publication . Article . Conference object . Other literature type . 2017

Query And Keyframe Representations For Ad-Hoc Video Search

Ionescu, Bogdan; Sebe, Nicu; Feng, Jiashi; Larson, Martha; Lienhart, Rainer; Snoek, Cees; Markatopoulou, Foteini; Galanopoulos, Damianos; Mezaris, Vasileios; Patras, Ioannis;
Open Access
  • Published: 06 Jun 2017
  • Publisher: Zenodo
<p>This paper presents a fully-automatic method that combines video concept detection and textual query analysis in order to solve the problem of ad-hoc video search. We present a set of NLP steps that cleverly analyse different parts of the query in order to convert it to related semantic concepts, we propose a new method for transforming concept-based keyframe and query representations into a common semantic embedding space, and we show that our proposed combination of concept-based representations with their corresponding semantic embeddings results to improved video search accuracy. Our experiments in the TRECVID AVS 2016 and the Video Search 2008 datasets s...
free text keywords: video concept detection, textual query analysis, Video search, Zero-shot learning, Visual analysis, Uncategorized, zenodo, Zero shot learning, Query expansion, Concept search, Video tracking, Information retrieval, Query analysis, Computer science, Web search query, Embedding, TRECVID
Funded by
Training towards a society of data-savvy information professionals to enable open leadership innovation
  • Funder: European Commission (EC)
  • Project Code: 693092
  • Funding stream: H2020 | RIA
In Video Veritas – Verification of Social Media Video Content for the News Industry
  • Funder: European Commission (EC)
  • Project Code: 687786
  • Funding stream: H2020 | IA
Download fromView all 9 versions
Other literature type . 2017
Provider: Datacite
Conference object . 2017
Provider: ZENODO
Any information missing or wrong?Report an Issue