Junction Dataset


 

1. Data fact

Video length: 1 hour (90000 frames)
Frame size: 360x288
Frame rate: 25 Hz
Compression codec: ffdshow mpeg-4

2. Download 

This video can be download here.

3. Author

David Russell, School of Elentronic Engineering and Computer Science, Queen Mary University of London.

4. References

[1] T. Hospedales, S. Gong and T. Xiang, Video Behaviour Mining Using A Dynamic Topic Model, International Journal of Computer Vision (IJCV), Vol. 98, No. 3, pp. 303-323, July 2012.

[2] J. Li, S. Gong and T. Xiang, Learning Behavioural Context, International Journal of Computer Vision (IJCV), Vol. 97, No. 3, pp. 276-304, May 2012.

[3] T. Hospedales, S. Gong and T. Xiang, A Markov Clustering Topic Model for Mining Behaviour in Video, Internatioanl Conference on Computer Vision (ICCV), Kyoto, Japan, September 2009.

[4] J. Li, S. Gong and T. Xiang, Scene Segmentation for Behaviour Correlation, European Conference on Computer Vision (ECCV), Marseille, France, October 2008.

[5] D. Russell and S. Gong, Multi-Layered Decomposition of Recurrent Scenes, European Conference on Computer Vision (ECCV), Marseille, France, October 2008.

[6] J. Li, S. Gong and T. Xiang, Global Behaviour Inference using Probabilistic Latent Semantic Analysis, British Machine Vision Conference (BMVC), Leeds, UK, September 2008.

[7] D. Russell and S. Gong, Exploiting Periodicity in Recurrent Scenes, British Machine Vision Conference (BMVC), Leeds, UK, September 2008.

[8] C. Loy, T. Xiang and S. Gong, From Local Temporal Correlation to Global Anomaly Detection, International Workshop on Machine Learning for Vision-based Motion Analysis, Marseille, France, October 2008.