A Face Annotation Framework with Partial Clustering and Interactive Labeling

Tian, Yuandong; Liu, Wei; Xiao, Rong; Wen, Fang; Tang, Xiaoou

doi:10.1109/cvpr.2007.383282

Cited by 74 publications

(54 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods that tackle the face clustering problem have shown that clothing, timestamps [16], and captions [2,12] are useful context, and that the most evident clusters can aid in interactive labeling [19]. We are the first to consider using the context of other faces to aid in discovering new faces in a photo collection.…”

Section: Related Workmentioning

confidence: 99%

“…The goal is to perform unsupervised clustering on faces detected in the images, in order to come up with a batch of photos likely of the same individual, so that the user can efficiently tag or prune them with minimal effort. In contrast to previous face clustering algorithms (e.g., [2,16,19]), we propose to expand the representation of the detected faces to include not just their appearance, but also their social context. Specifically, the main idea is to use cues from co-occurring people in the same image in order to produce more reliable groups.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Face Discovery with Social Context

Lee

Grauman

2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

We present an approach to discover novel faces in untagged photo collections by leveraging the "social context" of co-occurring people. Our idea exploits the social nature of consumer photos, in which people of the same clique (family, team, class, friends) often appear together. Initially, the system trains detectors for any individuals with tagged instances in the collection. Then, for each untagged image, it isolates any unfamiliar faces. Among those, it discovers novel face clusters by leveraging both their appearance, as well as descriptors encoding the (predicted) familiar faces with which the unfamiliar faces co-occur. The resulting discovered people can then be presented to a user for nametagging, thereby efficiently propagating manually provided labels. Our experiments with real consumer photo collections demonstrate that the system outperforms baseline approaches that either lack any social context model, or rely solely on the appearance of co-occurring faces. Furthermore, we show it can successfully use the discovered models it forms to auto-tag unseen faces in a new collection.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Face Discovery with Social Context

Lee

Grauman

2011

Procedings of the British Machine Vision Conference 2011

View full text Add to dashboard Cite

show abstract

“…Clustering and Face Information Fusion annotation techniques [12], [58], [63] that facilitate efficient and effective search in collections of personal photos [7], [15]. Personal photos are commonly annotated along the "who," "where," and "when" dimension in that order of importance [3].…”

Section: Automatic Face Annotation In Personal Photo Collections Usinmentioning

confidence: 99%

“…In contrast to generic image sets, it is well-known that collections of personal photos contain rich and powerful context clues [14], [15]. These context clues include metadata such as timestamps and global positioning system tags.…”

Section: Automatic Face Annotation In Personal Photo Collections Usinmentioning

confidence: 99%

Automatic Face Annotation in Personal Photo Collections Using Context-Based Unsupervised Clustering and Face Information Fusion

Choi

Neve

et al. 2010

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-In this paper, a novel face annotation framework is proposed that systematically leverages context information such as situation awareness information with current face recognition (FR) solutions. In particular, unsupervised situation and subject clustering techniques have been developed that are aided by context information. Situation clustering groups together photos that are similar in terms of capture time and visual content, allowing for the reliable use of visual context information during subject clustering. The aim of subject clustering is to merge multiple face images that belong to the same individual. To take advantage of the availability of multiple face images for a particular individual, we propose effective FR methods that are based on face information fusion strategies. The performance of the proposed annotation method has been evaluated using a variety of photo sets. The photo sets were constructed using 1385 photos from the MPEG-7 Visual Core Experiment 3 (VCE-3) data set and approximately 20 000 photos collected from wellknown photo-sharing websites. The reported experimental results show that the proposed face annotation method significantly outperforms traditional face annotation solutions at no additional computational cost, with accuracy gains of up to 25% for particular cases.

show abstract

“…Because of scenarios like this, face identity clustering and sequence-to-sequence matching are interesting and practical problems. Similarly, in a personal photo collection with auto tagging of pictures [21], the identity clusters and suggestion of tags can tremendously reduce the human effort. In this work, we provide the database for open set identification and verification problems, as well as introducing the protocol for identity clustering.…”

Section: Introductionmentioning

confidence: 99%

Large scale unconstrained open set face database

Sapkota

Boult

2013

2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)

View full text Add to dashboard Cite

This paper addresses large scale, unconstrained, open set face recognition, which exhibits the properties of operational face recognition scenarios. Most of the existing face recognition databases have been designed under controlled conditions or have been constructed from the images collected from the web. Face images collected from the web are less constrained than a mug-shot like collection. However, they lack information about the imaging conditions and have no operational paradigm. In either case, most of the databases and evaluation algorithms have taken the form of "closed set" recognition, in which all testing classes are assumed to be known at training time. A more realistic scenario in face recognition is an "open set," where limited knowledge is available at training time and unknown classes can be present at test time. The database we provide supports the open set paradigm, which more closely mimics actual usage than classic closed set testing. The database also exhibits the natural variability among the face images such as pose, illumination, scale, expressions, occlusion, etc. Our goal is to provide around 100,000 images of more than 1,000 people. Also, with this paper, we release part 1 of the database, which consists of 6,337 images from 308 subjects. The paper discusses the details of the database followed by the challenges and results of baseline algorithms.

show abstract

A Face Annotation Framework with Partial Clustering and Interactive Labeling

Cited by 74 publications

References 10 publications

Face Discovery with Social Context

Face Discovery with Social Context

Automatic Face Annotation in Personal Photo Collections Using Context-Based Unsupervised Clustering and Face Information Fusion

Large scale unconstrained open set face database

Contact Info

Product

Resources

About