The Experts below are selected from a list of 21771 Experts worldwide ranked by ideXlab platform
Song-chun Zhu - One of the best experts on this subject based on the ideXlab platform.
-
multi view people tracking via Hierarchical trajectory Composition
Computer Vision and Pattern Recognition, 2016Co-Authors: Xiaobai Liu, Yang Liu, Song-chun ZhuAbstract:This paper presents a Hierarchical Composition approach for multi-view object tracking. The key idea is to adaptively exploit multiple cues in both 2D and 3D, e.g., ground occupancy consistency, appearance similarity, motion coherence etc., which are mutually complementary while tracking the humans of interests over time. While feature online selection has been extensively studied in the past literature, it remains unclear how to effectively schedule these cues for the tracking purpose especially when encountering various challenges, e.g. occlusions, conjunctions, and appearance variations. To do so, we propose a Hierarchical Composition model and re-formulate multi-view multi-object tracking as a problem of Compositional structure optimization. We setup a set of Composition criteria, each of which corresponds to one particular cue. The Hierarchical Composition process is pursued by exploiting different criteria, which impose constraints between a graph node and its offsprings in the hierarchy. We learn the Composition criteria using MLE on annotated data and efficiently construct the Hierarchical graph by an iterative greedy pursuit algorithm. In the experiments, we demonstrate superior performance of our approach on three public datasets, one of which is newly created by us to test various challenges in multi-view multi-object tracking.
-
CVPR - Multi-view People Tracking via Hierarchical Trajectory Composition
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016Co-Authors: Xiaobai Liu, Yang Liu, Song-chun ZhuAbstract:This paper presents a Hierarchical Composition approach for multi-view object tracking. The key idea is to adaptively exploit multiple cues in both 2D and 3D, e.g., ground occupancy consistency, appearance similarity, motion coherence etc., which are mutually complementary while tracking the humans of interests over time. While feature online selection has been extensively studied in the past literature, it remains unclear how to effectively schedule these cues for the tracking purpose especially when encountering various challenges, e.g. occlusions, conjunctions, and appearance variations. To do so, we propose a Hierarchical Composition model and re-formulate multi-view multi-object tracking as a problem of Compositional structure optimization. We setup a set of Composition criteria, each of which corresponds to one particular cue. The Hierarchical Composition process is pursued by exploiting different criteria, which impose constraints between a graph node and its offsprings in the hierarchy. We learn the Composition criteria using MLE on annotated data and efficiently construct the Hierarchical graph by an iterative greedy pursuit algorithm. In the experiments, we demonstrate superior performance of our approach on three public datasets, one of which is newly created by us to test various challenges in multi-view multi-object tracking.
Kamel Barkaoui - One of the best experts on this subject based on the ideXlab platform.
-
RCIS - Towards a tile based LfP semantics
2008 Second International Conference on Research Challenges in Information Science, 2008Co-Authors: Aïcha Choutri, Faiza Belala, Kamel BarkaouiAbstract:LfP (Language for Prototyping) is an ADL (Architecture Description Language) with a Hierarchical and modular structure. In this paper, we propose tile logic (a rewriting logic extension) as a suitable semantic framework for this language. Indeed, it contributes to the formalization of LfP by providing a natural description for concurrency, synchronization and Hierarchical Composition aspects. A straight consequence of this work is the possibility to describe reconfigurable LfP architectures, and to handle with executable specification in Maude allowing Hierarchical formal verification.
-
Towards a Tile Based LfP Semantics
2008Co-Authors: Aïcha Choutri, Faiza Belala, Kamel BarkaouiAbstract:LfP (Language for Prototyping) is an ADL (Architecture Description Language) with a Hierarchical and modular structure. In this paper, we propose tile logic (a rewriting logic extension) as a suitable semantic framework for this language. Indeed, it contributes to the formalization of LfP by providing a natural description for concurrency, synchronization and Hierarchical Composition aspects. A straight consequence of this work is the possibility to describe reconfigurable LfP architectures, and to handle with executable specification in Maude allowing Hierarchical formal verification. For further information, please visit this web site.
Jerome Bonnet - One of the best experts on this subject based on the ideXlab platform.
-
Hierarchical Composition of reliable recombinase logic devices
Nature communications, 2019Co-Authors: Sarah Guiziou, Pauline Mayonove, Jerome BonnetAbstract:A major goal of synthetic biology is to reprogram living organisms to solve pressing challenges in manufacturing, environmental remediation, and healthcare. Recombinase devices can efficiently encode complex logic in many species, yet current designs are performed on a case-by-case basis, limiting their scalability and requiring time-consuming optimization. Here we provide a systematic framework for engineering reliable recombinase logic devices by Hierarchical Composition of well-characterized, optimized recombinase switches. We apply this framework to build a recombinase logic device family supporting up to 4-input Boolean logic within a multicellular system. This work enables straightforward implementation of multicellular recombinase logic and will support the predictable engineering of several classes of recombinase devices to reliably control cellular behavior.
-
Hierarchical Composition of reliable recombinase logic devices.
2018Co-Authors: Sarah Guiziou, Pauline Mayonove, Jerome BonnetAbstract:We provide a systematic framework for engineering reliable recombinase logic devices by Hierarchical Composition of well-characterized, optimized recombinase switches. We apply this framework to build a recombinase logic device family supporting up to 4-input Boolean logic. This work will support the predictable engineering of several classes of recombinase devices to reliably control cellular behavior.
