AI Paper Atlas

Research map / Video / Action recognition

RNN Fisher Vectors for Action Recognition and Image Annotation

Guy Lev, Gil Sadeh, Benjamin Klein, Lior Wolf

ECCV 2016 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 173 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use RNN-FV pooling instead of mean poolingVGG PCA features · HMDB51accuracy: 42.16 -> 45.62Improved
use RNN-FV pooling instead of GMM-FVVGG PCA features · HMDB51accuracy: 36.8 -> 45.62Improved
use RNN-FV pooling instead of GMM-FVC3D features · UCF101accuracy: 80.04 -> 82.33Improved
project VGG frames with image-sentence CCA instead of PCARNN-FV · UCF101accuracy: 79.29 -> 79.49Improved
fuse RNN-FV of C3D and VGG-CCA with idtRNN-FV · HMDB51accuracy: 54.33 -> 67.71Improved
fuse RNN-FV of C3D and VGG-CCA with idtRNN-FV · UCF101accuracy: 88.01 -> 94.08Improved
use regression RNN instead of classification RNN (ablation)RNN-FV w2v · Flickr8Ksentence mean rank: 13.2 -> 10.4Improved
use CCA word embedding instead of word2vec (ablation)RNN-FV · Flickr8K image annotationrecall@1: 27.4 -> 30.9Improved
train RNN on dataset sentences instead of Wikipedia (ablation)RNN-FV · Flickr8K image annotationrecall@1: 29.3 -> 27.4No clear effect
add GMM+HGLMM model to the CCA RNN-FV ensembleRNN-FV cca · Flickr8K image annotationrecall@1: 30.9 -> 32.9Improved
add reversed-sentence model to the CCA RNN-FV (ablation)RNN-FV cca · Flickr8K image annotationrecall@1: 30.9 -> 30.8No clear effect
reduce gradient dimension to 4,096 with PCA (ablation)RNN-FV · Flickr8K/Flickr30K/COCOrecallNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy