Faces in Places: compound query retrieval

Zhong, Yujie; Arandjelović, Relja; Zisserman, Andrew

doi:10.5244/c.30.56

Cited by 15 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, today, stateof-the-art deep learned models, based on CNN architectures are being used in almost all visual computing related domains. Examples include image perception [18], recognition [19], classification [20] [25], and information retrieval [21].…”

Section: Proposed Methodologymentioning

confidence: 99%

Experiments on Deep Face Recognition Using Partial Faces

Elmahmudi

Ugail

2018

2018 International Conference on Cyberworlds (CW)

View full text Add to dashboard Cite

Face recognition is a very current subject of great interest in the area of visual computing. In the past, numerous face recognition and authentication approaches have been proposed, though the great majority of them use full frontal faces both for training machine learning algorithms and for measuring the recognition rates. In this paper, we discuss some novel experiments to test the performance of machine learning, especially the performance of deep learning, using partial faces as training and recognition cues. Thus, this study sharply differs from the common approaches of using the full face for recognition tasks. In particular, we study the rate of recognition subject to the various parts of the face such as the eyes, mouth, nose and the forehead. In this study, we use a convolutional neural network based architecture along with the pre-trained VGG-Face model to extract features for training. We then use two classifiers namely the cosine similarity and the linear support vector machine to test the recognition rates. We ran our experiments on the Brazilian FEI dataset consisting of 200 subjects. Our results show that the cheek of the face has the lowest recognition rate with 15% while the (top, bottom and right) half and the 3/4 of the face have near 100% recognition rates.

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

Experiments on Deep Face Recognition Using Partial Faces

Elmahmudi

Ugail

2018

2018 International Conference on Cyberworlds (CW)

View full text Add to dashboard Cite

show abstract

“…Of relevance to the architectures developed in this paper are Siamese networks [6], in which similarity metrics are learnt for face classification without explicit class labels. [23,27] are also relevant in that they simultaneously train multi-stream networks in which the inputs are of different domains.…”

Section: Related Workmentioning

confidence: 99%

Out of Time: Automated Lip Sync in the Wild

Chung

Zisserman

2017

Computer Vision – ACCV 2016 Workshops

Self Cite

263

284

View full text Add to dashboard Cite

The goal of this work is to determine the audio-video synchronisation between mouth motion and speech in a video. We propose a two-stream ConvNet architecture that enables the mapping between the sound and the mouth images to be trained end-to-end from unlabelled data. The trained network is used to determine the lip-sync error in a video. We apply the network to two further tasks: active speaker detection and lip reading. On both tasks we set a new state-of-the-art on standard benchmark datasets.

show abstract

“…There has also been work in the area of transferring a face onto a target in a similar pose. Zhong et al (2016) paste celebrity faces onto images to generate a synthetic dataset of novel (celebrity face, action) pair images.…”

Section: Related Workmentioning

confidence: 99%

Privacy-preserving Object Detection

He¹,

Griffin²,

Kacprzyk³

et al. 2021

Preprint

View full text Add to dashboard Cite

Privacy considerations and bias in datasets are quickly becoming high-priority issues that the computer vision community needs to face. So far, little attention has been given to practical solutions that do not involve collection of new datasets. In this work, we show that for object detection on COCO, both anonymizing the dataset by blurring faces, as well as swapping faces in a balanced manner along the gender and skin tone dimension, can retain object detection performances while preserving privacy and partially balancing bias.

show abstract

Faces in Places: compound query retrieval

Cited by 15 publications

References 0 publications

Experiments on Deep Face Recognition Using Partial Faces

Experiments on Deep Face Recognition Using Partial Faces

Out of Time: Automated Lip Sync in the Wild

Privacy-preserving Object Detection

Contact Info

Product

Resources

About