Vidit Jain [ vidit -AT- cs -DOT- umass -DOT- edu ] I am a PhD student in the Computer Vision Laboratory at The University of Massachusetts Amherst. My adviser is Prof. Erik Learned-Miller. I am interested in developing machine learning solutions for computer vision problems. My dissertation research focuses on developing data-driven, probabilistic models for context-aware face detection and recognition. My other research interests include information extraction and information retrieval. I am graduating soon and currently looking for a job. My application materials can be found here. CV: [Brief] [Detailed], [Research Statement], and [Teaching Statement].

I have been very fortunate to be affiliated with these wonderful institutions and have the following great mentors:

1998-2002	2001	2002-04	2006	2007	2009	2004-
[College] Manindra Agrawal A. Mukerjee (Discrete Math, AI)	[Intern] Jop Sibeyn (Parallel Algo)	[Technical Lead] Tom Binford (Handwriting Recognition)	[Intern] M. Narasimhan Paul Viola (Information Extraction)	[Intern] A. Singhal Jiebo Luo (Event Classificaton)	[Intern] Manik Varma (Ranking for Image Search)	[Grad School] E. Learned-Miller Allen Hanson James Allan Andrew McCallum (Vision, ML, IR)

My full list of publication is available. Here are a few highlights:

• V Jain, A Singhal, J Luo. Selective Hidden Random Fields: Exploiting Domain Specific Saliency for Event Classification. CVPR 2008.
• V Jain, E Learned-Miller, A McCallum. People-LDA: Anchoring Topics to People using Face Recognition. ICCV 2007.
• G B Huang, V Jain, E Learned-Miller. Unsupervised Joint Alignment of Complex Images. ICCV 2007.
• V Jain, A Ferencz, E Learned-Miller. Discriminative Training of Hyper-feature Models for Object Identification. BMVC 2006.

I organize my research notes and general observations about computer vision and machine learning on my blog titled "Learning in Vision."