Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Fisher vectors meet neural networks: a hybrid visual classification architecture

Fisher vectors meet neural networks: a hybrid visual classification architecture

US Patent 9514391 · Granted Dec 6, 2016

Estimated economic value: $4,380,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Method for training a convolutional neural network for image recognition using i2022
Training and using a convolutional neural network for person re-identification2021
Instance-level image retrieval with a region proposal network2020
Latent embeddings for word images and their semantics2020
Label-embedding view of attribute-based recognition2019
Multi-query privacy-preserving parking management system and method2017
Extracting gradient features from neural networks2017
Vehicle occupancy detection using passenger to driver feature distance2017
One-to-many matching with application to efficient privacy-preserving re-identif2017
Clustering using non-negative matrix factorization on sparse graphs2017
Efficient object detection with patch-level window processing2017
Efficient object detection with patch-level window processing2017