Two faces are better than one: Face recognition in group photographs

Manyam, O.K.; Kumar, Neeraj; Belhumeur, Peter N.; Kriegman, David

doi:10.1109/ijcb.2011.6117516

Cited by 19 publications

(9 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Face attributes are beneficial for multiple applications such as face verification [15,2,25], identification [20], and retrieval. Predicting face attributes from images in the wild is challenging, because of complex face variations such as poses, lightings, and occlusions as shown in Fig.1.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Face Attributes in the Wild

Liu

Luo

Wang

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

6,403

4,808

View full text Add to dashboard Cite

Predicting face attributes in the wild is challenging due to complex face variations. We propose a novel deep learning framework for attribute prediction in the wild. It cascades two CNNs, LNet and ANet, which are finetuned jointly with attribute tags, but pre-trained differently. LNet is pre-trained by massive general object categories for face localization, while ANet is pre-trained by massive face identities for attribute prediction. This framework not only outperforms the state-of-the-art with a large margin, but also reveals valuable facts on learning face representation.(1) It shows how the performances of face localization (LNet) and attribute prediction (ANet) can be improved by different pre-training strategies. (2) It reveals that although the filters of LNet are fine-tuned only with imagelevel attribute tags, their response maps over entire images have strong indication of face locations. This fact enables training LNet for face localization with only image-level annotations, but without face bounding boxes or landmarks, which are required by all attribute recognition works. (3) It also demonstrates that the high-level hidden neurons of ANet automatically discover semantic concepts after pretraining with massive face identities, and such concepts are significantly enriched after fine-tuning with attribute tags. Each attribute can be well explained with a sparse linear combination of these concepts.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning Face Attributes in the Wild

Liu

Luo

Wang

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

6,403

4,808

View full text Add to dashboard Cite

show abstract

“…Context recently has caught attention in a lot of vision based face analysis problems [11], [27], [18], [19]. In an interesting work, Gallahger et al use the neighborhood information in group photographs as a prior for inference of age and gender.…”

Section: Motivation and Backgroundmentioning

confidence: 98%

“…In their experiments, they found that age and gender inference can gain using the context computed based on the neighbors of a subject. [18], use the neighbor subject's information for inference of identity of a subject. [5].…”

Section: Motivation and Backgroundmentioning

confidence: 99%

Context Based Facial Expression Analysis in the Wild

Dhall

2013

2013 Humaine Association Conference on Affective Computing and Intelligent Interaction

View full text Add to dashboard Cite

With the advances in the computer vision in the past few years, analysis of human facial expressions has gained attention. Facial expression analysis is now an active field of research for over two decades now. However, still there are a lot of questions unanswered. This project will explore and devise algorithms and techniques for facial expression analysis in practical environments. Methods will also be developed for inferring the emotion of a group of people. The central hypothesis of the project is that close to real-world data can be extracted from movies and facial expression analysis on movies is a stepping stone for moving to analysis in the real-world. The data extracted from movies carries with it rich meta-data information which will be useful for exploring the role of context in emotion recognition in the wild. For the analysis of groups of people various attributes effect the perception of mood. Study will be conducted and thorough literature survey will be performed on what are these contextual attributes. A system which can classify the mood of a group of people in videos will be developed and will be used to solve the problem of efficient image browsing and retrieval based on emotion.

show abstract

“…In face recognition [15], social context is employed to model the relationship between people, e.g. between friends on Facebook, using a Conditional Random Field (CRF) [16].…”

Section: Top-down Techniquesmentioning

confidence: 99%

Automatic Group Happiness Intensity Analysis

Dhall

Goecke

Gedeon

2015

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

Abstract-The recent advancement of social media has given users a platform to socially engage and interact with a larger population. Millions of images and videos are being uploaded everyday by users on the web from different events and social gatherings. There is an increasing interest in designing systems capable of understanding human manifestations of emotional attributes and affective displays. As images and videos from social events generally contain multiple subjects, it is an essential step to study these groups of people. In this paper, we study the problem of happiness intensity analysis of a group of people in an image using facial expression analysis. A user perception study is conducted to understand various attributes, which affect a person's perception of the happiness intensity of a group. We identify the challenges in developing an automatic mood analysis system and propose three models based on the attributes in the study. An 'in the wild' image-based database is collected. To validate the methods, both quantitative and qualitative experiments are performed and applied to the problem of shot selection, event summarisation and album creation. The experiments show that the global and local attributes defined in the paper provide useful information for theme expression analysis, with results close to human perception results.

show abstract

Two faces are better than one: Face recognition in group photographs

Cited by 19 publications

References 34 publications

Deep Learning Face Attributes in the Wild

Deep Learning Face Attributes in the Wild

Context Based Facial Expression Analysis in the Wild

Automatic Group Happiness Intensity Analysis

Contact Info

Product

Resources

About