Anaba: An obscure sightseeing spots discovering system

2016 IEEE Second International Conference on Multimedia Big Data (BigMM)

et al. 2016

Self Cite

Recommending points of interests (POIs) is drawing more attention to meet the growing demand for tours. A POI's quality (sightseeing value) estimation is one of the important challenges. In contrast to conventional studies of ranking POIs based on user behavior analysis, in this paper, we propose methods of quality estimation by analyzing geo-social images. Our approach estimates the sightseeing value from two aspects: (1) nature value; and (2) culture value. For the nature value, we extract image features that are related to favorable human perception to verify whether a POI would meet tourists' psychological requirements. Three criteria, coherence, imageability and visual-scale, are defined accordingly. For the culture value, we recognize the cultural elements (i.e., architectures) included in a POI. In the experiments, by applying our methods on the real discovered POIs, we present the effect of our approach.

“…1. Two dimensions to describe a POI proposed in [7]. authority based analysis, which is used to recommend popular POIs, is not useful.…”

Section: Zoom Inmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Sightseeing Value Estimation by Analyzing Geosocial Images

Shen

Min

2016 IEEE Second International Conference on Multimedia Big Data (BigMM)

et al. 2016

Self Cite

“…By dividing sightseeing spots into four quadrants on the basis of their "popularity" and "sightseeing quality", we are trying to discover the obscure ones [6]. Located in the quadrant with high sightseeing quality but low popularity, an obscure sightseeing location is a considerable choice for in-depth travel to not only enjoy the beautiful scenery but also experience local culture, especially for the repeat tourists who have already visited the most famous places there.…”

Section: Introductionmentioning

confidence: 99%

Discovering Obscure Sightseeing Spots by Analysis of Geo-tagged Social Images

Proceedings of the 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining 2015

Liang

et al. 2015

Self Cite

In contrast to conventional studies of discovering hot spots, by analyzing geo-tagged images on Flickr, we introduce novel methods to discover obscure sightseeing spots that are less well-known while still worth visiting. To this end, we face two new challenges that the classical authority analysis based methods do not encounter: how to discover and rank spots on the basis of 1) popularity (obscurity level) and 2) scenery quality. For the first challenge, we estimate the obscurity level of a spot in accordance with the visiting asymmetry between photographers who are familiar with a target city and those who are not. For the second challenge, the behavior of both viewers who browsed the images and photographers are analyzed per each spot. We also develop an application system to help users to explore sightseeing spots with different geographical granularities. Experimental evaluations and analysis on a real dataset well demonstrate the effectiveness of the proposed methods.

“…However, to the best of our knowledge, how to estimate a user's location familiarity by analyzing geo-tagged images has not yet been well studied. In [15], we are trying to develop a sightseeing recommendation system by dividing sightseeing spots into four quadrants on the basis of their "popularity" and "sightseeing quality". We have verified that the location familiarity is essential for discovering the obscure spots.…”

Section: Introductionmentioning

confidence: 99%

Location familiarity based flickr photographer classification for POI mining

Proceedings of the 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems

Yoshikawa

2015

Self Cite

In this paper, we propose and compare three ways of modeling photographers' location familiarity: a social network driven model, a time driven model and a location driven model. Then, the integration of the three models is further discussed. Experimental evaluations and analysis on a real data set consisting of 14,112 images collected from three cities well demonstrate the performance of the proposed classification methods. Many applications could benefit from information about the location familiarity, such as personalized geo-social recommendation, epidemic dispersion, urban computing, and so on.