Temat: visual search - Katalog OPAC zbiorów

Skocz do pozycji: 1.

Tytuł:: The Effects of Hearing Protectors on Auditory Localization: Evidence From Audio-Visual Target Acquisition
Autorzy:: Bolia, R. S.
McKinley, R. L.
Powiązania:: https://bibliotekanauki.pl/articles/90772.pdf
Data publikacji:: 2000
Wydawca:: Centralny Instytut Ochrony Pracy
Tematy:: auditory localization
hearing protection
visual search
ochrona słuchu
środowisko pracy
lokalizacja źródła dźwięku
Opis:: Response times (RT) in an audio-visual target acquisition task were collected from 3 participants while wearing either circumaural earmuffs, foam earplugs, or no hearing protection. Analyses revealed that participants took significantly longer to locate and identify an audio-visual target in both hearing protector conditions than they did in the unoccluded condition, suggesting a disturbance of the cues used by listeners to localize sounds in space. RTs were significantly faster in both hearing protector conditions than in a non-audio control condition, indicating that auditory localization was not completely disrupted. Results are discussed in terms of safety issues involved with wearing hearing protectors in an occupational environment.
Źródło:: International Journal of Occupational Safety and Ergonomics; 2000, 6, 3; 309-319
1080-3548
Pojawia się w:: International Journal of Occupational Safety and Ergonomics
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 2.

Tytuł:: Exploring the context of maritime SAR missions using visual data mining techniques
Autorzy:: Sonninen, M.
Goerlandt, F.
Powiązania:: https://bibliotekanauki.pl/articles/135224.pdf
Data publikacji:: 2015
Wydawca:: Akademia Morska w Szczecinie. Wydawnictwo AMSz
Tematy:: visual data mining
multidimensional data
maritime search and rescue
recreational boating
boating safety
maritime safety
Opis:: The environmental conditions in the Gulf of Finland vary significantly in different locations. In addition, the gulf is a busy and important area for waterway traffic and international trade throughout the year. In summer, the area is ideal for recreational activities such as boating and other water-related activities. Water accidents occur due to different factors and under varying weather conditions. This paper introduces a visual data mining analysis applied to Search and Rescue (SAR) missions related to recreational boating. Starting from a SAR operations database, an integrated database was constructed by adding weather and wave data. The aim was to compare the different mission types as well as the activity of different SAR organisations during challenging wind and wave conditions. The investigation was performed using visual analysis techniques. The densest areas of challenging wind and wave conditions were found in the western and eastern parts of the gulf. Other investigated parameters were travelled distances and occurrence of the incidents during different times of day. A more detailed analysis was conducted for one dataset.
Źródło:: Zeszyty Naukowe Akademii Morskiej w Szczecinie; 2015, 43 (115); 79-88
1733-8670
2392-0378
Pojawia się w:: Zeszyty Naukowe Akademii Morskiej w Szczecinie
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 3.

Tytuł:: Visual History Archive jako multimedialne narzędzie pracy z żywą historią XX wieku
Visual History Archive as a Multimedia Tool for Working with the Vivid History of the Twentieth Century
Autorzy:: MACIĄG, ANNA
LIPIŃSKI, SEWERYN
Powiązania:: https://bibliotekanauki.pl/articles/456218.pdf
Data publikacji:: 2018
Wydawca:: Uniwersytet Rzeszowski
Tematy:: Survivors of the Shoah Visual History Foundation
historia mówiona
system wyszukiwania
archiwum multimedialne
oral history
search system
multi-media archive
Opis:: Praca ma na celu opis i refleksję nad narzędziem stworzonym do przeszukiwania największego na świecie zbioru relacji video Survivors of the Shoah Visual History Foundation nagranych metoda oral history. Zbiór zawierający 52 tys. nagrań ze świadkami historii został opatrzony 65 tys. haseł indeksowych. Nagrania opisane są terminami ze wszelkich dziedzin i obszarów życia, minuta po minucie. Jest to jedyny na świecie, wciąż mało znany w Polsce system, który błyskawicznie pozwala odnaleźć fragmenty o konkretnej tematyce spośród ponad 7 mln minut nagrań. Choć dla użytkownika jest to ogromne udogodnienie, może wpływać na pobieżną pracę z narracjami historii mówionej, których celem pierwotnym jest ukazanie procesu pamiętania i doświadczeń z przeszłości bardziej niż pojedynczych faktów.
The work aim is to describe and reflect on the tool created to search the world's largest collection of video individual testimonies. The Visual History Archive is an online portal from USC Shoah Foundation that allows users to search through and view 52,000 oral history audiovisual testimonies of survivors and witnesses of the 2nd word war. Each video testimony has been indexed by 62,000 terms by assigning them to the relevant one-minute segments of each testimony. That allows you to find fragments about specific topics from over 7 million minutes of recordings. It is the only system in the world, still hardly known in Poland. While it brings users great conven-ience, it can affect a cursory work with narratives. This is because the primary purpose oral history is to show the process of remembering and experiences the past more than finding single facts.
Źródło:: Edukacja-Technika-Informatyka; 2018, 9, 3; 287-292
2080-9069
Pojawia się w:: Edukacja-Technika-Informatyka
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 4.

Tytuł:: Hybrid end-to-end approach integrating online learning with face-identification system
Autorzy:: Nguyene, Dat Van
Nguyen, Son Trung
Pham, Thi Hong Anh
Pham, Van Toan
Hoang, Thao Thu
Thanh, Ta Minh
Powiązania:: https://bibliotekanauki.pl/articles/27312886.pdf
Data publikacji:: 2023
Wydawca:: Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:: facial recognition
visual search engine
end-to-end applications
online learning
ElasticSearch (ES)
ES
Opis:: Facial recognition has been one of the most intriguing and exciting research topics over the last few years. It involves multiple face-based algorithms such asfacial detection, facial alignment, facial representation, and facial recognition. However, all of these algorithms are derived from large deep-learning architectures, leading to limitations in development, scalability, accuracy, and deployment for public use with mere CPU servers. Also, large data sets that contain hundreds of thousands of records are often required for training purposes. In this paper, we propose a complete pipeline for an effective face-recognition application that requires only a small data set of Vietnamese celebrities and a CPU for training, solving the problem of data leakage, and the need for GPU devices. The pipeline is based on the combination of a conversion algorithm from face vectors to string tokens and the indexing & retrieval process by Elasticsearch, thereby tackling the problem of online learning in facial recognition. Compared with other popular algorithms on the same data set, our proposed pipeline not only outperforms the counterpart in terms of accuracy but also delivers faster inference, which is essential to real-time applications.
Źródło:: Computer Science; 2023, 24 (1); 141--161
1508-2806
2300-7036
Pojawia się w:: Computer Science
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Informacja

Wyszukujesz frazę "visual search" wg kryterium: Temat

Źródło danych

Dostawca treści

Kolekcja

Rok wydania

Wydawca

Temat

Autor

Typ dokumentu

Język