The Experts below are selected from a list of 66129 Experts worldwide ranked by ideXlab platform
Qingming Huang - One of the best experts on this subject based on the ideXlab platform.
-
@ICT: attention-based Virtual Content insertion
Multimedia Systems, 2011Co-Authors: Huiying Liu, Qingming Huang, Shuqiang JiangAbstract:In this paper, we propose an attention-based Virtual Content insertion solution, called @ICT. Virtual Content insertion (VCI) is an emerging application of video analysis and has been used in video augmentation and advertisement insertion. An ideal VCI solution should make the inserted Virtual Content being noticed by audiences and at the same time should not interfere with audiences’ viewing experience on the original Content. To balance these two conflicting issues, meaning high attention and low intrusiveness, we choose higher attentive shots as insertion time while determine insertion place and Content interdependently by considering lower attention together with visual consistency. We also propose a measurement of intrusiveness from the viewpoint of visual attention. Furthermore, @ICT includes an in-scene insertion module, which embeds the Virtual Content into the videos with higher vividness and lower intrusiveness. @ICT is able to obtain an optimal balance between the noticing of the Virtual Content by audiences and disruption of viewing experience to the original Content. It needs little prior knowledge and is applied to general videos. Extensive quantitative and qualitative evaluations on the VCI result have verified the effectiveness of the solution.
-
a generic Virtual Content insertion system based on visual attention analysis
ACM Multimedia, 2008Co-Authors: Huiying Liu, Shuqiang Jiang, Qingming HuangAbstract:This paper presents a generic Virtual Content Insertion (VCI) system based on visual attention analysis. VCI is an emerging application of video analysis and has been used in video augmentation and advertisement insertion. There are three critical issues for a VCI system: when (time), where (place) and how (method) to insert the Virtual Content (VC) into the video. Our system selects the insertion time and place by performing temporal and spatial attention analysis, which predicts the attention change along time and the attended region over space. In order to enable the inserted VC to be noticed by audience while not to interrupt the audience's viewing experience to the original Content, the VC should be inserted at the time when the video Content attracts much audience attention and at the place where attracts less. Dynamic insertion is performed by using Global Motion Estimation (GME) and affine transformation. Our VCI system is able to obtain an optimal balance between the notice of the VC by audience and disruption of viewing experience to the original Content. Extensive subjective evaluations based on user study on the VCI result have verified the effectiveness of the system.
-
ICME - Lower attentive region detection for Virtual Content insertion in broadcast video
2008 IEEE International Conference on Multimedia and Expo, 2008Co-Authors: Huiying Liu, Shuqiang Jiang, Qingming HuangAbstract:Virtual Content Insertion (VCI) is an emerging application of video analysis. For VCI the spatial position is very important as improper placement will make the insertion intrusive. To choose the spatial position, we propose the notation of Lower Attentive Region (LAR) and provide a generic framework of LAR detection for broadcast video. An LAR is defined, from the cognition point of view, as a region of the video frame which attracts less audiencepsilas attention. It can be changed with little interruption to the main Content of the original video. The proposed LAR detection framework includes both bottom-up and top-down modules and can be adapted to all types of videos. Finally we apply the proposed LAR detection approach to broadcast sports video by integrating domain knowledge. The Experiments on LAR detection and VCI in broadcast video demonstrate the effectiveness of the proposed method.
-
ACM Multimedia - A generic Virtual Content insertion system based on visual attention analysis
Proceeding of the 16th ACM international conference on Multimedia - MM '08, 2008Co-Authors: Huiying Liu, Shuqiang Jiang, Qingming HuangAbstract:This paper presents a generic Virtual Content Insertion (VCI) system based on visual attention analysis. VCI is an emerging application of video analysis and has been used in video augmentation and advertisement insertion. There are three critical issues for a VCI system: when (time), where (place) and how (method) to insert the Virtual Content (VC) into the video. Our system selects the insertion time and place by performing temporal and spatial attention analysis, which predicts the attention change along time and the attended region over space. In order to enable the inserted VC to be noticed by audience while not to interrupt the audience's viewing experience to the original Content, the VC should be inserted at the time when the video Content attracts much audience attention and at the place where attracts less. Dynamic insertion is performed by using Global Motion Estimation (GME) and affine transformation. Our VCI system is able to obtain an optimal balance between the notice of the VC by audience and disruption of viewing experience to the original Content. Extensive subjective evaluations based on user study on the VCI result have verified the effectiveness of the system.
