MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015
-
Upload
multimediaeval -
Category
Education
-
view
160 -
download
4
Transcript of MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015
![Page 1: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/1.jpg)
CERTH/CEA LIST at MediaEval Placing Task 2015 Giorgos Kordopatis-Zilos1, Adrian Popescu2, Symeon Papadopoulos1 and Yiannis Kompatsiaris1
1 Information Technologies Institute (ITI), CERTH, Greece
2 CEA LIST, 91190 Gif-sur-Yvette, France
MediaEval 2015 Workshop, Sept. 14-15, 2015, Wurzen, Germany
![Page 2: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/2.jpg)
Summary
#2
Tag-based location estimation (2 runs) • Based on a geographic Language Model • Built upon the scheme of our 2014 participation [2] (Kordopatis-Zilos et
al., MediaEval 2014) • Extensions from [3]: improved feature selection and weighting
(Kordopatis-Zilos et al., PAISI 2015)
Visual-based location estimation (1 run) • Geospatial clustering scheme of the most visually similar images
Hybrid location estimation (2 run) • Combination of the textual and visual approaches
Training sets • Training set released by the organisers (≈4.7M geotagged items) • YFCC dataset, excl. images from users in test set (≈40M geotagged items)
![Page 3: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/3.jpg)
Tag-based location estimation
#3
• Processing steps of the approach – Offline: language model construction – Online: location estimation
![Page 4: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/4.jpg)
Language Model (LM)
#4
![Page 5: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/5.jpg)
Feature Selection and Weighting
#5
accuracy locality
![Page 6: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/6.jpg)
Accuracy
#6
Estimated
Locations
![Page 7: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/7.jpg)
Locality
#7
![Page 8: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/8.jpg)
Locality – value distribution
#8
london (6975), paris (5452), nyc (3917)
luminancehdr (0.0035), dsc6362 (0.003), air photo (0.002)
![Page 9: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/9.jpg)
Extensions
• Spatial Entropy (SE) function – calculate entropy values applying the Shannon entropy formula in the tag-cell
probabilities – build a Gaussian weight function based on the values of the tag SE
#9
• Internal Grid – Built an additional LM using a finer grid, cell side length of 0.001° – combine the MLC of the individual language models
![Page 10: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/10.jpg)
Visual-based location estimation
#10
![Page 11: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/11.jpg)
Hybrid-based location estimation
#11
![Page 12: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/12.jpg)
Confidence
#12
![Page 13: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/13.jpg)
Runs and Results
#13
measure RUN-1 RUN-2 RUN-3 RUN-4 RUN-5
acc(1m) 0.15 0.01 0.15 0.16 0.16
acc(10m) 0.61 0.08 0.62 0.75 0.76
acc(100m) 6.40 1.76 6.52 7.73 7.83
acc(1km) 24.33 5.19 24.61 27.30 27.54
acc(10km) 43.07 7.43 43.41 46.48 46.77
m. error (km) 69 5663 61 24 22
RUN-1: Tag-based location estimation + released training set
RUN-2: Visual-based location estimation + released training set
RUN-3: Hybrid location estimation + released training set
RUN-4: Tag-based location estimation + YFCC dataset
RUN-5: Hybrid location estimation + YFCC dataset
![Page 14: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/14.jpg)
Thank you!
• Code:
https://github.com/MKLab-ITI/multimedia-geotagging
• Get in touch:
@sympapadopoulos / [email protected]
@georgekordopatis / [email protected]
#14
![Page 15: MediaEval 2015 - CERTH/CEA LIST at MediaEval Placing Task 2015](https://reader031.fdocuments.in/reader031/viewer/2022021506/58a1ab6d1a28abe6468b646b/html5/thumbnails/15.jpg)
References
#15
[1] Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, and T. Darrell. Caffe: Convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093, 2014.
[2] G. Kordopatis-Zilos, G. Orfanidis, S. Papadopoulos, and Y. Kompatsiaris. Socialsensor at mediaeval placing task 2014. In MediaEval 2014 Placing Task, 2014.
[3] G. Kordopatis-Zilos, S. Papadopoulos, and Y. Kompatsiaris. Geotagging social media content with a refined language modelling approach. In Intelligence and Security Informatics, pages 21–40, 2015.
[4] A. Popescu. CEA LIST's participation at mediaeval 2013 placing task. In MediaEval 2013 Placing Task, 2013.
[5] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations, 2015.
[6] O. Van Laere, S. Schockaert, and B. Dhoedt. Finding locations of Flickr resources using language models and similarity search. ICMR ’11, pages 48:1–48:8, New York, NY, USA, 2011. ACM.