Learning from Web Videos for Event Classification

Nicolas Chesneau 1 Karteek Alahari 1 Cordelia Schmid 1
1 Thoth - Apprentissage de modèles à partir de données massives
LJK - Laboratoire Jean Kuntzmann, Inria Grenoble - Rhône-Alpes
Abstract : 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [46 references]  Display  Hide  Download

https://hal.inria.fr/hal-01618400
Contributor : Nicolas Chesneau <>
Submitted on : Tuesday, October 17, 2017 - 7:55:03 PM
Last modification on : Wednesday, February 27, 2019 - 3:37:33 PM
Long-term archiving on : Thursday, January 18, 2018 - 2:51:08 PM

File

final_version.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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

Share

Metrics

Record views

616

Files downloads

494