O
Omkar M. Parkhi
Researcher at University of Oxford
Publications - 28
Citations - 10082
Omkar M. Parkhi is an academic researcher from University of Oxford. The author has contributed to research in topics: Facial recognition system & TRECVID. The author has an hindex of 16, co-authored 25 publications receiving 7648 citations. Previous affiliations of Omkar M. Parkhi include Facebook & International Institute of Information Technology, Hyderabad.
Papers
More filters
Proceedings ArticleDOI
Total Cluster: A person agnostic clustering method for broadcast videos
Makarand Tapaswi,Omkar M. Parkhi,Esa Rahtu,Eric Sommerlade,Rainer Stiefelhagen,Andrew Zisserman +5 more
TL;DR: The extent to which faces can be clustered automatically without making an error is explored, and an extension of the clustering method to entire episodes using exemplar SVMs based on the negative training data automatically harvested from the editing structure is proposed.
Proceedings ArticleDOI
On-the-fly specific person retrieval
TL;DR: A method of visual search for finding people in large video datasets that can be specified at run time by a text query, and a discriminative classifier for that person is then learnt on-the-fly using images downloaded from Google Image search.
AXES at TRECVid 2012: KIS, INS, and MED
Robin Aly,Kevin McGuinness,Shu Chen,Noel E. O'Connor,Ken Chatfield,Omkar M. Parkhi,Relja Arandjelovic,Andrew Zisserman,Basura Fernando,Tinne Tuytelaars,Dan Oneata,Matthijs Douze,Jerome Revaud,Jochen Schwenninger,Danila Potapov,Heng Wang,Zaid Harchaoui,Jakob Verbeek,Cordelia Schmid +18 more
TL;DR: The AXES project participated in the interactive instance search task (INS), the known-item search task, and the multimedia event detection task (MED) for TRECVid 2012 as mentioned in this paper.
The AXES submissions at TrecVid 2013
Robin Aly,Relja Arandjelovic,Ken Chatfield,Matthijs Douze,Basura Fernando,Zaid Harchaoui,Kevin Mcguiness,Noel E. O'Connor,Dan Oneata,Omkar M. Parkhi,Danila Potapov,Jerome Revaud,Cordelia Schmid,Jochen Schwenninger,David Scott,Tinne Tuytelaars,Jakob Verbeek,Heng Wang,Andrew Zisserman +18 more
TL;DR: The authors' INS, MER, and MED systems, which use systems based on state-of-the-art local low-level descriptors for motion, image, and sound, as well as high-level features to capture speech and text and the visual and audio stream respectively, are described.
Proceedings ArticleDOI
GrokNet: Unified Computer Vision Model Trunk and Embeddings For Commerce
Sean Bell,Yiqun Liu,Sami Alsheikh,Yina Tang,Edward Pizzi,M. Henning,Karun Singh,Omkar M. Parkhi,Fedor Vladimirovich Borisyuk +8 more
TL;DR: GrekNet leverages a multi-task learning approach to train a single computer vision trunk, achieving a 2.1x improvement in exact product match accuracy when compared to the previous state-of-the-art Facebook product recognition system.