A Prior-Less Method for Multi-Face Tracking in Unconstrained Videos

2018-06-01 · CVPR 2018 6 · Chung-Ching Lin, Ying Hung

This paper presents a prior-less method for tracking and clustering an unknown number of human faces and maintaining their individual identities in unconstrained videos. The key challenge is to accurately track faces with partial occlusion and drastic appearance changes in multiple shots resulting from significant variations of makeup, facial expression, head pose and illumination. To address this challenge, we propose a new multi-face tracking and re-identification algorithm, which provides high accuracy in face association in the entire video with automatic cluster number generation, and is robust to outliers. We develop a co-occurrence model of multiple body parts to seamlessly create face tracklets, and recursively link tracklets to construct a graph for extracting clusters. A Gaussian Process model is introduced to compensate the deep feature insufficiency, and is further used to refine the linking results. The advantages of the proposed algorithm are demonstrated using a variety of challenging music videos and newly introduced body-worn camera videos. The proposed method obtains significant improvements over the state of the art [51], while relying less on handling video-specific prior information to achieve high performance.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Clustering

Methods 이 논문이 사용한 방법론

Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Unconstrained Realtime Facial Performance Capture

2015-06-01 · CVPR 2015 6 · Pei-Lun Hsieh, Chongyang Ma, Jihun Yu, Hao Li

We introduce a realtime facial tracking system specifically designed for performance capture in unconstrained settings using a consumer-level RGB-D sensor. Our framework provides uninterrupted 3D facial tracking, even in…

Real-Time Facial Segmentation and Performance Capture from RGB Input

2016-04-10 · Shunsuke Saito, Tianye Li, Hao Li

We introduce the concept of unconstrained real-time 3D facial performance capture through explicit semantic segmentation in the RGB input. To ensure robustness, cutting edge supervised learning approaches rely on large t…

Data Augmentation Segmentation Semantic Segmentation

A Generative Model for Depth-Based Robust 3D Facial Pose Tracking

2017-07-01 · CVPR 2017 7 · Lu Sheng, Jianfei Cai, Tat-Jen Cham, Vladimir Pavlovic 외

We consider the problem of depth-based robust 3D facial pose tracking under unconstrained scenarios with heavy occlusions and arbitrary facial expression variations. Unlike the previous depth-based discriminative or data…

Face Model Pose Estimation Pose Tracking

Soft Biometrics: Gender Recognition from Unconstrained Face Images using Local Feature Descriptor

2017-02-08 · Olasimbo Ayodeji Arigbabu, Sharifah Mumtazah Syed Ahmad, Wan Azizun Wan Adnan, Salman Yussof 외

Gender recognition from unconstrained face images is a challenging task due to the high degree of misalignment, pose, expression, and illumination variation. In previous works, the recognition of gender from unconstraine…

Visibility Constrained Generative Model for Depth-based 3D Facial Pose Tracking

2019-05-06 · Lu Sheng, Jianfei Cai, Tat-Jen Cham, Vladimir Pavlovic 외

In this paper, we propose a generative framework that unifies depth-based 3D facial pose tracking and face model adaptation on-the-fly, in the unconstrained scenarios with heavy occlusions and arbitrary facial expression…