3rd Place Solution to Google Landmark Recognition Competition 2021

Xu, Chuanzhi; Wang, Weimin; Liu, Shuai; Wang, Yong; Tang, Yajuan; Bian, Tianling; Yan, Yanyu; She, Qi; Yang, Cheng

doi:10.48550/arxiv.2110.02794

Cited by 1 publication

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The task can be implemented using either classification or matching approaches. Recent classification approaches [8,54] use deep architectures such as EfficientNet [46] or visual transformers [27], in isolation or ensembled, to automatically label POIs in images. This process is fast since it only requires an inference for test images.…”

Section: Related Workmentioning

confidence: 99%

Vis2Rec: A Large-Scale Visual Dataset for Visit Recommendation

Soumm¹,

Popescu²,

Delezoide

2023

2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Most recommendation datasets for tourism are restricted to one world region and rely on explicit data such as checkins. However, in reality, tourists visit various places worldwide and document their trips primarily through photos. These images contain a wealth of raw information that can be used to capture users' preferences and recommend personalized content. Visual content was already used in past works, but no large-scale publicly-available dataset that gives access to users' personal images exists for recommender systems. As such a resource would open-up possibilities for new image-based recommendation algorithms, we introduce Vis2Rec, a new dataset based on visit data extracted from users' Flickr photographic streams, which includes over 7 million photos, 36k recognizable points of interest, and 14k user profiles. Google Landmarks v2 is used as an auxiliary dataset to identify points of interest in users' photos, using a state-of-the-art image-matching deep architecture. Image-based user profiles are then constituted by aggregating the points of interest detected for each user. In addition, ground truth visits were determined for the test subset in order to enable accurate evaluation. Finally, we benchmark Vis2Rec using various existing recommender systems, and discuss the possibilities opened up by the availability of user images, as well as the societal issues that come with them. Following good practice in dataset sharing, Vis2Rec is created using only freely distributable content, and additional anonymization is performed to ensure the privacy of users. The raw dataset and the preprocessed user profiles will be publicly available at https://github.com/MSoumm/Vis2Rec.

show abstract

Section: Related Workmentioning

confidence: 99%