Object detection with discriminatively trained part-based models (Record no. 50316)

MARC details
000 -LEADER
fixed length control field 02215nam a2200397Ia 4500
003 - CONTROL NUMBER IDENTIFIER
control field MX-MdCICY
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20250625160145.0
040 ## - CATALOGING SOURCE
Transcribing agency CICY
090 ## - LOCALLY ASSIGNED LC-TYPE CALL NUMBER (OCLC); LOCAL CALL NUMBER (RLIN)
Classification number (OCLC) (R) ; Classification number, CALL (RLIN) (NR) B-16142
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 250602s9999 xx |||||s2 |||| ||und|d
245 10 - TITLE STATEMENT
Title Object detection with discriminatively trained part-based models
490 0# - SERIES STATEMENT
Volume/sequential designation IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9), p.1627-1645, 2010
520 3# - SUMMARY, ETC.
Summary, etc. 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.
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element DATA SETS
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element DEFORMABLE MODELS
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element DISCRIMINATIVE TRAINING
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element LABELED DATA
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element LATENT INFORMATION
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element LATENT VALUE
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element LATENT VARIABLE
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element MULTISCALES
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element NEGATIVE EXAMPLES
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element OBJECT CLASS
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element OBJECT DETECTION
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element OBJECT DETECTION SYSTEMS
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element OBJECTIVE FUNCTIONS
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element PICTORIAL STRUCTURES
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element POSITIVE EXAMPLES
650 14 - SUBJECT ADDED ENTRY--TOPICAL TERM
Topical term or geographic name entry element POSITIVE EXAMPLES
700 12 - ADDED ENTRY--PERSONAL NAME
Personal name Felzenszwalb, P.F.
700 12 - ADDED ENTRY--PERSONAL NAME
Personal name Girshick, R.B.
700 12 - ADDED ENTRY--PERSONAL NAME
Personal name Mcallester, D.
700 12 - ADDED ENTRY--PERSONAL NAME
Personal name Ramanan, D.
856 40 - ELECTRONIC LOCATION AND ACCESS
Uniform Resource Identifier <a href="https://drive.google.com/file/d/1ToXQgJa4IsOSudxz-w0FAsUW0sZHb6HC/view?usp=drivesdk">https://drive.google.com/file/d/1ToXQgJa4IsOSudxz-w0FAsUW0sZHb6HC/view?usp=drivesdk</a>
Public note Para ver el documento ingresa a Google con tu cuenta: @cicy.edu.mx
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Clasificación local
Koha item type Documentos solicitados
Holdings
Lost status Source of classification or shelving scheme Damaged status Not for loan Collection Home library Current library Shelving location Date acquired Total checkouts Full call number Date last seen Price effective from Koha item type
  Clasificación local     Ref1 CICY CICY Documento préstamo interbibliotecario 25.06.2025   B-16142 25.06.2025 25.06.2025 Documentos solicitados