Huiying Liu - One of the best experts on this subject based on the ideXlab platform.
-
@ICT: attention-based Virtual Content insertion
Multimedia Systems, 2011Co-Authors: Huiying Liu, Qingming Huang, Shuqiang JiangAbstract:In this paper, we propose an attention-based Virtual Content insertion solution, called @ICT. Virtual Content insertion (VCI) is an emerging application of video analysis and has been used in video augmentation and advertisement insertion. An ideal VCI solution should make the inserted Virtual Content being noticed by audiences and at the same time should not interfere with audiences’ viewing experience on the original Content. To balance these two conflicting issues, meaning high attention and low intrusiveness, we choose higher attentive shots as insertion time while determine insertion place and Content interdependently by considering lower attention together with visual consistency. We also propose a measurement of intrusiveness from the viewpoint of visual attention. Furthermore, @ICT includes an in-scene insertion module, which embeds the Virtual Content into the videos with higher vividness and lower intrusiveness. @ICT is able to obtain an optimal balance between the noticing of the Virtual Content by audiences and disruption of viewing experience to the original Content. It needs little prior knowledge and is applied to general videos. Extensive quantitative and qualitative evaluations on the VCI result have verified the effectiveness of the solution.
-
a generic Virtual Content insertion system based on visual attention analysis
ACM Multimedia, 2008Co-Authors: Huiying Liu, Shuqiang Jiang, Qingming HuangAbstract:This paper presents a generic Virtual Content Insertion (VCI) system based on visual attention analysis. VCI is an emerging application of video analysis and has been used in video augmentation and advertisement insertion. There are three critical issues for a VCI system: when (time), where (place) and how (method) to insert the Virtual Content (VC) into the video. Our system selects the insertion time and place by performing temporal and spatial attention analysis, which predicts the attention change along time and the attended region over space. In order to enable the inserted VC to be noticed by audience while not to interrupt the audience's viewing experience to the original Content, the VC should be inserted at the time when the video Content attracts much audience attention and at the place where attracts less. Dynamic insertion is performed by using Global Motion Estimation (GME) and affine transformation. Our VCI system is able to obtain an optimal balance between the notice of the VC by audience and disruption of viewing experience to the original Content. Extensive subjective evaluations based on user study on the VCI result have verified the effectiveness of the system.
-
ICME - Lower attentive region detection for Virtual Content insertion in broadcast video
2008 IEEE International Conference on Multimedia and Expo, 2008Co-Authors: Huiying Liu, Shuqiang Jiang, Qingming HuangAbstract:Virtual Content Insertion (VCI) is an emerging application of video analysis. For VCI the spatial position is very important as improper placement will make the insertion intrusive. To choose the spatial position, we propose the notation of Lower Attentive Region (LAR) and provide a generic framework of LAR detection for broadcast video. An LAR is defined, from the cognition point of view, as a region of the video frame which attracts less audiencepsilas attention. It can be changed with little interruption to the main Content of the original video. The proposed LAR detection framework includes both bottom-up and top-down modules and can be adapted to all types of videos. Finally we apply the proposed LAR detection approach to broadcast sports video by integrating domain knowledge. The Experiments on LAR detection and VCI in broadcast video demonstrate the effectiveness of the proposed method.
-
ACM Multimedia - A generic Virtual Content insertion system based on visual attention analysis
Proceeding of the 16th ACM international conference on Multimedia - MM '08, 2008Co-Authors: Huiying Liu, Shuqiang Jiang, Qingming HuangAbstract:This paper presents a generic Virtual Content Insertion (VCI) system based on visual attention analysis. VCI is an emerging application of video analysis and has been used in video augmentation and advertisement insertion. There are three critical issues for a VCI system: when (time), where (place) and how (method) to insert the Virtual Content (VC) into the video. Our system selects the insertion time and place by performing temporal and spatial attention analysis, which predicts the attention change along time and the attended region over space. In order to enable the inserted VC to be noticed by audience while not to interrupt the audience's viewing experience to the original Content, the VC should be inserted at the time when the video Content attracts much audience attention and at the place where attracts less. Dynamic insertion is performed by using Global Motion Estimation (GME) and affine transformation. Our VCI system is able to obtain an optimal balance between the notice of the VC by audience and disruption of viewing experience to the original Content. Extensive subjective evaluations based on user study on the VCI result have verified the effectiveness of the system.
