Learning from Web Videos for Event Classification - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Circuits and Systems for Video Technology Year : 2018

Learning from Web Videos for Event Classification


Traditional approaches for classifying event videos rely on a manually curated training dataset. While this paradigm has achieved excellent results on benchmarks such as TrecVid multimedia event detection (MED) challenge datasets, it is restricted by the effort involved in careful annotation. Recent approaches have attempted to address the need for annotation by automatically extracting images from the web, or generating queries to retrieve videos. In the former case, they fail to exploit additional cues provided by video data, while in the latter, they still require some manual annotation to generate relevant queries. We take an alternate approach in this paper, leveraging the synergy between visual video data and the associated textual metadata, to learn event classifiers without manually annotating any videos. Specifically, we first collect a video dataset with queries constructed automatically from textual description of events, prune irrelevant videos with text and video data, and then learn the corresponding event classifiers. We evaluate this approach in the challenging setting where no manually annotated training set is available, i.e., EK0 in the TrecVid challenge, and show state-of-the-art results on MED 2011 and 2013 datasets.
Fichier principal
Vignette du fichier
final_version.pdf (7.62 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01618400 , version 1 (17-10-2017)



Nicolas Chesneau, Karteek Alahari, Cordelia Schmid. Learning from Web Videos for Event Classification. IEEE Transactions on Circuits and Systems for Video Technology, 2018, 28 (10), pp.3019-3029. ⟨10.1109/TCSVT.2017.2764624⟩. ⟨hal-01618400⟩
457 View
429 Download



Gmail Mastodon Facebook X LinkedIn More