TY  - BOOK
AU  - Felzenszwalb,P.F.
AU  - Girshick,R.B.
AU  - Mcallester,D.
AU  - Ramanan,D.
TI  - Object detection with discriminatively trained part-based models
KW  - DATA SETS
KW  - DEFORMABLE MODELS
KW  - DISCRIMINATIVE TRAINING
KW  - LABELED DATA
KW  - LATENT INFORMATION
KW  - LATENT VALUE
KW  - LATENT VARIABLE
KW  - MULTISCALES
KW  - NEGATIVE EXAMPLES
KW  - OBJECT CLASS
KW  - OBJECT DETECTION
KW  - OBJECT DETECTION SYSTEMS
KW  - OBJECTIVE FUNCTIONS
KW  - PICTORIAL STRUCTURES
KW  - POSITIVE EXAMPLES
N2  - We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL data sets. Our system relies on new methods for discriminative training with partially labeled data. We combine a margin-sensitive approach for data-mining hard negative examples with a formalism we call latent SVM. A latent SVM is a reformulation of MI-SVM in terms of latent variables. A latent SVM is semiconvex, and the training problem becomes convex once latent information is specified for the positive examples. This leads to an iterative training algorithm that alternates between fixing latent values for positive examples and optimizing the latent SVM objective function
UR  - https://drive.google.com/file/d/1ToXQgJa4IsOSudxz-w0FAsUW0sZHb6HC/view?usp=drivesdk
ER  -