检索结果-内蒙古大学图书馆

9th International Conference on Hybrid Intelligent Systems (HIS 2009)

作者： Hu, Wu-Chih Yang, Ching-Yu Huang, Deng-Yuan Hsu, Jung-Fu Department of Computer Science and Information Engineering National Penghu University Taiwan Department of Electrical Engineering Dayeh University Taiwan

ISBN: (纸本)9780769537450

This paper proposes an effective method for video object segmentation without background construction. In the proposed method, the coarse foreground extraction and fine foreground extraction are obtained using the motion information, edge information, and gradient-variation information which are first evaluated by two successive frames. Next, the video object is extracted using the horizontal/vertical filling scheme based on the coarse foreground extraction and fine foreground extraction. Finally, video object refining is used to obtain the more accurate video object. Experimental results show that the proposed method has good performance in sensitivity, specificity, and spatial accuracy.

关键词： video object segmentation foreground extraction

来源：评论

学校读者我要写书评

暂无评论

video object segmentation AGGREGATION

VIDEO OBJECT SEGMENTATION AGGREGATION

引用

IEEE International Conference on Multimedia & Expo (ICME)

作者： Zhou, Tianfei Lu, Yao Di, Huijun Zhang, Jian Beijing Lab Intelligent Informat Technol Beijing Peoples R China Beijing Inst Technol Sch Comp Sci Beijing Peoples R China Univ Technol Sydney Fac Engn & Informat Technol Sydney NSW 2007 Australia

ISBN: (纸本)9781467372589

We present an approach for unsupervised object segmentation in unconstrained videos. Driven by the latest progress in this field, we argue that segmentation performance can be largely improved by aggregating the results generated by state-of-the- art algorithms. Initially, objects in individual frames are estimated through a per-frame aggregation procedure using majority voting. While this can predict relatively accurate object location, the initial estimation fails to cover the parts that are wrongly labeled by more than half of the algorithms. To address this, we build a holistic appearance model using non-local appearance cues by linear regression. Then, we integrate the appearance priors and spatio-temporal information into an energy minimization framework to refine the initial estimation. We evaluate our method on challenging benchmark videos and demonstrate that it outperforms state-of-the-art algorithms.

关键词： video object segmentation data fusion appearance model

来源：评论

学校读者我要写书评

暂无评论

video object segmentation by Learning Location-Sensitive Embeddings 15th

Video Object Segmentation by Learning Location-Sensitive Emb...

引用

15th European Conference on Computer Vision (ECCV)

作者： Ci, Hai Wang, Chunyu Wang, Yizhou Peking Univ EECS Beijing Peoples R China Microsoft Res Asia Beijing Peoples R China Deepwise AI Lab Beijing Peoples R China

ISBN: (纸本)9783030012526;9783030012519

We address the problem of video object segmentation which outputs the masks of a target object throughout a video given only a bounding box in the first frame. There are two main challenges to this task. First, the background may contain similar objects as the target. Second, the appearance of the target object may change drastically over time. To tackle these challenges, we propose an end-to-end training network which accomplishes foreground predictions by leveraging the location-sensitive embeddings which are capable to distinguish the pixels of similar objects. To deal with appearance changes, for a test video, we propose a robust model adaptation method which pre-scans the whole video, generates pseudo foreground/background labels and retrains the model based on the labels. Our method outperforms the state-of-the-art methods on the DAVIS and the SegTrack v2 datasets.

关键词： video object segmentation Location-sensitive embeddings

来源：评论

学校读者我要写书评

暂无评论

video object segmentation Based on Guided Feature Transfer Learning 28th

Video Object Segmentation Based on Guided Feature Transfer L...

