Proceedings of the British Machine Vision Conference 2014最新文献

Structured Semi-supervised Forest for Facial Landmarks Localization with Face Mask Reasoning 基于人脸面具推理的结构化半监督森林人脸标志定位

Proceedings of the British Machine Vision Conference 2014 Pub Date : 1900-01-01 DOI: 10.5244/C.28.85

Xuhui Jia, Heng Yang, Kwok-Ping Chan, I. Patras

{"title":"Structured Semi-supervised Forest for Facial Landmarks Localization with Face Mask Reasoning","authors":"Xuhui Jia, Heng Yang, Kwok-Ping Chan, I. Patras","doi":"10.5244/C.28.85","DOIUrl":"https://doi.org/10.5244/C.28.85","url":null,"abstract":"Despite the great success of recent facial landmarks localization approaches, the presence of occlusions significantly degrades the performance of the systems. However, very few works have addressed this problem explicitly due to the high diversity of occlusion in real world. In this paper, we address the face mask reasoning and facial landmarks localization in an unified Structured Decision Forests framework. We first assign a portion of the face dataset with face masks, i.e., for each face image we give each pixel a label to indicate whether it belongs to the face or not. Then we incorporate such additional information of dense pixel labelling into training the Structured Classification-Regression Decision Forest. The classification nodes aim at decreasing the variance of the pixel labels of the patches by using our proposed structured criterion while the regression nodes aim at decreasing the variance of the displacements between the patches and the facial landmarks. The proposed framework allows us to predict the face mask and facial landmarks locations jointly. We test the model on face images from several datasets with significant occlusion. The proposed method 1) yields promising results in face mask reasoning; 2) improves the existing Decision Forests approaches in facial landmark localization, aided by the face mask reasoning.","PeriodicalId":278286,"journal":{"name":"Proceedings of the British Machine Vision Conference 2014","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125284133","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 20

Regularized Multi-Concept MIL for weakly-supervised facial behavior categorization 弱监督面部行为分类的正则化多概念MIL

Proceedings of the British Machine Vision Conference 2014 Pub Date : 1900-01-01 DOI: 10.5244/C.28.13

Adria Ruiz, Joost van de Weijer, Xavier Binefa

{"title":"Regularized Multi-Concept MIL for weakly-supervised facial behavior categorization","authors":"Adria Ruiz, Joost van de Weijer, Xavier Binefa","doi":"10.5244/C.28.13","DOIUrl":"https://doi.org/10.5244/C.28.13","url":null,"abstract":"In this work, we address the problem of estimating high-level semantic labels for videos of recorded people by means of analysing their facial expressions. This problem, to which we refer as facial behavior categorization, is a weakly-supervised learning problem where we do not have access to frame-by-frame facial gesture annotations but only weak-labels at the video level are available. Therefore, the goal is to learn a set of discriminative expressions appearing during the training videos and how they determine these labels. Facial behavior categorization can be posed as a Multi-Instance-Learning (MIL) problem and we propose a novel MIL method called Regularized Multi-Concept MIL to solve it. In contrast to previous approaches applied in facial behavior analysis, RMC-MIL follows a Multi-Concept assumption which allows different facial expressions (concepts) to contribute differently to the video-label. Moreover, to handle with the high-dimensional nature of facial-descriptors, RMC-MIL uses a discriminative approach to model the concepts and structured sparsity regularization to discard non-informative features. RMC-MIL is posed as a convex-constrained optimization problem where all the parameters are jointly learned using the Projected-Quasi-Newton method. In our experiments, we use two public data-sets to show the advantages of the Regularized MultiConcept approach and its improvement compared to existing MIL methods. RMC-MIL outperforms state-of-the-art results in the UNBC data-set for pain detection.","PeriodicalId":278286,"journal":{"name":"Proceedings of the British Machine Vision Conference 2014","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130148185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 22

An Efficient Online Hierarchical Supervoxel Segmentation Algorithm for Time-critical Applications 一种用于时间关键应用的高效在线分层超体素分割算法

Proceedings of the British Machine Vision Conference 2014 Pub Date : 1900-01-01 DOI: 10.5244/C.28.130

