MétaCan
← all works

Learning to Relate Images

2013· review· en· 93 citations· W1970819022 on OpenAlex· 10.1109/tpami.2013.53

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian affiliationAn author listed a Canadian institution. This is the only route the usual frame has.

The three-model screen

all 1,000 screened works →

All three models called this out of scope.

stratum: aff_core · design weight: 5595.24 (the sample is stratified; any rate computed without the weight is wrong)
Claude Opus 4.8OUT
genre: conceptual
about Canada: no
confidence: high

Review of relational deep-learning methods for image correspondence; a machine-learning methods contribution in its own domain.

GPT-5.6 (high)OUT
genre: conceptual
about Canada: no
confidence: high

This reviews machine-learning methods for image relations, not methods or practices of research.

Grok 4.5OUT
genre: conceptual
about Canada: no
confidence: high

Computer-vision methods review on learning image correspondences; domain ML/vision, not metaresearch.

Abstract

A fundamental operation in many vision tasks, including motion understanding, stereopsis, visual odometry, or invariant recognition, is establishing correspondences between images or between images and data from other modalities. Recently, there has been increasing interest in learning to infer correspondences from data using relational, spatiotemporal, and bilinear variants of deep learning methods. These methods use multiplicative interactions between pixels or between features to represent correlation patterns across multiple images. In this paper, we review the recent work on relational feature learning, and we provide an analysis of the role that multiplicative interactions play in learning to encode relations. We also discuss how square-pooling and complex cell models can be viewed as a way to represent multiplicative interactions and thereby as a way to encode relations.

Stored with the screening record, where it is evidence for the labels above.

The record

Venue
IEEE Transactions on Pattern Analysis and Machine Intelligence
Topic
Cell Image Analysis Techniques
Field
Biochemistry, Genetics and Molecular Biology
Canadian institutions
Université de Montréal
Funders
Keywords
ENCODEArtificial intelligenceComputer sciencePoolingFeature (linguistics)Pattern recognition (psychology)ModalitiesMultiplicative functionBilinear interpolationDeep learningComputer visionMachine learningMathematics
Has abstract in OpenAlex
yes