The Experts below are selected from a list of 27723 Experts worldwide ranked by ideXlab platform
Ruxandra Tapu - One of the best experts on this subject based on the ideXlab platform.
-
Salient object detection based on spatiotemporal attention models
Consumer Electronics (ICCE) 2013 IEEE International Conference, 2013Co-Authors: Ruxandra Tapu, Zaharia TitusAbstract:In this paper we propose a method for automatic detection of salient objects in video streams. The movie is firstly segmented into shots based on a scale space filtering Graph Partition method. Next, we introduced a combined spatial and temporal video attention model. The proposed approach combines a region-based contrast saliency measure with a novel temporal attention model. The camera/background motion is determined using a set of homoGraphic transforms, estimated by recursively applying the RANSAC algorithm on the SIFT interest point correspondence, while other types of movements are identified using agglomerative clustering and temporal region consistency. A decision is taken based on the combined spatial and temporal attention models. Finally, we demonstrate how the extracted saliency map can be used to create segmentation masks. The experimental results validate the proposed framework and demonstrate that our approach is effective for various types of videos, including noisy and low resolution data.
-
Video Segmentation and Structuring for Indexing Applications
International Journal of Multimedia Data Engineering and Management (IJMDEM), 2012Co-Authors: Ruxandra Tapu, Titus ZahariaAbstract:This paper introduces a complete framework for temporal video segmentation. First, a computationally efficient shot extraction method is introduced, which adopts the normalized Graph Partition approach, enriched with a non-linear, multiresolution filtering of the similarity vectors involved. The shot boundary detection technique proposed yields high precision (90%) and recall (95%) rates, for all types of transitions, both abrupt and gradual. Next, for each detected shot we construct a static storyboard, by introducing a leap keyframe extraction method. The video abstraction algorithm is 23% faster than existing, state of the art techniques, for similar performances. Finally, we propose a shot grouping strategy that iteratively clusters visually similar shots, under a set of temporal constraints. Two different types of visual features are here exploited: HSV color histograms and interest points. In both cases, the precision and recall rates present average performances of 86%.
-
Video Structuring: From Pixels to Visual Entities
2012Co-Authors: Ruxandra Tapu, Zaharia TitusAbstract:In this paper we propose a complete framework for automatic detection of salient objects in video streams. The video flow is firstly segmented into shots based on scale space filtering Graph Partition method. For each detected shot the associated static summary is developed using a leap keyframe extraction method. Based on the representative images we introduce next a combined spatial and temporal video attention models that is able to recognize both interesting objects and actions in image sequences. The approach extends the state-of-the-art image region based contrast saliency with a temporal attention model. Different types of motion presented in the current shot are determined using a set of homoGraphic transforms, estimated by recursively applying the RANSAN algorithm on the interest point correspondence. Finally, a decision is taken based on the combined information from both saliency maps. The experimental results validate the proposed framework and demonstrate that our approach is suitable for various types of videos and is robust to noise and low resolution
-
A complete framework for temporal video segmentation
2011 IEEE International Conference on Consumer Electronics -Berlin (ICCE-Berlin), 2011Co-Authors: Ruxandra Tapu, Titus ZahariaAbstract:In this paper we propose a complete high level segmentation algorithm of video flows into scenes. In the first stage of our implementation we detected shot boundaries using an enhanced Graph Partition method based on non-linear scale space filtering at reduce computational time. In the second phase we develop static summaries for each detected shot based on a leap extraction technique that selects a variable number of keyframes depending on the visual content variation. Finally, we propose an iterative, temporally constrained shot clustering technique that detects video scenes with an average precision and recall rates of 85% and 84%.
-
Automatic Multilevel Temporal Video Structuring
2011Co-Authors: Ruxandra Tapu, Titus ZahariaAbstract:In this paper we propose a novel and complete video scene segmentation framework, developed on different structural levels of analysis. Firstly, a shot boundary detection algorithm is introduced that extends the Graph Partition method with a nonlinear scale space filtering technique which increase the detection efficiency with gains of 7,4% to 9,8% in terms of both precision and recall rates. Secondly, static storyboards are formed based on a leap keyframe extraction method that selects a variable number of keyframes, adapted to the visual content variation, for each detected shot. Finally using the tracted keyframes, spatio-temporal coherent shots are clustered into the same scene based on temporal constraints and with the help of a new concept of neutralized shots. Video scenes are obtained with average precision and recall rates of 86%.
