipeline to an iterative retrieval framework, based on interactive questioning and answering.

Discussion (0). Sign in to comment.

Pith tools