April 20th, 2012 @ 2:30pm Alex Berg (Stony Brook University)

Large Scale Recognition in Computer Vision

Recognition in computer vision is beginning to work – one of the hot current lines of inquiry is what we should be recognizing. Recent work – our own and others – has explored increasing the “label space” for recognition toward large numbers of semantic labels embedded in a hierarchy, toward multiple attribute labels, and toward detailed spatial parsing. Predictions of these labels are improving results on problems from face recognition to large scale similar image retrieval. At the same time there are unavoidable challenges in large scale computation that must be met. I will present some of our results in each of these directions and try to motivate some of the wide open problems in this area.

Related papers:

Hedging Your Bets: Optimizing Accuracy-Specificity Trade-offs in Large Scale Visual Recognition Jia Deng, Jonathan Krause, Alexander C. Berg, Li Fei-Fei CVPR 2012 (Providence)

DCMSVM: Distributed Parallel Training For Single-Machine Multiclass Classifiers Xufeng Han, Alexander C. Berg CVPR 2012 (Providence)

Collective Generation of Natural Image Descriptions Polina Kuznetsova, Vicente Ordonez, Alexander C. Berg, Tamara Berg Yejin Choi ACL 2012 (Jeju)

Fast and Balanced: Efficient Label Tree Learning for Large Scale Object Recognition Jia Deng, Sanjeev Satheesh, Alexander C. Berg, Li Fei-Fei Li NIPS 2011 (Granada)

Describable Visual Attributes for Face Verification and Image Search Neeraj Kumar, Alexander C. Berg, Peter N. Belhumeur, Shree K. Nayar IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), October 2011

Hierarchical Semantic Indexing for Large Scale Image Retrieval Jia Deng, Alexander C. Berg, Li Fei-Fei CVPR 2011 (Colorado Springs)

Bio:

Alex Berg's research concerns computational visual recognition. He has worked on general object recognition in images, action recognition in video, human pose identification in images, image parsing, face recognition, image search, and efficient large scale machine learning for computer vision. He is currently an assistant professor in the computer science department at Stony Brook University. Prior to that he was a research scientist at Columbia University and Yahoo! Research. His PhD at U.C. Berkeley developed a novel approach to deformable template matching. He earned a BA and MA in Mathematics from Johns Hopkins University and learned to race sailboats at SSA in Annapolis.

seminars/seminaritems/2012-04-20.txt · Last modified: 2012/04/12 11:21 by silberman