Hongyang Chao - One of the best experts on this subject based on the ideXlab platform.
-
discovering video shot categories by unsupervised stochastic Graph Partition
IEEE Transactions on Multimedia, 2013Co-Authors: Xiaohua Duan, Liang Lin, Hongyang ChaoAbstract:Video shots are often treated as the basic elements for retrieving information from videos. In recent years, video shot categorization has received increasing attention, but most of the methods involve a procedure of supervised learning, i.e., training a multi-class predictor (classifier) on the labeled data. In this paper, we study a general framework to unsupervisedly discover video shot categories. The contributions are three-fold in feature, representation, and inference: (1) A new feature is proposed to capture local information in videos, defined with small video patches (e.g., 11 × 11 × 5 pixels). A dictionary of video words can be thus clustered off-line, characterizing both appearance and motion dynamics. (2) We pose the problem of categorization as an automated Graph Partition task, in that each Graph vertex represents a video shot, and a Partitioned sub-Graph consisting of connected Graph vertices represents a clustered category. The model of each video shot category can be analytically calculated by a projection pursuit type of learning process. (3) An MCMC-based cluster sampling algorithm, namely Swendsen-Wang cuts, is adopted to efficiently solve the Graph Partition. Unlike traditional Graph Partition techniques, this algorithm is able to explore the nearly global optimal solution and eliminate the need for good initialization. We apply our method on a wide variety of 1600 video shots collected from Internet as well as a subset of TRECVID 2010 data, and two benchmark metrics, i.e., Purity and Conditional Entropy, are adopted for evaluating performance. The experimental results demonstrate superior performance of our method over other popular state-of-the-art methods.
Titus Zaharia - One of the best experts on this subject based on the ideXlab platform.
-
Video Segmentation and Structuring for Indexing Applications
International Journal of Multimedia Data Engineering and Management (IJMDEM), 2012Co-Authors: Ruxandra Tapu, Titus ZahariaAbstract:This paper introduces a complete framework for temporal video segmentation. First, a computationally efficient shot extraction method is introduced, which adopts the normalized Graph Partition approach, enriched with a non-linear, multiresolution filtering of the similarity vectors involved. The shot boundary detection technique proposed yields high precision (90%) and recall (95%) rates, for all types of transitions, both abrupt and gradual. Next, for each detected shot we construct a static storyboard, by introducing a leap keyframe extraction method. The video abstraction algorithm is 23% faster than existing, state of the art techniques, for similar performances. Finally, we propose a shot grouping strategy that iteratively clusters visually similar shots, under a set of temporal constraints. Two different types of visual features are here exploited: HSV color histograms and interest points. In both cases, the precision and recall rates present average performances of 86%.
-
A complete framework for temporal video segmentation
2011 IEEE International Conference on Consumer Electronics -Berlin (ICCE-Berlin), 2011Co-Authors: Ruxandra Tapu, Titus ZahariaAbstract:In this paper we propose a complete high level segmentation algorithm of video flows into scenes. In the first stage of our implementation we detected shot boundaries using an enhanced Graph Partition method based on non-linear scale space filtering at reduce computational time. In the second phase we develop static summaries for each detected shot based on a leap extraction technique that selects a variable number of keyframes depending on the visual content variation. Finally, we propose an iterative, temporally constrained shot clustering technique that detects video scenes with an average precision and recall rates of 85% and 84%.
-
Automatic Multilevel Temporal Video Structuring
2011Co-Authors: Ruxandra Tapu, Titus ZahariaAbstract:In this paper we propose a novel and complete video scene segmentation framework, developed on different structural levels of analysis. Firstly, a shot boundary detection algorithm is introduced that extends the Graph Partition method with a nonlinear scale space filtering technique which increase the detection efficiency with gains of 7,4% to 9,8% in terms of both precision and recall rates. Secondly, static storyboards are formed based on a leap keyframe extraction method that selects a variable number of keyframes, adapted to the visual content variation, for each detected shot. Finally using the tracted keyframes, spatio-temporal coherent shots are clustered into the same scene based on temporal constraints and with the help of a new concept of neutralized shots. Video scenes are obtained with average precision and recall rates of 86%.