Blair Macintyre - One of the best experts on this subject based on the ideXlab platform.
-
a non photorealistic rendering framework with temporal coherence for augmented reality
International Symposium on Mixed and Augmented Reality, 2012Co-Authors: Jiajian Chen, Greg Turk, Blair MacintyreAbstract:Many augmented reality (AR) applications require a seamless blending of real and Virtual Content as key to increased immersion and improved user experiences. Photorealistic and non-photorealistic rendering (NPR) are two ways to achieve this goal. Compared with photorealistic rendering, NPR stylizes both the real and Virtual Content and makes them indistinguishable. Maintaining temporal coherence is a key challenge in NPR. We propose a NPR framework with support for temporal coherence by leveraging model-space information. Our systems targets painterly rendering styles of NPR. There are three major steps in this rendering framework for creating coherent results: tensor field creation, brush anchor placement, and brush stroke reshaping. To achieve temporal coherence for the final rendered results, we propose a new projection-based surface sampling algorithm which generates anchor points on model surfaces. The 2D projections of these samples are uniformly distributed in image space for optimal brush stroke placement. We also propose a general method for averaging various properties of brush stroke textures, such as their skeletons and colors, to further improve the temporal coherence. We apply these methods to both static and animated models to create a painterly rendering style for AR. Compared with existing image space algorithms our method renders AR with NPR effects with a high degree of coherence.
-
ISMAR - A non-photorealistic rendering framework with temporal coherence for augmented reality
2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), 2012Co-Authors: Jiajian Chen, Greg Turk, Blair MacintyreAbstract:Many augmented reality (AR) applications require a seamless blending of real and Virtual Content as key to increased immersion and improved user experiences. Photorealistic and non-photorealistic rendering (NPR) are two ways to achieve this goal. Compared with photorealistic rendering, NPR stylizes both the real and Virtual Content and makes them indistinguishable. Maintaining temporal coherence is a key challenge in NPR. We propose a NPR framework with support for temporal coherence by leveraging model-space information. Our systems targets painterly rendering styles of NPR. There are three major steps in this rendering framework for creating coherent results: tensor field creation, brush anchor placement, and brush stroke reshaping. To achieve temporal coherence for the final rendered results, we propose a new projection-based surface sampling algorithm which generates anchor points on model surfaces. The 2D projections of these samples are uniformly distributed in image space for optimal brush stroke placement. We also propose a general method for averaging various properties of brush stroke textures, such as their skeletons and colors, to further improve the temporal coherence. We apply these methods to both static and animated models to create a painterly rendering style for AR. Compared with existing image space algorithms our method renders AR with NPR effects with a high degree of coherence.
Dan Liao - One of the best experts on this subject based on the ideXlab platform.
-
Energy-efficient Virtual Content distribution network provisioning in cloud-based data centers
Future Generation Computer Systems, 2018Co-Authors: Dan Liao, Gang Sun, Yang Guanghua, Victor ChangAbstract:Abstract Cloud-based Content distribution networks (CDNs) consist of multiple servers that consume large amounts of energy. However, with the development of a cloud-based software defined network (SDN), a new paradigm of the Virtual Content distribution network (vCDN) has emerged. In an emerging cloud-based vCDN environment, the development and adjustment of vCDN components has become easier with the aid of SDN technology. This transformation provides the opportunity to use vCDNs to reduce energy consumption by adjusting the scale of the vCDN components. Energy costs can be reduced by deactivating the commercial servers carrying the software components of the vCDN, such as replica servers, the firewall or routers. In addition, the CDN requires a high service level agreement (SLA) to respond to clients’ requests, potentially consuming large amounts of energy. In this research, we focus on the issue of the energy savings of a CDN in a cloud computing environment while maintaining a high quality of service (QoS). We propose an approximate algorithm termed max flow forecast (MFF) to determine the number of software components in the vCDN. Additionally, we use a real traffic trace from a website to assess our algorithm. The experimental results show that MFF can produce a larger energy reduction than the existing algorithms for an identical SLA. We fully justify our research as a good example for the emerging cloud.
