computer-vision-3

Face Clustering

3260 papers • 126 benchmarks • 313 datasets

Face Clustering in the videos

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in face-clustering-3

Trend

Dataset

Best Model

Actions

EasyCom

Libraries

i

Use these libraries to find face-clustering-3 models and implementations

yl-1993/learn-to-cluster

2 papers 697

Datasets

EasyCom

MovieGraphs

A View From Somewhere (AVFS)

Subtasks

No subtasks available.

Most implemented papers

Sparse Subspace Clustering: Algorithm, Theory, and Applications

R. Vidal, Ehsan Elhamifar•Sun Mar 04 2012

An algorithm to cluster high-dimensional data points that lie in a union of low-dimensional subspaces, called Sparse Subspace Clustering, which does not require initialization, can be solved efficiently, and can handle data points near the intersections of subspace.

2445

Content

xiaoxiong74/face-cluster-by-infomap

2 papers 156

0

Paper Graph

Learning to Cluster Faces via Confidence and Connectivity Estimation

Chen Change Loy, Dahua Lin, Rui Zhao, Xiaohang Zhan, Dapeng Chen, Lei Yang•Tue Mar 31 2020

This paper proposes a fully learnable clustering framework without requiring a large number of overlapped subgraphs, and transforms the clustering problem into two sub-problems, designed to estimate the confidence of vertices and the connectivity of edges, respectively.

97 0

Paper Graph

Linkage Based Face Clustering via Graph Convolution Network

Shengjin Wang, Liang Zheng, Zhongdao Wang, Yali Li•Tue Mar 26 2019

This paper presents an accurate and scalable approach to the face clustering task, and shows that the proposed method does not need the number of clusters as prior, is aware of noises and outliers, and can be extended to a multi-view version for more accurate clustering accuracy.

184 0

Paper Graph

An Online Algorithm for Constrained Face Clustering in Videos

Prakhar Kulshreshtha, T. Guha•Sun Sep 30 2018

We address the problem of face clustering in long, real world videos. This is a challenging task because faces in such videos exhibit wide variability in scale, pose, illumination, expressions, and may also be partially occluded. The majority of the existing face clustering algorithms are offline, i.e., they assume the availability of the entire data at once. However, in many practical scenarios, complete data may not be available at the same time or may be too large to process or may exhibit significant variation in the data distribution over time. We propose an online clustering algorithm that processes data sequentially in short segments of variable length. The faces detected in each segment are either assigned to an existing cluster or are used to create a new one. Our algorithm uses several spatiotemporal constraints, and a convolutional neural network (CNN) to obtain a robust representation of the faces in order to achieve high clustering accuracy on two benchmark video databases (82.1 % and 93.8%). Despite being an online method (usually known to have lower accuracy), our algorithm achieves comparable or better results than state-of-the-art offline and online methods.

21 0

Paper Graph

Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit

R. Vidal, Chong You, Daniel P. Robinson•Sat Jul 04 2015

This paper studies a subspace clustering method based on orthogonal matching pursuit that is both computationally efficient and guaranteed to give a subspace-preserving affinity under broad conditions and is the first one to handle 100,000 data points.

368 0

Paper Graph

Learning Hierarchical Graph Neural Networks for Image Clustering

Yuanjun Xiong, Tianjun Xiao, Stefano Soatto, Yifan Xing, Weihao Xia, Yongxin Wang, Tong He, David Wipf Paul, Zheng Zhang•Fri Jul 02 2021

This work proposes a hierarchical graph neural network model that learns how to cluster a set of images into an unknown number of identities using a training set of image annotated with labels belonging to a disjoint set of identities.

41 0

Paper Graph

Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space

Senzhang Wang, Yaobin Zhang, Fangyi Zhang, Ming-Ching Lin, Yuqi Zhang, Xiuyu Sun•Mon Feb 07 2022

Experiments on multiple public clustering datasets show that Ada-NETS significantly outperforms current state-of-the-art methods, proving its superiority and generalization.

36 0

Paper Graph

Robust Subspace Clustering via Smoothed Rank Approximation

Zhao Kang, Chong Peng, Q. Cheng•Thu Jul 23 2015

This letter proposes a rank approximation based on Logarithm-Determinant that gives promising results on face clustering and motion segmentation tasks compared to the state-of-the-art subspace clustering algorithms.

49 0

Paper Graph

Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data

Hongdong Li, M. Salzmann, Pan Ji•Tue Sep 08 2015

This paper revisits the Shape Interaction Matrix and reveals its connections to several recent subspace clustering methods, and derives a simple, yet effective algorithm to robustify the SIM and make it applicable to realistic scenarios where the data is corrupted by noise.

77 0

Paper Graph

Robust Subspace Clustering via Tighter Rank Approximation

Chong Peng, Q. Cheng, Zhao Kang•Fri Oct 16 2015

This paper develops an effective optimization procedure based on a type of augmented Lagrange multipliers (ALM) method forMatrix rank minimization problem and uses it on the challenging subspace clustering problem.

23 0

Paper Graph

Adding a benchmark result helps the community track progress.