Yiliang Xu, Dezhen Song, A. Hoogs

{"title":"An Efficient Online Hierarchical Supervoxel Segmentation Algorithm for Time-critical Applications","authors":"Yiliang Xu, Dezhen Song, A. Hoogs","doi":"10.5244/C.28.130","DOIUrl":"https://doi.org/10.5244/C.28.130","url":null,"abstract":"Video segmentation has been used in a variety of computer vision algorithms as a pre-processing step. Despite its wide application, many existing algorithms require preloading all or part of the video and batch processing the frames, which introduces temporal latency and significantly increases memory and computational cost. Other algorithms rely on human specification for segmentation granularity control. In this paper, we propose an online, hierarchical video segmentation algorithm with no latency. The new algorithm leverages a graph-based image segmentation technique and recent advances in dense optical flow. Our contributions include: 1) an efficient, yet effective probabilistic segment label propagation across consecutive frames; 2) a new method for label initialization for the incoming frame; and 3) a temporally consistent hierarchical label merging scheme. We conduct a thorough experimental analysis of our algorithm on a benchmark dataset and compare it with state-of-the-art algorithms. The results indicate that our algorithm achieves comparable or better segmentation accuracy than state-ofthe-art batch-processing algorithms, and outperforms streaming algorithms despite a significantly lower computation cost, which is required for time-critical applications.","PeriodicalId":278286,"journal":{"name":"Proceedings of the British Machine Vision Conference 2014","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128760094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Multi-target tracking in team-sports videos via multi-level context-conditioned latent behaviour models 基于多层次情境条件潜在行为模型的团队运动视频多目标跟踪

Proceedings of the British Machine Vision Conference 2014 Pub Date : 1900-01-01 DOI: 10.5244/C.28.101

Jingjing Xiao, R. Stolkin, A. Leonardis

{"title":"Multi-target tracking in team-sports videos via multi-level context-conditioned latent behaviour models","authors":"Jingjing Xiao, R. Stolkin, A. Leonardis","doi":"10.5244/C.28.101","DOIUrl":"https://doi.org/10.5244/C.28.101","url":null,"abstract":"Multi-target tracking techniques increasingly exploit contextual information about group dynamics. However, approaches established in pedestrian tracking make assumptions about features and motion models which are often inappropriate to sports team tracking, where motion is erratic and players wear similar uniforms with frequent interplayer occlusions. On the other hand, approaches designed specifically for sports team tracking are predominantly aimed at detecting game-state rather than using game-state to enhance individual tracking. We propose a multi-level multi-target sports-team tracker, which overcomes these problems by modelling latent behaviours at both individual and player-pair levels, informed by team-level context dynamics. At the player-level, targets are tracked using adaptive representations, constrained by probabilistic models of player behaviour with respect to collision avoidance. At the team-level, we exploit an adaptive meshing and voting scheme to predict regions of interest, which inform strong motion priors for key individual players. Thus, latent knowledge is derived from team-level contexts to inform player-level tracking. To evaluate our approach, we have developed a new data-set with fully ground-truthed team-sports videos, and demonstrate significantly improved performance over state-of-the-art trackers from the literature.","PeriodicalId":278286,"journal":{"name":"Proceedings of the British Machine Vision Conference 2014","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129247447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Compact Video Code and Its Application to Robust Face Retrieval in TV-Series 压缩视频编码及其在电视连续剧鲁棒人脸检索中的应用

Proceedings of the British Machine Vision Conference 2014 Pub Date : 1900-01-01 DOI: 10.5244/C.28.93

Yan Li, Ruiping Wang, Zhen Cui, S. Shan, Xilin Chen

{"title":"Compact Video Code and Its Application to Robust Face Retrieval in TV-Series","authors":"Yan Li, Ruiping Wang, Zhen Cui, S. Shan, Xilin Chen","doi":"10.5244/C.28.93","DOIUrl":"https://doi.org/10.5244/C.28.93","url":null,"abstract":"We address the problem of video face retrieval in TV-Series which searches video clips based on the presence of specific character, given one video clip of his/hers. This is tremendously challenging because on one hand, faces in TV-Series are captured in largely uncontrolled conditions with complex appearance variations, and on the other hand retrieval task typically needs efficient representation with low time and space complexity. To handle this problem, we propose a compact and discriminative representation for the huge body of video data, named Compact Video Code (CVC). Our method first models the video clip by its sample (i.e., frame) covariance matrix to capture the video data variations in a statistical manner. To incorporate discriminative information and obtain more compact video signature, the high-dimensional covariance matrix is further encoded as a much lower-dimensional binary vector, which finally yields the proposed CVC. Specifically, each bit of the code, i.e., each dimension of the binary vector, is produced via supervised learning in a max margin framework, which aims to make a balance between the discriminability and stability of the code. Face retrieval experiments on two challenging TV-Series video databases demonstrate the competitiveness of the proposed CVC over state-of-the-art retrieval methods. In addition, as a general video matching algorithm, CVC is also evaluated in traditional video face recognition task on a standard Internet database, i.e., YouTube Celebrities, showing its quite promising performance by using an extremely compact code with only 128 bits.","PeriodicalId":278286,"journal":{"name":"Proceedings of the British Machine Vision Conference 2014","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130724431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 16