-
The cost-efficient deployment of replica servers in Virtual Content distribution networks for data fusion
Information Sciences, 2018Co-Authors: Gang Sun, Yang Guanghua, Victor Chang, Dan LiaoAbstract:Abstract Content distribution networks (CDNs) play an important role in distributing Content between end users and servers because they can effectively reduce response delays and bandwidth consumption by deploying sets of servers close to end users for service provision. A remaining challenge to CDN deployment is how to efficiently place the replica servers while guaranteeing the quality of service (QoS). As a newly emerging technology, network function Virtualization (NFV) facilitates the use of network function software and enables the deployment of different network functions on networked commercial servers. Virtual CDNs are among the most relevant cases that could benefit from NFV. In this paper, we study the problem of efficiently deploying replica servers (middle boxes) in cloud data centers via NFV. We propose an approximation algorithm based on spectral clustering theory to solve the replica server placement problem within an NFV environment. We conduct simulations using local and large-scale data centers to evaluate the performance of our proposed algorithm. The simulation results show that our algorithm achieves lower deployment costs and improved data fusion while optimizing nodes, services and data processing.
Theo Lynn - One of the best experts on this subject based on the ideXlab platform.
-
Towards simulation and optimization of cache placement on large Virtual Content distribution networks
Journal of Computational Science, 2020Co-Authors: Christos K. Filelis-papadopoulos, Patricia Takako Endo, James M. Byrne, Konstantinos M. Giannoutakis, George A. Gravvanis, Dimitrios Tzovaras, Malika Bendechache, Sergej Svorobej, Theo LynnAbstract:Abstract IP video traffic is forecast to be 82% of all IP traffic by 2022. Traditionally, Content distribution networks (CDN) were used extensively to meet quality of service levels for IP video services. To handle the dramatic growth in video traffic, CDN operators are migrating their infrastructure to the cloud and fog in order to leverage its greater availability and flexibility. For hyperscale deployments, energy consumption, cache placement, and resource availability can be analyzed using simulation in order to improve resource utilization and performance. Recently, a discrete-time simulator for modelling hierarchical Virtual CDNs (vCDNs) was proposed with reduced memory requirements and increased performance using multi-core systems to cater for the scale and complexity of these networks. The first iteration of this discrete-time simulator featured a number of limitations impacting accuracy and applicability: it supports only tree-based topology structures, the results are computed per level, and requests of the same Content differ only in time duration. In this paper, we present an improved simulation framework that (a) supports graph-based network topologies, (b) requests have been reconstituted for differentiation of requirements, and (c) statistics are now computed per site and network metrics per link, improving granularity and parallel performance. Moreover, we also propose a two phase optimization scheme that makes use of simulation outputs to guide the search for optimal cache placements. In order to evaluate our proposal, we simulate a vCDN network based on real traces obtained from the BT vCDN infrastructure, and analyze performance and scalability aspects.
-
ISCC - Analyzing resource distribution over a real-world large-scale Virtual Content infrastructure
2019 IEEE Symposium on Computers and Communications (ISCC), 2019Co-Authors: Patricia Takako Endo, James M. Byrne, Theo Lynn, Radhika Loomba, Ruth Quinn, Christos K. Filelis-papadopoulos, Konstantinos M. Giannoutakis, George A. Gravvanis, Dimitrios Tzovaras, Peter WillisAbstract:Communication service providers (CSPs) face competitive pressure to increase infrastructure utilization and reduce operational costs while at the same time maximize bandwidth and maintain quality of service for end users. Content Distribution Networks (CDNs) are widely used to achieve these goals by optimally distributing Content to cache servers at the edge, access and core networks. More recently, Virtualization and cloud computing are being used to deploy and utilize Virtual Content Delivery Networks (vCDNs) to reduce costs and increase elasticity while avoiding performance, quality, reliability and availability limitations that characterize traditional CDNs. In order to study the effectiveness of Virtual cache placements and optimal distribution over a real-world large-scale vCDN infrastructure, we model and simulate BT’s network using a novel parallel simulation framework. Results show that Virtual cache placement impacts on the number of accepted requests, resource consumption (compute and network), and end-user network latency. We also present a trade-off analysis between infrastructure provider utility and service customer utility to quantity the number and distribution of these Virtual cache placements and to determine the optimal number of Virtual cache servers that should be deployed.
