Image classification with the Fisher vector: theory and practice

DOI10.1007/s11263-013-0636-xzbMath1286.68447MaRDI QIDQ2450399

Thomas Mensink, Jorge Sánchez, Florent Perronnin, Jakob Verbeek

Publication date: 14 May 2014

Published in: International Journal of Computer Vision (Search for Journal in Brave)

Full work available at URL: https://hal.inria.fr/hal-00830491/file/journal.pdf

zbMATH Keywords

image classification; Fisher vector; large-scale classification; Fisher kernel; Bag-of-Visual words; product quantization

Mathematics Subject Classification ID

68U10: Computing methodologies for image processing

94A08: Image processing (compression, reconstruction, etc.) in information and communication theory

68T45: Machine vision and scene understanding

Related Items

Orthogonal sparse linear discriminant analysis, An Image-Based Approach to Detecting Structural Similarity Among Mixed Integer Programs, High-dimensional model recovery from random sketched data by exploring intrinsic sparsity, Collaborative linear coding for robust image classification, Local color oppugnant quantized extrema patterns for image retrieval, Tensor decomposition for learning Gaussian mixtures from moments, Kernel-based transition probability toward similarity measure for semi-supervised learning, Facial Image Classification Using Rotation, Illumination, Scale and Expression Invariant Dense Features and ENN, Low-Rank Online Metric Learning

Uses Software

• Pegasos
• SIFT
• ImageNet
• Caltech-256
• PASCAL VOC

Cites Work

• Unnamed Item
• Unnamed Item
• Pegasos: primal estimated sub-gradient solver for SVM
• Asymptotic distribution of coordinates on high dimensional spheres
• $L_p$-norm uniform distribution
• Quantization