Pose-Free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape Model

Yu, Xiaojun; Huang, Junzhou; Zhang, Shaoting; Wang, Yan; Metaxas, Dimitris N.

doi:10.1109/iccv.2013.244

Cited by 196 publications

(190 citation statements)

References 22 publications

Supporting

Mentioning

187

Contrasting

Order By: Relevance

“…Zhu & Ramanan [23] further extended the idea of mixtures of trees with a shared pool of parts. Instead of using all densely distributed facial feature points, Yu et al [24] proposed a group sparse learning method to select the most representative facial feature points to improve the tracking speed performance. Ghiasi & Fowlkes [25] proposed a hierarchical deformable shape approach for face alignment that explicitly models occlusions of parts.…”

Section: Deformable Shape Approachesmentioning

confidence: 99%

“…The basic idea of deformable shape approaches [20]- [24] is to represent a face by a collection of face feature parts arranged in a deformable shape configuration. Specifically, the appearance of each face part is modeled separately while the deformable shape is represented by "springlike" connections between pairs of face parts.…”

Section: Deformable Shape Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Robust Face Alignment with Random Forest: Analysis of Initialization, Landmarks Regression, and Shape Regularization Methods

Liew

Yairi

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYRandom forest regressor has recently been proposed as a local landmark estimator in the face alignment problem. It has been shown that random forest regressor can achieve accurate, fast, and robust performance when coupled with a global face-shape regularizer. In this paper, we extend this approach and propose a new Local Forest Classification and Regression (LFCR) framework in order to handle face images with large yaw angles. Specifically, the LFCR has an additional classification step prior to the regression step. Our experiment results show that this additional classification step is useful in rejecting outliers prior to the regression step, thus improving the face alignment results. We also analyze each system component through detailed experiments. In addition to the selection of feature descriptors and several important tuning parameters of the random forest regressor, we examine different initialization and shape regularization processes. We compare our best outcomes to the state-of-the-art system and show that our method outperforms other parametric shape-fitting approaches. key words: face alignment, shape model fitting, random forest, point distribution model, sparse representation model

show abstract

Section: Deformable Shape Approachesmentioning

confidence: 99%

Section: Deformable Shape Approachesmentioning

confidence: 99%

Robust Face Alignment with Random Forest: Analysis of Initialization, Landmarks Regression, and Shape Regularization Methods

Liew

Yairi

2016

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…It can get the hypothesis of highest possibility. Although the run time of DPM based method is slower than [126,146,59], the performance of [152] is reasonable enough.…”

Section: Proposed Dpm Based Face Detection and Alignmentmentioning

confidence: 99%

“…There are several other works employing DPM for face alignment. For example, Yu et al [146] proposed a two-stage cascaded deformable shape model for face alignment, where a group sparse learning method is proposed to automatically select the optimised anchor points to achieve robust initialization based on the part mixture model of [152]. Later, Hsu et al [54] proposed a Regression Tree Structure Model (RTSM) which achieves better time efficiency and localisation accuracy than [152].…”

Section: Model (Aam)mentioning

confidence: 99%

See 1 more Smart Citation

Exploring the frontier of smart video surveillance: novel domains and fine-grain event understanding

Zhang¹

View full text Add to dashboard Cite

Video surveillance plays an important role in our times. It is a great help in reducing the crime rate, and it can also help monitoring the status of facilities or animals. The contribution video surveillance is significant especially regarding the public and home safety.However, the performance of video surveillance system is limited by human factors such as fatigue, time efficiency, and human resources. It would be beneficial for all if fully automatic video surveillance systems are employed to do the job. With this aim, many commercial products and research prototypes have been developed for the automation of video surveillance. Although progress has been made, the performance and ability of the emerging automatic surveillance systems are still not satisfying regarding two major unsolved problems: 1) The ability to work in multiple domains; 2)The ability to understand and describe the events like the human.On the one hand, special domains such as the thermal camera or hidden camera in the wild forest are seldom considered today. We can develop great potential usage for these novel domains. For example, we can catch the thief even if the light is turned off at night with a thermal face recognition surveillance system. We can also study surveillance system with wildlife without worrying about privacy issues with the human. And surveillance in wildlife domain is a great help to zoologists and biologists. In a short word, the ability to work under different circumstances is an important sign of an advanced surveillance system and it can have numerous benefits.On the other hand, existing surveillance systems lack the event understanding and description ability. For example, current commercialised smart surveillance systems can only detect motion changes or human faces. They are far away from the ideal system that can understand the meaning of the motion in the perspective of events. Even the research prototypes which have the abilities of event recognition and anomaly detection are not able to deal with unseen events or understand relationships between roles in an event. For instance, when the detector of the smart surveillance system detected keywords "person", "baby" and "feed", we do not want the system to report "a person feeding a baby" when the actual screen is a scene where the baby is trying to share the food.This thesis aims to explore the frontier of smart video surveillance systems by investigating the above-mentioned two problems. In this thesis, several methods are proposed to study video surveillance in various domains such as crowded scene domain, and more importantly, in novel domains that are barely investigated such as thermal imaging and wildlife domain. Also, novel methods of event analysis and video description are proposed to enhance the efficiency of human-machine interaction.All the methods are connected in the scope of smart video surveillance framework. With the novel directions, three new datasets are built in this thesis as well. Enhancing the smart video surveillance system wit...

show abstract

Facial Landmark Detection

Belmonte¹,

Tirilly²,

Bilasco³

et al. 2022

Face Analysis Under Uncontrolled Conditions

View full text Add to dashboard Cite

Pose-Free Facial Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Shape Model

Abstract: Abstract

Cited by 196 publications

References 22 publications

Robust Face Alignment with Random Forest: Analysis of Initialization, Landmarks Regression, and Shape Regularization Methods

Robust Face Alignment with Random Forest: Analysis of Initialization, Landmarks Regression, and Shape Regularization Methods

Exploring the frontier of smart video surveillance: novel domains and fine-grain event understanding

Facial Landmark Detection

Contact Info

Product

Resources

About