Video Retrieval by Mimicking Poses

Nataraj Jammalamadaka, Andrew Zisserman, Marcin Eichner, Vittorio Ferrari, C. V. Jawahar

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We describe a method for real time video retrieval where the task is to match the 2D human pose of a query. A user can form a query by (i) interactively controlling a stickman on a web based GUI, (ii) uploading an image of the desired pose, or (iii) using the Kinect and acting out the query himself. The method is scalable and is applied to a dataset of 18 films totaling more than three million frames. The real time performance is achieved by searching for approximate nearest neighbors to the query using a random forest of K-D trees. Apart from the query modalities, we introduce two other areas of novelty. First, we show that pose retrieval can proceed using a low dimensional representation. Second, we show that the precision of the results can be improved substantially by combining the outputs of independent human pose estimation algorithms. The performance of the system is assessed quantitatively over a range of pose queries
Original languageEnglish
Title of host publicationProceedings of the 2Nd ACM International Conference on Multimedia Retrieval
Place of PublicationNew York, NY, USA
Number of pages9
Publication statusPublished - 2012

Publication series

NameICMR '12


  • human pose search, video processing


Dive into the research topics of 'Video Retrieval by Mimicking Poses'. Together they form a unique fingerprint.

Cite this