TY - JOUR
T1 - Strategies for searching video content with text queries or video examples
AU - Yu, Shoou I.
AU - Xu, Shicheng
AU - Ma, Zhigang
AU - Li, Huan
AU - Hauptmann, Alexander G.
AU - Chang, Xiaojun
AU - Yang, Yi
AU - Meng, Deyu
AU - Lin, Ming
AU - Lan, Zhenzhong
AU - Gan, Chuang
AU - Xu, Zhongwen
AU - Mao, Zexi
AU - Li, Xuanchong
AU - Jiang, Lu
AU - Du, Xingzhong
PY - 2016
Y1 - 2016
N2 - The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search. However, metadata is often lacking for user-generated videos, thus these videos are unsearchable by current search engines. Therefore, content-based video retrieval (CBVR) tackles this metadata-scarcity problem by directly analyzing the visual and audio streams of each video. CBVR encompasses multiple research topics, including low-level feature design, feature fusion, semantic detector training and video search/reranking. We present novel strategies in these topics to enhance CBVR in both accuracy and speed under different query inputs, including pure textual queries and query by video examples. Our proposed strategies have been incorporated into our submission for the TRECVID 2014 Multimedia Event Detection evaluation, where our system outperformed other submissions in both text queries and video example queries, thus demonstrating the effectiveness of our proposed approaches.
AB - The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search. However, metadata is often lacking for user-generated videos, thus these videos are unsearchable by current search engines. Therefore, content-based video retrieval (CBVR) tackles this metadata-scarcity problem by directly analyzing the visual and audio streams of each video. CBVR encompasses multiple research topics, including low-level feature design, feature fusion, semantic detector training and video search/reranking. We present novel strategies in these topics to enhance CBVR in both accuracy and speed under different query inputs, including pure textual queries and query by video examples. Our proposed strategies have been incorporated into our submission for the TRECVID 2014 Multimedia Event Detection evaluation, where our system outperformed other submissions in both text queries and video example queries, thus demonstrating the effectiveness of our proposed approaches.
KW - Content-based Video Retrieval
KW - Motion & Image Features
KW - Multimedia Event Detection
KW - Multimodal Fusion
KW - Reranking
KW - Semantic Concept Detectors
UR - http://www.scopus.com/inward/record.url?scp=84979643061&partnerID=8YFLogxK
U2 - 10.3169/mta.4.227
DO - 10.3169/mta.4.227
M3 - Article
AN - SCOPUS:84979643061
SN - 2186-7364
VL - 4
SP - 227
EP - 238
JO - ITE Transactions on Media Technology and Applications
JF - ITE Transactions on Media Technology and Applications
IS - 3
ER -