Henrique N. Cunha - One of the best experts on this subject based on the ideXlab platform.
-
Enhancing IP cores specifications using Hierarchical Composition and set theory
Design Automation for Embedded Systems, 2011Co-Authors: Cássio L. Rodrigues, Karina Rocha Gomes Da Silva, Henrique N. Cunha, Jorge C. A. Figueiredo, Dalton D. S. Guerrero, Elmar MelcherAbstract:During the functional verification, complex interactions between multiple blocks that compose an Intellectual Property (IP) core can reveal hard-to-find bugs. Functional verification specifications must be precise to assure these interactions occur during the simulation. In this work, we are proposing a technique for improving the functional verification specification of individual blocks, preserving the occurrence of these interaction scenarios in the Composition phase. Our approach was implemented for the VeriSC methodology, a SystemC-based functional verification methodology. After each block that composes the IP core was stand-alone verified, we exploit the Composition phase using set theory to increase the coverage numbers and to justify why some of these numbers cannot, or need not, reach 100%. By applying our approach in a MPEG 4 video decoder design, we show how our work can save functional verification time during the Hierarchical Composition. Using mutation based-tests, we demonstrate that our work can contribute to error detection. Furthermore, we demonstrate the effectiveness of our approach with regard to traditional structural coverage metrics, such as line coverage and branch coverage.
-
improving functional verification of embedded systems using Hierarchical Composition and set theory
ACM Symposium on Applied Computing, 2009Co-Authors: Cássio L. Rodrigues, Karina Rocha Gomes Da Silva, Henrique N. CunhaAbstract:During functional verification, complex interactions between multiple modules that compose a digital circuit design can reveal hard-to-find bugs. Functional coverage specifications must be precise to assure these interactions occur during the simulation. We are proposing a technique for improving the functional verification specification of individual modules, preserving the occurrence of these interactions scenarios in the Composition phase. We obtain these new specifications in a deductive way, by means of set theory. Using experimental results, we show how our work can contribute to error detection and save functional verification time.
-
SAC - Improving functional verification of embedded systems using Hierarchical Composition and set theory
Proceedings of the 2009 ACM symposium on Applied Computing - SAC '09, 2009Co-Authors: Cássio L. Rodrigues, Karina Rocha Gomes Da Silva, Henrique N. CunhaAbstract:During functional verification, complex interactions between multiple modules that compose a digital circuit design can reveal hard-to-find bugs. Functional coverage specifications must be precise to assure these interactions occur during the simulation. We are proposing a technique for improving the functional verification specification of individual modules, preserving the occurrence of these interactions scenarios in the Composition phase. We obtain these new specifications in a deductive way, by means of set theory. Using experimental results, we show how our work can contribute to error detection and save functional verification time.
Xiaobai Liu - One of the best experts on this subject based on the ideXlab platform.
-
multi view people tracking via Hierarchical trajectory Composition
Computer Vision and Pattern Recognition, 2016Co-Authors: Xiaobai Liu, Yang Liu, Song-chun ZhuAbstract:This paper presents a Hierarchical Composition approach for multi-view object tracking. The key idea is to adaptively exploit multiple cues in both 2D and 3D, e.g., ground occupancy consistency, appearance similarity, motion coherence etc., which are mutually complementary while tracking the humans of interests over time. While feature online selection has been extensively studied in the past literature, it remains unclear how to effectively schedule these cues for the tracking purpose especially when encountering various challenges, e.g. occlusions, conjunctions, and appearance variations. To do so, we propose a Hierarchical Composition model and re-formulate multi-view multi-object tracking as a problem of Compositional structure optimization. We setup a set of Composition criteria, each of which corresponds to one particular cue. The Hierarchical Composition process is pursued by exploiting different criteria, which impose constraints between a graph node and its offsprings in the hierarchy. We learn the Composition criteria using MLE on annotated data and efficiently construct the Hierarchical graph by an iterative greedy pursuit algorithm. In the experiments, we demonstrate superior performance of our approach on three public datasets, one of which is newly created by us to test various challenges in multi-view multi-object tracking.
-
CVPR - Multi-view People Tracking via Hierarchical Trajectory Composition
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016Co-Authors: Xiaobai Liu, Yang Liu, Song-chun ZhuAbstract:This paper presents a Hierarchical Composition approach for multi-view object tracking. The key idea is to adaptively exploit multiple cues in both 2D and 3D, e.g., ground occupancy consistency, appearance similarity, motion coherence etc., which are mutually complementary while tracking the humans of interests over time. While feature online selection has been extensively studied in the past literature, it remains unclear how to effectively schedule these cues for the tracking purpose especially when encountering various challenges, e.g. occlusions, conjunctions, and appearance variations. To do so, we propose a Hierarchical Composition model and re-formulate multi-view multi-object tracking as a problem of Compositional structure optimization. We setup a set of Composition criteria, each of which corresponds to one particular cue. The Hierarchical Composition process is pursued by exploiting different criteria, which impose constraints between a graph node and its offsprings in the hierarchy. We learn the Composition criteria using MLE on annotated data and efficiently construct the Hierarchical graph by an iterative greedy pursuit algorithm. In the experiments, we demonstrate superior performance of our approach on three public datasets, one of which is newly created by us to test various challenges in multi-view multi-object tracking.