Author manuscript, published in "International Journal of Computer Vision (2013)" International Journal of Computer Vision manuscript No. (will be inserted by the editor) Image Classification with…

By Jorge Sánchez, Florent Perronnin, Thomas Mensink, Jakob Verbeek. 2013

1,235 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

In Representation & Self-Supervised Learning

Citations in the corpus

Scattering Networks for Hybrid Representation Learning (2018, methodology): “and comparable to that of [43], [45], for which SIFT features are extracted followed by FV [46] encoding.”
Squeeze-and-Excitation Networks (2017, background): “Exploiting such information is prevalent in feature engineering work [35, 38, 49].”
Unsupervised Learning by Predicting Noise (2017, methodology): “, SIFT with Fisher Vectors (SIFT+FV) (Sánchez et al., 2013).”
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks (2018, background): “The family of bag-of-visual-words [5, 47, 34] models demonstrated the effectiveness of pooling the information contained in local descriptors to form a global image representation out of a local one.”
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation (2015, methodology): “The Fisher vector [44] can be replicated using the following mappingm(d) given below.”
RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, methodology): “To take advantage of both Fisher Vector [74] and RNN, Lev et al. [75] introduced a Recurrent Neural Network Fisher Vector (RNN-FV) where the GMM probabilistic model in the fisher vector is replaced by a RNN and thus avoids the need for the assumptions of data distribution in the GMM.”
Unsupervised Learning of Long-Term Motion Dynamics for Videos (2017, methodology): “The most successful example is to extract improved trajectory features [38] and employ Fisher vector representation [25].”
Hierarchical Recurrent Neural Encoder for Video Representation with Application to Captioning (2015, methodology): “Bag-of-Words (BoWs) [28] and Fisher vector encoding [25] are then applied to accumulate the local descriptors and generate the video representation.”
Towards Good Practices for Very Deep Two-Stream ConvNets (2015, methodology): “The most successful example is to extract improved trajectory features [16] and employ Fisher vector representation [11].”
Action recognition with trajectory-pooled deep-convolutional descriptors (2015, methodology): “We choose Fisher vector [23] to encode the TDDs of a video clip into high dimensional representation as its effectiveness for action recognition has been verified in previous works [38, 27], and then use a linear SVM as the classifer (C = 100).”
SUN Database: Exploring a Large Collection of Scene Categories (2014, background): “The best performance on this benchmark that we are aware of is based on Fisher vector [38], where they achieve impressive 47.”
Modeling Spatial-Temporal Clues in a Hybrid Deep Learning Framework for Video Classification (2015, methodology): “In addition, further improvements may be achieved by using advantageous feature encoding methods like the Fisher Vectors [29] or adopting feature normalization strategies, such as RootSift [1] and Power Norm [32].”
Analyzing Classifiers: Fisher Vectors and Deep Neural Networks (2015, methodology): “Fisher Vectors [21, 24] are a powerful tool to compute rich image or video representations and provide state-ofthe-art performance amongst feature extraction algorithms.”
Scaling the Scattering Transform: Deep Hybrid Networks (2017, neutral): “In term of architecture, our hybrid model is analogous, and comparable to that of [30, 28], for which SIFT features are extracted followed by FV [31] encoding.”
Label-Embedding for Image Classification (2015, background): “Yu and Aloimonos’s topic model [28] is only applicable to bag-of-visual-word image representations and, therefore, cannot leverage recent stateof-the-art image features such as the Fisher vector [29].”
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning (2015, methodology): “using Fisher vectors (FVs) [39] and convolutional neural net-”
Towards Weakly-Supervised Action Localization (2016, methodology): “Each of the 4 Fisher Vectors is then independently power-normalized and L2-normalized [41].”
Temporal Segment Networks for Action Recognition in Videos (2017, methodology): “Then encoding methods are employed to aggregate these local descriptors into a global representation, and typical encoding methods include Bag of Visual Words (BoVW) [43], Fisher vector (FV) [44], Vector of Locally Aggregated Descriptors (VLAD) [45], and MultiView Super Vector (MVSV) [46].”
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch (2019, methodology): “For ease of use, it supported Windows, Mac OS X, and Linux, and has been a reference e.g for efﬁcient implementations of algorithms such as Fisher Vector [47], VLAD [24], SIFT [33], and MSER [35].”