publication . Conference object . 2020

Attention Mechanisms, Signal Encodings and Fusion Strategies for Improved Ad-hoc Video Search with Dual Encoding Networks.

Damianos Galanopoulos; Vasileios Mezaris;
Open Access
  • Published: 07 Jun 2020
  • Publisher: ACM
Abstract
In this paper, the problem of unlabeled video retrieval using textual queries is addressed. We present an extended dual encoding network which makes use of more than one encodings of the visual and textual content, as well as two different attention mechanisms. The latter serve the purpose of highlighting temporal locations in every modality that can contribute more to effective retrieval. The different encodings of the visual and textual inputs, along with early/late fusion strategies, are examined for further improving performance. Experimental evaluations and comparisons with state-of-the-art methods document the merit of the proposed network.
Subjects
free text keywords: Video search, Video retrieval, Ad-hoc video search, Deep learning, Dual encoding network, Attention mechanism, Speech recognition, Encoding (memory), Fusion, Computer science
Funded by
EC| ReTV
Project
ReTV
Enhancing and Re-Purposing TV Content for Trans-Vector Engagement
  • Funder: European Commission (EC)
  • Project Code: 780656
  • Funding stream: H2020 | RIA
Download fromView all 2 versions
ZENODO
Conference object . 2020
Provider: ZENODO
https://dl.acm.org/doi/pdf/10....
Conference object . 2020
Provider: Crossref
Any information missing or wrong?Report an Issue