# Understanding the Fisher Vector: a multimodal part model

Source: [Understanding the Fisher Vector: a multimodal part model](<https://www.sota2.com/research/paper/68fa61cd1e209131ce9f60b5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:06:28.249Z

Authors: David Novotn\\'y, Diane Larlus, Florent Perronnin, Andrea Vedaldi

Published: 2015-04-18T21:12:41.000Z

## Abstract

Fisher Vectors and related orderless visual statistics have demonstrated excellent performance in object detection, sometimes superior to established approaches such as the Deformable Part Models. However, it remains unclear how these models can capture complex appearance variations using visual codebooks of limited sizes and coarse geometric information. In this work, we propose to interpret Fisher-Vector-based object detectors as part-based models. Through the use of several visualizations and experiments, we show that this is a useful insight to explain the good performance of the model. Furthermore, we reveal for the first time several interesting properties of the FV, including its ability to work well using only a small subset of input patches and visual words. Finally, we discuss the relation of the FV and DPM detectors, pointing out differences and commonalities between them.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1504.04763>)

[PDF](<https://arxiv.org/pdf/1504.04763.pdf>)