引用

28th International Workshop on Frontiers of Computer Vision (IW-FCV)

作者： Fiaz, Mustansar Mahmood, Arif Farooq, Sehar Shahzad Ali, Kamran Shaheryar, Muhammad Jung, Soon Ki Mohamed Bin Zayed Univ Artificial Intelligence Dept Comp Vis Abu Dhabi U Arab Emirates Informat Technol Univ Dept Comp Sci Lahore Pakistan Kyungpook Natl Univ Sch Comp Sci & Engn Daegu South Korea Univ Cent Florida Dept Comp Sci Orland FL USA

ISBN: (纸本)9783031063817;9783031063800

video object segmentation (VOS) is a fundamental task with many real-world computer vision applications and challenging due to available distractors and background clutter. Many existing online learning approaches have limited practical significance because of high computational cost required to fine-tune network parameters. Moreover, matching based and propagation approaches are computationally efficient but may suffer from degraded performance in cluttered backgrounds and object drifts. In order to handle these issues, we propose an offline end-to-end model to learn guided feature transfer for VOS. We introduce guided feature modulation based on target mask to capture the video context information and a generative appearance model is used to provide cues for both the target and the background. Proposed guided feature modulation system learns the target semantic information based on modulation activations. Generative appearance model learns the probability of a pixel to be target or background. In addition, low-resolution features from deeper networks may not capture the global contextual information and may reduce the performance during feature refinement. Therefore, we also propose a guided pooled decoder to learn the global as well as local context information for better feature refinement. Evaluation over two VOS benchmark datasets including DAVIS2016 and DAVIS2017 have shown excellent performance of the proposed framework compared to more than 20 existing state-of-the-art methods.

关键词： video object segmentation Guided Feature Modulation Generative appearance model Guided Pooled Decoder

来源：评论

学校读者我要写书评

暂无评论

Fast target-aware learning for few-shot video object segmentation

引用

Science China(Information Sciences) 2022年第8期65卷 71-86页

作者： Yadang CHEN Chuanyan HAO Zhi-Xin YANG Enhua WU Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and Technology School of Education Science and Technology Nanjing University of Posts and Telecommunications State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of Macau State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of Sciences Faculty of Science and Technology University of Macau

Few-shot video object segmentation(FSVOS) aims to segment a specific object throughout a video sequence when only the first-frame annotation is given. In this study, we develop a fast target-aware learning approach for FSVOS, where the proposed approach adapts to new video sequences from its firstframe annotation through a lightweight procedure. The proposed network comprises two models. First, the meta knowledge model learns the general semantic features for the input video image and up-samples the coarse predicted mask to the original image size. Second, the target model adapts quickly from the limited support set. Concretely, during the online inference for testing the video, we first employ fast optimization techniques to train a powerful target model by minimizing the segmentation error in the first frame and then use it to predict the subsequent frames. During the offline training, we use a bilevel-optimization strategy to mimic the full testing procedure to train the meta knowledge model across multiple video *** proposed method is trained only on an individual public video object segmentation(VOS) benchmark without additional training sets and compared favorably with state-of-the-art methods on DAVIS-2017, with a J &F overall score of 71.6%, and on YouT ubeVOS-2018, with a J &F overall score of 75.4%. Meanwhile,a high inference speed of approximately 0.13 s per frame is maintained.

关键词： video object segmentation few-shot target-aware meta knowledge bilevel-optimization

来源：评论

学校读者我要写书评

暂无评论

ASDeM: Augmenting SAM With Decoupled Memory for video object segmentation

引用

IEEE ACCESS 2024年 12卷 73218-73227页

作者： Liu, Xiaohu Luo, Yichuang Sun, Wei Shaanxi Univ Technol Trine Engn Inst Hanzhong 723001 Peoples R China Xian Peihua Univ Dept Intelligent Sci & Engn Xian 710125 Peoples R China Shaanxi Univ Technol Sch Mech Engn Hanzhong 723001 Peoples R China

video object segmentation models have gained impressive performance, but present low interactivity with different prompts, such as click, box or text. Some models combined with SAM in a naive manner to enhance this ability, which achieve a limited performance owing to the coarse mask and inconsistent segmentation propagation. In this paper, we propose ASDeM, which augments SAM with decoupled memory, achieving high-performance on tracking and segmentation in videos. Specifically, to explore the combination of SAM and VOS model, ASDeM fully utilizes the class-agnostic features from SAM to build the memory features for VOS model, and further the object-agnostic temporal propagation with decoupled memory is applied to address the feature staleness problem and the oblivion problem of visual information. Given the prompt for the specific object in a video, people can get satisfactory segmentation and tracking results. The experiments demonstrate the effectiveness of ASDeM on public benchmarks.

