Proceedings ArticleDOI
Total Cluster: A person agnostic clustering method for broadcast videos
Makarand Tapaswi,Omkar M. Parkhi,Esa Rahtu,Eric Sommerlade,Rainer Stiefelhagen,Andrew Zisserman +5 more
- pp 7
TLDR
The extent to which faces can be clustered automatically without making an error is explored, and an extension of the clustering method to entire episodes using exemplar SVMs based on the negative training data automatically harvested from the editing structure is proposed.Abstract:
The goal of this paper is unsupervised face clustering in edited video material – where face tracks arising from different people are assigned to separate clusters, with one cluster for each person. In particular we explore the extent to which faces can be clustered automatically without making an error. This is a very challenging problem given the variation in pose, lighting and expressions that can occur, and the similarities between different people.The novelty we bring is three fold: first, we show that a form of weak supervision is available from the editing structure of the material – the shots, threads and scenes that are standard in edited video; second, we show that by first clustering within scenes the number of face tracks can be significantly reduced with almost no errors; third, we propose an extension of the clustering method to entire episodes using exemplar SVMs based on the negative training data automatically harvested from the editing structure.The method is demonstrated on multiple episodes from two very different TV series, Scrubs and Buffy. For both series it is shown that we move towards our goal, and also outperform a number of baselines from previous works.read more
Citations
More filters
Journal ArticleDOI
Clustering Millions of Faces by Identity
TL;DR: In this paper, an approximate Rank-Order clustering algorithm was proposed to address the challenges of run-time complexity and cluster quality, which achieves an F-measure of 0.87 on the LFW benchmark (13 K faces of 5,749 individuals).
Proceedings ArticleDOI
Efficient Parameter-Free Clustering Using First Neighbor Relations
TL;DR: A new clustering method in the form of a single clustering equation that is able to directly discover groupings in the data that has a very low computational overhead, is easily scalable and applicable to large practical problems.
Posted Content
Clustering Millions of Faces by Identity
TL;DR: An approximate Rank-Order clustering algorithm is presented that performs better than popular clustering algorithms (k-Means and Spectral) and an internal per-cluster quality measure is developed to rank individual clusters for manual exploration of high quality clusters that are compact and isolated.
Book ChapterDOI
Joint Face Representation Adaptation and Clustering in Videos
TL;DR: Experiments demonstrate that the proposed joint face representation adaptation and clustering approach generates character clusters with high purity compared to existing video face clustering methods, which are either based on deep face representation (without adaptation) or carefully engineered features.
Proceedings ArticleDOI
End-to-End Face Detection and Cast Grouping in Movies Using Erdös-Rényi Clustering
TL;DR: A novel clustering method is introduced, motivated by the classic graph theory results of Erdös and Rényi, based on the observations that large clusters can be fully connected by joining just a small fraction of their point pairs, while just a single connection between two different people can lead to poor clustering results.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Journal ArticleDOI
Object Detection with Discriminatively Trained Part-Based Models
TL;DR: An object detection system based on mixtures of multiscale deformable part models that is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges is described.
Proceedings ArticleDOI
Good features to track
Jianbo Shi,Tomasi +1 more
TL;DR: A feature selection criterion that is optimal by construction because it is based on how the tracker works, and a feature monitoring method that can detect occlusions, disocclusions, and features that do not correspond to points in the world are proposed.
Proceedings ArticleDOI
A discriminatively trained, multiscale, deformable part model
TL;DR: A discriminatively trained, multiscale, deformable part model for object detection, which achieves a two-fold improvement in average precision over the best performance in the 2006 PASCAL person detection challenge and outperforms the best results in the 2007 challenge in ten out of twenty categories.
Proceedings ArticleDOI
Face recognition in unconstrained videos with matched background similarity
Lior Wolf,Tal Hassner,Itay Maoz +2 more
TL;DR: A comprehensive database of labeled videos of faces in challenging, uncontrolled conditions, the ‘YouTube Faces’ database, along with benchmark, pair-matching tests are presented and a novel set-to-set similarity measure, the Matched Background Similarity (MBGS), is described.