Creating enriched YouTube media fragments with NERD using timed-text
ISWC 2012, 11th International Semantic Web Conference, Demo Session, November 11-15, 2012, Boston, USA
This demo enables the automatic creation of semantically annotated YouTube media fragments. A video is first ingested in the Synote system and a new method enables to retrieve its associated subtitles or closed captions. Next, NERD is used to extract named entities from the transcripts which are then temporally aligned with the video. The entities are disambiguated in the LOD cloud and a user interface enables to browse through the entities detected in a video or get more information. We evaluated our application with 60 videos from 3 YouTube channels.
Title: | Creating enriched YouTube media fragments with NERD using timed-text |
Keywords: | Media fragment, media annotation, NERD |
Type: | Poster / Demo |
Language: | English |
City: | Boston |
Country: | UNITED STATES |
Date: | November 2012 |
Department: | Data Science |
Eurecom ref: | 3806 |
Copyright: | CEUR |
Bibtex: | @poster / demo{EURECOM+3806, year = {2012}, title = {{C}reating enriched {Y}ou{T}ube media fragments with {NERD} using timed-text}, author = {{L}i, {Y}unjia and {R}izzo, {G}iuseppe and {T}roncy, {R}apha{\"e}l and {W}ald, {M}ike and {W}ills, {G}ary}, number = {EURECOM+3806}, month = {11}, institution = {Eurecom} address = {{B}oston, {UNITED} {STATES}}, url = {http://www.eurecom.fr/publication/3806} } |
See also: |
|
Permalink: http://www.eurecom.fr/publication/3806