Clues from the beaten path: Location estimation with bursty sequences of tourist photos

Chen, Chao-Yeh; Grauman, Kristen

doi:10.1109/cvpr.2011.5995412

Cited by 28 publications

(19 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most relevant to our work are methods that exploit the biases of human photographers. This includes work on discovering iconic images of landmarks [36,24,41] (e.g., the Statue of Liberty) or other tourist favorites [12,17,1,20] by exploiting the fact that people tend to take similar photos of popular sites. Similarly, the photos users upload when trying to sell a particular object (e.g., a used car) reveal that object's canonical viewpoints, which can help select keyframes to summarize short videos of the same object [19].…”

Section: Related Workmentioning

confidence: 99%

Detecting Snap Points in Egocentric Video with a Web Photo Prior

Xiong

Grauman

2014

Computer Vision – ECCV 2014

Self Cite

View full text Add to dashboard Cite

Abstract. Wearable cameras capture a first-person view of the world, and offer a hands-free way to record daily experiences or special events. Yet, not every frame is worthy of being captured and stored. We propose to automatically predict "snap points" in unedited egocentric videothat is, those frames that look like they could have been intentionally taken photos. We develop a generative model for snap points that relies on a Web photo prior together with domain-adapted features. Critically, our approach avoids strong assumptions about the particular content of snap points, focusing instead on their composition. Using 17 hours of egocentric video from both human and mobile robot camera wearers, we show that the approach accurately isolates those frames that human judges would believe to be intentionally snapped photos. In addition, we demonstrate the utility of snap point detection for improving object detection and keyframe selection in egocentric video.

show abstract

Section: Related Workmentioning

confidence: 99%

Detecting Snap Points in Egocentric Video with a Web Photo Prior

Xiong

Grauman

2014

Computer Vision – ECCV 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another thread of related research is to explore the collections of landmark photos taken by tourists. In this line of work, the storylines are implicitly implemented in geometric ways such as 3D models of landmarks [21] or tourists' paths [2,7]. Our work differs in that we aim at building storyline graphs of general topics in which no geometric constraints are available (such as fly+fishing).…”

Section: Introductionmentioning

confidence: 99%

Reconstructing Storyline Graphs for Image Recommendation from Web Community Photos

Kim

Xing

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

In this paper, we investigate an approach for reconstructing storyline graphs from large-scale collections of Internet images, and optionally other side information such as friendship graphs. The storyline graphs can be an effective summary that visualizes various branching narrative structure of events or activities recurring across the input photo sets of a topic class. In order to explore further the usefulness of the storyline graphs, we leverage them to perform the image sequential prediction tasks, from which photo recommendation applications can benefit. We formulate the storyline reconstruction problem as an inference of sparse time-varying directed graphs, and develop an optimization algorithm that successfully addresses a number of key challenges of Web-scale problems, including global optimality, linear complexity, and easy parallelization. With experiments on more than 3.3 millions of images of 24 classes and user studies via Amazon Mechanical Turk, we show that the proposed algorithm improves other candidate methods for both storyline reconstruction and image prediction tasks.

show abstract

“…This model captures the heavy-tailed nature of travel, but ignores the actual locations being visited. Second, one can build probability tables based on empirical travel histograms [4,6,9,10,15,16]. Such models are more accurate than simple stochastic process models, but require enormous datasets while revealing little about the underlying structure of the data.…”

Section: Introductionmentioning

confidence: 99%

“…Destinations that are equidistant from one's current location are equally likely, regardless of whether they are in New York City or in the Arctic. Second, one can build probability tables based on empirical travel histograms [4,6,9,10,15,16]. For example, Kalogerakis et al [16] use counts of actual transitions in a database of 6 million travel records.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, tools for analysis and prediction of movement can be useful for numerous applications. For example, travel models can help in predicting the spread of disease [6,15]; surveying tourism [9,10], traffic [2,14], and special events mobility for urban planning [3]; geolocating with computer vision [4,16]; interpreting activity from movements [19,22]; and recommending travel [7,17]. Analysis of travel data can also play a role within the larger context of analysis of social network data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning Latent Factor Models of Travel Data for Travel Prediction and Analysis

Guerzhoy

Hertzmann

2014

Advances in Artificial Intelligence

View full text Add to dashboard Cite

Abstract. We describe latent factor probability models of human travel, which we learn from data. The latent factors represent interpretable properties: travel distance cost, desirability of destinations, and affinity between locations. Individuals are clustered into distinct styles of travel. The latent factors combine in a multiplicative manner, and are learned using Maximum Likelihood. We show that our models explain the data significantly better than histogrambased methods. We also visualize the model parameters to show information about travelers and travel patterns. We show that different individuals exhibit different propensity to travel large distances. We extract the desirability of destinations on the map, which is distinct from their popularity. We show that pairs of locations have different affinities with each other, and that these affinities are partly explained by travelers' preference for staying within national borders and within the borders of linguistic areas. The method is demonstrated on two sources of travel data: geotags from Flickr images, and GPS tracks from Shanghai taxis.

show abstract

Clues from the beaten path: Location estimation with bursty sequences of tourist photos

Abstract: Abstract

Cited by 28 publications

References 21 publications

Detecting Snap Points in Egocentric Video with a Web Photo Prior

Detecting Snap Points in Egocentric Video with a Web Photo Prior

Reconstructing Storyline Graphs for Image Recommendation from Web Community Photos

Learning Latent Factor Models of Travel Data for Travel Prediction and Analysis

Contact Info

Product

Resources

About