What makes Paris look like Paris?

Doersch, Carl; Singh, Saurabh; Gupta, Abhinav; Šivic, Josef; Efros, Alexei A.

doi:10.1145/2830541

Cited by 112 publications

(54 citation statements)

References 23 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Most of the existing visual location recognition methods (see [4], [8]- [16], [18], [24]- [28]) are based on image retrieval, while a few studies (see [17], [29], [30]) cast the visual localization problem as an image classification task. They all focus on visual location recognition for a global environment, such as buildings on both sides of the street in a city, symbol architecture in the world, and so on.…”

Section: A Visual Localizationmentioning

confidence: 99%

A Semi-Supervised Method for Surveillance-Based Visual Location Recognition

Liu

Yang

Wang

et al. 2017

IEEE Trans. Cybern.

View full text Add to dashboard Cite

In this paper, we are devoted to solving the problem of crossing surveillance and mobile phone visual location recognition, especially for the case that the query and reference images are captured by mobile phone and surveillance camera, respectively. Besides, we also study the influence of the environmental condition variations on this problem. To explore that problem, we first build a cross-device location recognition dataset, which includes images of 22 locations taken by mobile phones and surveillance cameras under different time and weather conditions. Then based on careful analysis of the problems existing in the data, we specifically design a method which unifies an unsupervised subspace alignment method and the semi-supervised Laplacian support vector machine. Experiments are performed on our dataset. Compared with several related methods, our method shows to be more efficient on the problem of crossing surveillance and mobile phone visual location recognition. Furthermore, the influence of several factors such as feature, time, and weather is studied.

show abstract

Section: A Visual Localizationmentioning

confidence: 99%

A Semi-Supervised Method for Surveillance-Based Visual Location Recognition

Liu

Yang

Wang

et al. 2017

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…To tackle the challenges posed by large appearance variations due to season or time of the day changes, alternative image representations proposed in [16] where authors used low resolution patches discriminative for locations. In [14] authors adopt the strategy proposed by [6] and use midlevel patches endowed by Histogram of Oriented Gradient (HOG) descriptors accompanied by per-location training procedure that determines which patches are discriminative for the location. This method assumes that many images under different imaging conditions are acquired per location.…”

Section: Related Workmentioning

confidence: 99%

Semantically guided location recognition for outdoors scenes

Mousavian¹,

Košecká²,

Lien³

2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

The problem of image based localization has a long history both in robotics and computer vision and shares many similarities with image based retrieval problem. Existing techniques use either local features or (semi)-global image signatures in the context of topological mapping or loop closure detection. Difficulties of the location recognition problem are often affected by large appearance and viewpoint variation between the query view and reference dataset and presence of non-discriminative features due to vegetation, sky and road. In this work we show that semantic segmentation labeling of man-made structures can inform the traditional bag-of-visual words models to obtain proper feature weighting and improve the overall location recognition accuracy. We also demonstrate additional capability of identifying individual buildings and estimating their extent in images, providing the essential building block for semantic localization. Towards this end we introduce a new challenging outdoors urban dataset exhibiting large variations in appearance and viewpoint.

show abstract

“…Most existing approaches for landmark classification are built upon scalable image search [11]- [16]. One of typical examples is that Philbin et al [23] propose to retrieve landmark images represented by bag-of-visual-words (BoVW) [24], where large vocabularies and fast spatial matching are leveraged.…”

Section: A Searching-based Approachmentioning

confidence: 99%

Landmark Classification With Hierarchical Multi-Modal Exemplar Feature

Zhu

Shen

Jin

et al. 2015

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Landmark image classification attracts increasing research attention due to its great importance in real applications, ranging from travel guide recommendation to 3-D modelling and visualization of geolocation. While large amount of efforts have been invested, it still remains unsolved by academia and industry. One of the key reasons is the large intra-class variance rooted from the diverse visual appearance of landmark images. Distinguished from most existing methods based on scalable image search, we approach the problem from a new perspective and model landmark classification as multi-modal categorization, which enjoys advantages of low storage overhead and high classification efficiency. Toward this goal, a novel and effective feature representation, called hierarchical multi-modal exemplar (HMME) feature, is proposed to characterize landmark images. In order to compute HMME, training images are first partitioned into the regions with hierarchical grids to generate candidate images and regions. Then, at the stage of exemplar selection, hierarchical discriminative exemplars in multiple modalities are discovered automatically via iterative boosting and latent region label mining. Finally, HMME is generated via a region-based locality-constrained linear coding (RLLC), which effectively encodes semantics of the discovered exemplars into HMME. Meanwhile, dimension reduction is applied to reduce redundant information by projecting the raw HMME into lower-dimensional space. The final HMME enjoys advantages of discriminative and linearly separable. Experimental study has been carried out on real world landmark datasets, and the results demonstrate the superior performance of the proposed approach over several state-of-the-art techniques.Index Terms-Dimension reduction, diverse visual contents, exemplar selection, hierarchical multi-modal exemplar feature (HMME), landmark classification, region-based locality-constrained linear coding (RLLC).

show abstract

What makes Paris look like Paris?

Cited by 112 publications

References 23 publications

A Semi-Supervised Method for Surveillance-Based Visual Location Recognition

A Semi-Supervised Method for Surveillance-Based Visual Location Recognition

Semantically guided location recognition for outdoors scenes

Landmark Classification With Hierarchical Multi-Modal Exemplar Feature

Contact Info

Product

Resources

About