关键词： Image segmentation Visualization object segmentation Task analysis object tracking Micromechanical devices Decoding videos video object segmentation segment-anything model decoupled memory

来源：评论

学校读者我要写书评

暂无评论

Adaptive Selection of Reference Frames for video object segmentation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 1057-1071页

作者： Hong, Lingyi Zhang, Wei Chen, Liangyu Zhang, Wenqiang Fan, Jianping Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China Lenovo Res AI Lab Beijing 100085 Peoples R China

video object segmentation is a challenging task in computer vision because the appearances of target objects might change drastically along the time in the video. To solve this problem, space-time memory (STM) networks are exploited to make use of the information from all the intermediate frames between the first frame and the current frame in the video. However, fully using the information from all the memory frames may make STM not practical for long videos. To overcome this issue, a novel method is developed in this paper to select the reference frames adaptively. First, an adaptive selection criterion is introduced to choose the reference frames with similar appearance and precise mask estimation, which can efficiently capture the rich information of the target object and overcome the challenges of appearance changes, occlusion, and model drift. Secondly, bi-matching (bi-scale and bi-direction) is conducted to obtain more robust correlations for objects of various scales and prevents multiple similar objects in the current frame from being mismatched with the same target object in the reference frame. Thirdly, a novel edge refinement technique is designed by using an edge detection network to obtain smooth edges from the outputs of edge confidence maps, where the edge confidence is quantized into ten sub-intervals to generate smooth edges step by step. Experimental results on the challenging benchmark datasets DAVIS-2016, DAVIS-2017, YouTube-VOS, and a Long-video dataset have demonstrated the effectiveness of our proposed approach to video object segmentation.

关键词： object segmentation Optical imaging Correlation Adaptation models Predictive models Bidirectional control Task analysis video object segmentation space-time memory adaptive reference selection deep convolutional networks

来源：评论

学校读者我要写书评

暂无评论

HFVOS: History-Future Integrated Dynamic Memory for video object segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR video TECHNOLOGY 2024年第10期34卷 10208-10222页

作者： Li, Wanyun Fan, Jack Guo, Pinxue Hong, Lingyi Zhang, Wei Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai 200433 Peoples R China Univ North Carolina Chapel Hill Dept Comp Sci Chapel Hill NC 27599 USA Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China

Memory-based methods have substantially enhanced the precision of video object segmentation (VOS) by storing features in an expanding memory bank. However, this comes at the cost of increased computational demands and storage overhead. While recent methods have sought to alleviate this issue via compression or selection strategies, their reliance solely on history cues and simple memory structures result in precision degradation and intrinsic limitations, such as error accumulation and poor robustness. In this paper, we introduce HFVOS, an efficient yet effective framework to bolster VOS performance in both speed and precision by meticulously considering the memory design with low redundancy, high accuracy, and adaptability. First, we construct a novel hierarchical memory update pipeline with the proposed Buffered Memory Mechanism, which incorporates both future and history cues to reduce redundancy and improve the utility of memory. Second, we propose an Adaptive Dual-stream Selection Network (ADSN) to carry out the adaptive selection and drop operations of the memory update, and integrate an ADSN based long-term memory to enhance the robustness, especially for long videos. Furthermore, to further boost HFVOS, a progressive selection loss is designed to facilitate ADSN gradually adapting to fewer features while preserving high precision. Experiments show that HFVOS achieves the state-of-the-art segmentation precision and speed on both short-term datasets (DAVIS-17 val: 86.8% J & F and 33.0 FPS, DAVIS-16 val: 92.0% J & F and 42.0 FPS) and long-term datasets (LVOS val: 58.0% J & F and 37.4 FPS).

