Find Us On:

Linked In


Join Our Mailing List


We won't spam you or ever share your information.

Jagannadan Varadarajan

Profile Text
Jagannadan Varadarajan
Former Research Scientist

Jagan Varadarajan is a former Research Scientist at ADSC, Illinois at Singapore Pt Ltd, Singapore. His research work focused on higher level semantic understanding of sports videos. At ADSC, he collaborates with Prof. Narendra Ahuja, Dr. Indriyati Atmosukarto, Dr. Bernard Ghanem, Dr. Tianzhu Zhang and Shaunak Ahuja. He completed his Ph.D at the Ecole Polytechnique Federal de Lausanne, Lausanne, Switzerland (EPFL*), and Idiap Research Institute, Switzerland. His thesis work was done under the supervision of Dr. Jean-Marc Odobez.

Research Interests: Video analysis, Data mining, Graphical models, Bayesian Inference, Machine learning, Computer vision and Image processing

ADSC Project:

Semantic Analysis of Video


Previously, he received his B.Sc (Mathematics) in 2001, M.Sc (Mathematics) in 2003 and M.Tech in Computer Science in 2005 from Sri Sathya Sai University, Prasanthi Nilayam, AP, India. Subsequently, he worked as a Scientist at HP Labs, Bangalore from July 2005 to June 2007 and GE Global Research, Bangalore until June 2008.  



  • A Sequential Topic Model for Mining Recurrent Activities from Long Term Video Logs [PDF] [Additional material]
    Jagannadan Varadarajan, Remi Emonet and Jean-Marc Odobez 
    Accepted in International Journal of Computer Vision (IJCV)


  • Bridging the Past, Present and Future: Modeling Scene Activities From Event Relationships and Global Rules[PDF][Additional material][Poster] 
    Jagannadan Varadarajan, Remi Emonet and Jean-Marc Odobez 
    IEEE Computer Vision and Pattern Recognition (CVPR), 2012
  • Multi-camera Open Space Human Activity Discovery for Anomaly Detection [PDF] 
    Remi Emonet, Jagannadan Varadarajan and Jean-Marc Odobez 
    IEEE Conference on Advanced Video and Signal-Based Surveillance (AVSS)
  • Extracting and Locating Temporal Motifs in Video Scenes Using a Hierarchical Non Parametric Bayesian Model.[PDF] 
    Remi Emonet, Jagannadan Varadarajan and Jean-Marc Odobez 
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011
  • A Sparsity Constraint for Topic Models - Application to Temporal Activity Mining [PDF] 
    Jagannadan Varadarajan, Remi Emonet and Jean-Marc Odobez, 
    NIPS 2010, Workshop on Practical Applications of Sparse Modeling: Open Issues and New Directions, 2010
  • Probablistic Latent Sequential Motifs: Discovering sequential patterns in video scenes[PDF] 
    Jagannadan Varadarajan, Remi Emonet and Jean-Marc Odobez 
    British Machine Vision Conference (BMVC), 2010
  • Topic models for Scene Analysis and Abnormality Detection.[PDF] 
    Jagannadan Varadarajan and Jean-Marc Odobez 
    ICCV 12th International Workshop on Visual Surveillance, 2009.
  • Digital ink to Form Alignment for Electronic Clipboard devices.[PDF] 
    Jagannadan Varadarajan and Sriganesh Madhvanath 
    IAPR International workshop on Document Analysis Systems (DAS), 2008
  • Evaluating Motion Correction in Respiratory-Gated PET for Solitory Pulmonary Nodules: Qualitative and Quantitative Methods. 
    Girishankar Gopalakrishnan, Kris Thielemans, Jagannadan Varadarajan, Rakesh Mullick, et al. 
    World Molecular Imaging Congress, 2008
  • Edge and corner detection in grayscale and color images using first Fourier basis. 
    M.C. Prakash, Jagannadan Varadarajan, GV Prabhakar Rao, R.Raghunatha Sarma. 
    Proc. SPIE Vol. 6006, 2005.
  • Feature Extraction and Image Registration of Color Images using Fourier Bases[PDF] 
    Jagannadan Varadarajan, M.C. Prakash, R.Raghunatha Sarma, GV Prabhakar Rao. 
    IEEE International Conference on Image Processing (ICIP), 2005.


  • System and Method for Computerized Searching with a Community Perspective 
    Vineel Chandrakanth Gujjar, Steven Matt Gustafson, Samit Paul, Babu Ozhur Narayan, Jagannadan Varadarajan 
    GE Global Research, Bangalore