Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval 2013
DOI: 10.1145/2484028.2484160
|View full text |Cite
|
Sign up to set email alerts
|

On contextual photo tag recommendation

Abstract: Image tagging is a growing application on social media websites, however, the performance of many auto-tagging methods are often poor. Recent work has exploited an image's context (e.g. time and location) in the tag recommendation process, where tags which co-occur highly within a given time interval or geographical area are promoted. These models, however, fail to address how and when different image contexts can be combined. In this paper, we propose a weighted tag recommendation model, building on an existi… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2014
2014
2023
2023

Publication Types

Select...
4
4
1

Relationship

2
7

Authors

Journals

citations
Cited by 10 publications
(6 citation statements)
references
References 9 publications
0
6
0
Order By: Relevance
“…time and location) has been exploited for tag recommendation and visualisation purposes: Zhang et al [23] cluster tags based on geolocation and temporal trends allowing for the construction of tag cluster visualisations. McParlane et al [2] exploit the daily, monthly and yearly trends of tags for tag recommendation purposes.…”
Section: Image Context and Contentsmentioning
confidence: 99%
“…time and location) has been exploited for tag recommendation and visualisation purposes: Zhang et al [23] cluster tags based on geolocation and temporal trends allowing for the construction of tag cluster visualisations. McParlane et al [2] exploit the daily, monthly and yearly trends of tags for tag recommendation purposes.…”
Section: Image Context and Contentsmentioning
confidence: 99%
“…Individual user tagging history has been studied before with application to Factorization Machines in [47]. Alternatively, [48] used the tagging history data corresponding to the image location and time. Further, the role of context has been explored in [49] and [50], these works are mainly focused on single tag prediction [49] and are trained on smaller datasets with a small set of lab curated labels [50].…”
Section: Related Workmentioning
confidence: 99%
“…In McParlane et al [2013b], time-constrained tag co-occurrence statistics are considered to refine the output of visual classifiers for tag assignment. In their follow-up work [McParlane et al 2013a], location-constrained tag co-occurrence computed from images Johnson et al [2015], social network metadata such as image groups membership or contacts of users is employed to resolve ambiguity in visual appearance. Comparing the three groups, tag + image appears to be the mainstream, as evidenced by the imbalanced distribution in Table I.…”
Section: Media For Tag Relevancementioning
confidence: 99%