Fisher Vector Faces in the Wild

Simonyan, Karen; Parkhi, Omkar M.; Vedaldi, Andrea; Zisserman, Andrew

doi:10.5244/c.27.8

Cited by 456 publications

(413 citation statements)

References 37 publications

Supporting

Mentioning

407

Contrasting

Unclassified

Order By: Relevance

“…Besides, compared with other stae-of-the-art methods, our model's accuracy is higher than DeepFace and DeepID2 for single net. Also, our model outperforms the result of WebFace and other traditional methods, High-dim LBP [12] and Fisher Vector Face [13]. VGG-Face is slightly superior than ours with an extremely complex network which has about 167 times number of parameters than our model.…”

Section: Fig3 Weight Value Percentage Distributionmentioning

confidence: 82%

Compressed Deep Convolution Neural Network for Face Recognition

Zou¹,

Xiao-hong²

2016

Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications

View full text Add to dashboard Cite

Abstract. Deep convolution neural network (CNN) has achieved a great success on face recognition techniques. But most of CNN models tend to be much deeper, which are at the expenses of high consumption of computation and storage. So, it is hard for these deep CNNs applied to mobile equipments because of poor computational and memory resources. To alleviate this issue, this paper optimizes a lightened baseline CNN model by adopting an additional contrastive loss to learn more discriminative features. To further reduce the number of parameters, a pruning strategy is tried to compress our model, which slightly improves accuracy on the LFW dataset with the compression ratio of 0.7. Finally, experimental result shows that the proposed method achieve state-of-the-art results with much smaller size and fewer training data.

show abstract

Section: Fig3 Weight Value Percentage Distributionmentioning

confidence: 82%

Compressed Deep Convolution Neural Network for Face Recognition

Zou¹,

Xiao-hong²

2016

Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications

View full text Add to dashboard Cite

show abstract

“…A filter can be visualized by using gradient ascent to find an input image that maximizes the filter's output activation [21]. Using this technique we generated the images shown in figure 14, which provide visualization of the filters in the second convolutional layer of the CNN+LSTM model.…”

Section: Track Parameter Estimation With Lstms and Cnnsmentioning

confidence: 99%

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

Farrell¹,

Anderson²,

Calafiura³

et al. 2017

EPJ Web Conf.

View full text Add to dashboard Cite

Abstract. Particle track reconstruction in dense environments such as the detectors of the High Luminosity Large Hadron Collider (HL-LHC) is a challenging pattern recognition problem. Traditional tracking algorithms such as the combinatorial Kalman Filter have been used with great success in LHC experiments for years. However, these state-of-theart techniques are inherently sequential and scale poorly with the expected increases in detector occupancy in the HL-LHC conditions. The HEP.TrkX project is a pilot project with the aim to identify and develop cross-experiment solutions based on machine learning algorithms for track reconstruction. Machine learning algorithms bring a lot of potential to this problem thanks to their capability to model complex non-linear data dependencies, to learn effective representations of high-dimensional data through training, and to parallelize easily on high-throughput architectures such as GPUs. This contribution will describe our initial explorations into this relatively unexplored idea space. We will discuss the use of recurrent (LSTM) and convolutional neural networks to find and fit tracks in toy detector data.

show abstract

“…Many researches had been dedicated to solve the face recognition problem with the existence of one or more types of these variations. Recently, due to the improvement of the face and facial landmark detection accuracy as well as the increase of the computational power, researches [4,27,2] show that we can achieve near-human performance on face verification benchmark taken in the unconstrainted environments such as Labeled Faces in the Wild dataset (LFW) [11]. However, as LFW dataset contains large variations in pose, illumination, and expression, it contains little variation in aging.…”

Section: Introductionmentioning

confidence: 99%

Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval

Chen

Hsu

2014

Computer Vision – ECCV 2014

281

208

View full text Add to dashboard Cite

Abstract. Recently, promising results have been shown on face recognition researches. However, face recognition and retrieval across age is still challenging. Unlike prior methods using complex models with strong parametric assumptions to model the aging process, we use a data-driven method to address this problem. We propose a novel coding framework called Cross-Age Reference Coding (CARC). By leveraging a large-scale image dataset freely available on the Internet as a reference set, CARC is able to encode the low-level feature of a face image with an ageinvariant reference space. In the testing phase, the proposed method only requires a linear projection to encode the feature and therefore it is highly scalable. To thoroughly evaluate our work, we introduce a new large-scale dataset for face recognition and retrieval across age called Cross-Age Celebrity Dataset (CACD). The dataset contains more than 160,000 images of 2,000 celebrities with age ranging from 16 to 62. To the best of our knowledge, it is by far the largest publicly available crossage face dataset. Experimental results show that the proposed method can achieve state-of-the-art performance on both our dataset as well as the other widely used dataset for face recognition across age, MORPH dataset.

show abstract

Fisher Vector Faces in the Wild

Cited by 456 publications

References 37 publications

Compressed Deep Convolution Neural Network for Face Recognition

Compressed Deep Convolution Neural Network for Face Recognition

The HEP.TrkX Project: deep neural networks for HL-LHC online and offline tracking

Cross-Age Reference Coding for Age-Invariant Face Recognition and Retrieval

Contact Info

Product

Resources

About