关键词： Streaming media Memory management History Robustness Redundancy Pipelines Feature extraction video object segmentation dynamic memory bank real-time video object segmentation

来源：评论

学校读者我要写书评

暂无评论

Unified Spatio-Temporal Dynamic Routing for Efficient video object segmentation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第5期25卷 4512-4526页

作者： Dang, Jisheng Zheng, Huicheng Xu, Xiaohao Guo, Yulan Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China Guangdong Prov Key Lab Informat Secur Technol Guangzhou 510006 Peoples R China Univ Michigan Robot Dept Ann Arbor MI 48104 USA Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen Campus Shenzhen 518000 Peoples R China Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410073 Peoples R China

Existing methods for video object segmentation (VOS) have achieved significant success by performing semantic guidance, spatial constraint, or temporal consistency. However, VOS still remains highly challenging because it is difficult to collaboratively leverage spatial constraint, temporal consistency, and semantic guidance while reducing redundant information. In this paper, we propose an efficient unified spatio-temporal dynamic routing (STDR) framework to address VOS by achieving a better spatio-temporal balance while avoiding redundancy. Specifically, our unified spatio-temporal modeling contains three paths: 1) short-term spatial path is employed to mine the spatial constraints from the previous frame;2) long-term semantic path is used to capture semantic cues from the first reference frame with ground-truth labels;3) memory queue path is designed to efficiently exploit the temporal consistency of middle frames with a compact memory bank of constant size. To enhance the input of each path, we introduce a progressive contextual memory enhancement module to exploit the contextualized memory with growing receptive fields by progressively aggregating spatial contextual information from adjacent frames for each memory frame. Furthermore, we design a dynamic memory-routed module to globally refine the outputs of our three paths for unified modeling. Enhanced by the proposed modules, our STDR achieves state-of-the-art performance with fast speed on the DAVIS 2016, DAVIS 2017 Val/Test, YouTube-VOS 2018/2019, and real-world long-video benchmarks.

关键词： video object segmentation spatio-temporal dynamic routing progressive contextual memory enhancement spatial constraint temporal consistency

来源：评论

学校读者我要写书评

暂无评论

A Bayesian approach to video object segmentation via merging 3-D watershed volumes

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR video TECHNOLOGY 2005年第1期15卷 175-180页

作者： Tsai, YP Lai, CC Hung, YP Shih, ZC Acad Sinica Inst Informat Sci Taipei 115 Taiwan Natl Chiao Tung Univ Dept Comp & Informat Sci Hsinchu 300 Taiwan Natl Taiwan Univ Dept Comp Sci & Informat Engn Taipei 106 Taiwan Natl Chiao Tung Univ Dept Comp & Informat Sci Hsinchu 30050 Taiwan

In this letter, we propose a Bayesian approach to video object segmentation. Our method consists of two stages. In the first stage, we partition the video data into a set of three-dimensional (3-D) watershed volumes, where each watershed volume is a series of corresponding two-dimensional (2-D) image regions. These 2-D image regions are obtained by applying to each image frame the marker-controlled watershed segmentation, where the markers are extracted by first generating a set of initial markers via temporal tracking and then refining the markers with two shrinking schemes: the iterative adaptive erosion and the verification against a presimplified watershed segmentation. Next, in the second stage, we use a Markov random field to model the spatio-temporal relationship among the 3-D watershed volumes that are obtained from the first stage. Then, the desired video objects can be extracted by merging watershed volumes having similar motion characteristics within a Bayesian framework. A major advantage of this method is that it can take into account the global motion information contained in each watershed volume. Our experiments have shown that the proposed method has potential for extracting moving objects from a video sequence.

关键词： Markov random field three-dimensional (3-D) watershed volume video object segmentation watershed segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：