Pith. sign in

REVIEW

An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information

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 2104.02605 v1 pith:IUJFID5N submitted 2021-03-21 cs.CV cs.AIcs.MM

classification cs.CVcs.AIcs.MM
keywords approachbiasdocumentimage-sentencepositivesamplingalleviatedocument-level
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach achieves positive results, it introduces a sampling bias and fails to distinguish instances with high semantic similarity. To alleviate the bias, we propose a new sampling strategy to select additional intra-document image-sentence pairs as positive or negative samples. Furthermore, to recognize the complex pattern in intra-document samples, we propose a Transformer based model to capture fine-grained features and implicitly construct a graph for each document, where concepts in a document are introduced to bridge the representation learning of images and sentences in the context of a document. Experimental results show the effectiveness of our approach to alleviate the bias and learn well-aligned multimodal representations.

Discussion (0). Sign in to comment.

Pith tools