Xinchao Li

Pairwise geometric matching for large-scale object retrieval

Spatial verification is a key step in boosting the performance of object-based image retrieval. It serves to eliminate unreliable correspondences between salient points in a given pair of images, and is typically performed by analyzing the consistency of spatial transformations between the image regions involved in individual correspondences. In this paper, we consider the pairwise geometric relations between correspondences and propose a strategy to incorporate these relations at significantly reduced computational cost, which makes it suitable for large-scale object retrieval. In addition, we combine the information on geometric relations from both the individual correspondences and pairs of correspondences to further improve the verification accuracy. Experimental results on three reference datasets show that the proposed approach results in a substantial performance improvement compared to the existing methods, without making concessions regarding computational efficiency.

Global-Scale Location Prediction for Social Images Using Geo-Visual Ranking

We propose an automatic method that addresses the challenge of predicting the geo-location of social images using only the visual content of those images. Our method is able to generate a geo-location prediction for an image globally . In this respect, it contrasts with other existing approaches, specifically with those that generate predictions restricted to specific cities, landmarks, or an otherwise pre-defined set of locations. The essence and the main novelty of our ranking-based method is that for a given query image a geo-location is recommended based on the evidence collected from images that are not only geographically close to this geo-location, but also have sufficient visual similarity to the query image within the considered image collection. Our method is evaluated experimentally on a public dataset of 8.8 million geo-tagged images from Flickr, released by the MediaEval 2013 evaluation benchmark. Experiments show that the proposed method delivers a substantial performance improvement compared to the existing related approaches, particularly for queries with high numbers of neighbors . In addition, a detailed analysis of the methods performance reveals the impact of different visual feature extraction and image matching strategies, as well as the densities and types of images found at different locations, on the prediction accuracy.

Geo-Distinctive Visual Element Matching for Location Estimation of Images

We propose an image representation and matching approach that substantially improves visual-based location estimation for images. The main novelty of the approach, called distinctive visual element matching (DVEM), is its use of representations that are specific to the query image whose location is being predicted. These representations are based on visual element clouds, which robustly capture the connection between the query and visual evidence from candidate locations. We then maximize the influence of visual elements that are geo-distinctive because they do not occur in images taken at many other locations. We carry out experiments and analysis for both geo-constrained and geo-unconstrained location estimation cases using two large-scale, publicly available datasets: the San Francisco Landmark dataset with 1.06 million street-view images and the MediaEval’15 Placing Task dataset with 5.6 million geo-tagged images from Flickr. We present examples that illustrate the highly transparent mechanics of the approach, which are based on commonsense observations about the visual patterns in image collections. Our results show that the proposed method delivers a considerable performance improvement compared to the state-of-the-art.

Simple tag-based subclass representations for visually-varied image classes

In this paper, we present a subclass-representation approach that predicts the probability of a social image belonging to one particular class. We explore the co-occurrence of user-contributed tags to find subclasses with a strong connection to the top level class. We then project each image onto the resulting subclass space, generating a subclass representation for the image. The advantage of our tag-based subclasses is that they have a chance of being more visually stable and easier to model than top-level classes. Our contribution is to demonstrate that a simple and inexpensive method for generating sub-class representations has the ability to improve classification results in the case of tag classes that are visually highly heterogenous. The approach is evaluated on a set of 1 million photos with 10 top-level classes, from the dataset released by the ACM Multimedia 2013 Yahoo! Large-scale Flickr-tag Image Classification Grand Challenge. Experiments show that the proposed system delivers sound performance for visually diverse classes compared with methods that directly model top classes.