Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Serafettin Tasci"'
Autor:
Dawei Li, C.-C. Jay Kuo, Jie Zhang, Shalini Ghosh, Larry Heck, Serafettin Tasci, Heming Zhang, Junting Zhang
Publikováno v:
WACV
Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) --- an abrupt degradation of performance on the original set of classes when the training objective is adapted to a newly added set of classes. E
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::20d677a2c0a827f3d0459267901b8327
https://doi.org/10.1109/wacv45572.2020.9093365
https://doi.org/10.1109/wacv45572.2020.9093365
Autor:
Larry S. Davis, Xianzhi Du, Dawei Li, Stephen Walsh, Xiaolong Wang, Jingwen Zhu, Cameron Upright, Serafettin Tasci
Publikováno v:
FG
Compared to the general semantic segmentation problem, portrait segmentation has higher precision requirement on boundary area. However, this problem has not been well studied in previous works. In this paper, we propose a boundary-sensitive deep neu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6277cb07335a3efcee181055e5fe659c
https://doi.org/10.1109/fg.2019.8756516
https://doi.org/10.1109/fg.2019.8756516
Publikováno v:
SEC
Object detection models shipped with camera-equipped edge devices cannot cover the objects of interest for every user. Therefore, the incremental learning capability is a critical feature for a robust and personalized object detection system that man
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::54916458c6ee0f525ca874f99c8fdec9
Autor:
Serafettin Tasci, Murat Demirbas
Publikováno v:
IEEE BigData
In-memory data grid (IMDG) is a new technology that enables scalable and low-latency processing of big data by sharding it over the RAMs of multiple servers. In this paper, we explore the design space of IMDGs to identify their advantages and avoid t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::894a240f3b25b594ce5202c63549cc04
https://doi.org/10.1109/bigdata.2015.7363959
https://doi.org/10.1109/bigdata.2015.7363959
Autor:
Murat Demirbas, Serafettin Tasci
Publikováno v:
IEEE BigData
For datacenter applications that require tight synchronization, transactions are commonly employed for achieving concurrency while preserving correctness. Unfortunately, distributed transactions are hard to scale due to the decentralized lock acquisi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bebac5d8689917d64bd012c6e4b7454b
https://doi.org/10.1109/bigdata.2015.7363762
https://doi.org/10.1109/bigdata.2015.7363762
Autor:
Murat Demirbas, Serafettin Tasci
Publikováno v:
Euro-Par 2013 Parallel Processing ISBN: 9783642400469
Euro-Par
Euro-Par
Bulk Synchronous Parallelism (BSP) provides a good model for parallel processing of many large-scale graph applications, however it is unsuitable/inefficient for graph applications that require coordination, such as graph-coloring, subcoloring, and c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5e474bdf7e09a4f4529e9298f12a91dc
https://doi.org/10.1007/978-3-642-40047-6_47
https://doi.org/10.1007/978-3-642-40047-6_47
Publikováno v:
ISCC
Concurrent execution is a big challenge for distributed systems programming and cloud computing. Using locks is the most common technique for developing distributed applications that require tight synchronization. Unfortunately, locking is manual, er
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5612250c7e170a7c75c0453c5ccfb2b
https://doi.org/10.1109/iscc.2012.6249404
https://doi.org/10.1109/iscc.2012.6249404
Publikováno v:
IPDPS
In wireless sensor network (WSN) deployments, Receiver-side Collision Detection (RCD) has been proposed for speeding up collaborative feedback collection from a single hop neighborhood. Using RCD, an initiator node can query the existence of a predic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::21d4b9fd2b59b2bdbcee655ef517a11c
https://doi.org/10.1109/ipdps.2011.39
https://doi.org/10.1109/ipdps.2011.39
Autor:
Serafettin Tasci, Tunga Güngör
Publikováno v:
ISCIS
Text categorization is the task of automatically assigning unlabeled text documents to some predefined category labels by means of an induction algorithm. Since the data in text categorization are high-dimensional, feature selection is broadly used i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c246c46923809f1c9ae35ed378b4b20d
https://doi.org/10.1109/iscis.2009.5291818
https://doi.org/10.1109/iscis.2009.5291818