Guoming Zhang - One of the best experts on this subject based on the ideXlab platform.
-
unsupervised multi granular chinese word segmentation and term discovery via Graph Partition
Journal of Biomedical Informatics, 2020Co-Authors: Zheng Yuan, Yuanhao Liu, Qiuyang Yin, Xiaobin Feng, Guoming ZhangAbstract:Abstract Objective This study aims at realizing unsupervised term discovery in Chinese electronic health records (EHRs) by using the word segmentation technique. The existing supervised algorithms do not perform satisfactorily in the case of EHRs, as annotated medical data are scarce. We propose an unsupervised segmentation method (GTS) based on the Graph Partition principle, whose multi-granular segmentation capability can help realize efficient term discovery. Methods A sentence is converted to an undirected Graph, with the edge weights based on n-gram statistics, and ratio cut is used to split the sentence into words. The Graph Partition is solved efficiently via dynamic programming, and multi-granularity is realized by setting different Partition numbers. A BERT-based discriminator is trained using generated samples to verify the correctness of the word boundaries. The words that are not recorded in existing dictionaries are retained as potential medical terms. Results We compared the GTS approach with mature segmentation systems for both word segmentation and term discovery. MD students manually segmented Chinese EHRs at fine and coarse granularity levels and reviewed the term discovery results. The proposed unsupervised method outperformed all the competing algorithms in the word segmentation task. In term discovery, GTS outperformed the best baseline by 17 percentage points (a 47% relative percentage of increment) on F1-score. Conclusion In the absence of annotated training data, the Graph Partition technique can effectively use the corpus statistics and even expert knowledge to realize unsupervised word segmentation of EHRs. Multi-granular segmentation can be used to provide potential medical terms of various lengths with high accuracy.
Yuanhao Liu - One of the best experts on this subject based on the ideXlab platform.
-
unsupervised multi granular chinese word segmentation and term discovery via Graph Partition
Journal of Biomedical Informatics, 2020Co-Authors: Zheng Yuan, Yuanhao Liu, Qiuyang Yin, Xiaobin Feng, Guoming ZhangAbstract:Abstract Objective This study aims at realizing unsupervised term discovery in Chinese electronic health records (EHRs) by using the word segmentation technique. The existing supervised algorithms do not perform satisfactorily in the case of EHRs, as annotated medical data are scarce. We propose an unsupervised segmentation method (GTS) based on the Graph Partition principle, whose multi-granular segmentation capability can help realize efficient term discovery. Methods A sentence is converted to an undirected Graph, with the edge weights based on n-gram statistics, and ratio cut is used to split the sentence into words. The Graph Partition is solved efficiently via dynamic programming, and multi-granularity is realized by setting different Partition numbers. A BERT-based discriminator is trained using generated samples to verify the correctness of the word boundaries. The words that are not recorded in existing dictionaries are retained as potential medical terms. Results We compared the GTS approach with mature segmentation systems for both word segmentation and term discovery. MD students manually segmented Chinese EHRs at fine and coarse granularity levels and reviewed the term discovery results. The proposed unsupervised method outperformed all the competing algorithms in the word segmentation task. In term discovery, GTS outperformed the best baseline by 17 percentage points (a 47% relative percentage of increment) on F1-score. Conclusion In the absence of annotated training data, the Graph Partition technique can effectively use the corpus statistics and even expert knowledge to realize unsupervised word segmentation of EHRs. Multi-granular segmentation can be used to provide potential medical terms of various lengths with high accuracy.
-
Word Segmentation as Graph Partition
arXiv: Computation and Language, 2018Co-Authors: Yuanhao LiuAbstract:We propose a new approach to the Chinese word segmentation problem that considers the sentence as an undirected Graph, whose nodes are the characters. One can use various techniques to compute the edge weights that measure the connection strength between characters. Spectral Graph Partition algorithms are used to group the characters and achieve word segmentation. We follow the Graph Partition approach and design several unsupervised algorithms, and we show their inspiring segmentation results on two corpora: (1) electronic health records in Chinese, and (2) benchmark data from the Second International Chinese Word Segmentation Bakeoff.
