Work

Dublin City University and Partners' participation in the INS and VTT Tracks at TRECVid 2016

Year: 2016

Type: conference-paper

Abstract: Dublin City University participated with a consortium of colleagues from NUI Galway and Universitat Polit`ecnica de Catalunya in two tasks in TRECVid 2016, Instance Search (INS) and Video to Text (VTT). For the INS task we developed a framework consisting of face detection and representation and place detection and representation, with a user annotation of top-ranked videos. For the VTT task we ran 1,000 concept detectors from the VGG-16 deep CNN on 10 keyframes per video and submitted 4 runs for caption re-ranking, based on BM25, Fusion, Word2Vec and a fusion of baseline BM25 and Word2Vec. With the same pre-processing for caption generation we used an open source image-to-caption CNN-RNN toolkit NeuralTalk2 to generate a caption for each keyframe and combine them.

Source: Arrow@dit (Dublin Institute of Technology)

DOI: 10.13025/21353

Authors: Marsden, Mark, Mohedano, Eva, McGuinness, Kevin, Calafell, Andrea, Giro-I-Nieto, Xavier, Ó Connor, Noel E., Zhou, Jiang, Azevedo, Lucas, Daudert, Tobias, Davis, Brian, Hürlimann, Manuela, Afli, Haithem, Du, Jinhua, Ganguly, Debasis, Li, Wei, Way, Andy, Smeaton, Alan F.

Language: English

Topic: Video Analysis and Summarization

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Science Foundation Ireland, Insight SFI Research Centre for Data Analytics

Awards: G1383882326, G1637072894, G3989894238, ADAPT: Centre for Digital Content Platform Research, G4053123157, G5098725405, INSIGHT - Irelands Big Data and Analytics Research Centre, G8001517797

OpenAlex ID: W2560015768

FWCI: 0.347

Cites: 15

Cited by: 3

Related to: 10