Category-specific video summarization

Danila Potapov 1 Matthijs Douze 1, 2 Zaid Harchaoui 1, 3 Cordelia Schmid 1, 3
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In large video collections with clusters of typical categories, such as ''birthday party'' or ''flash-mob'', category-specific video summarization can produce higher quality video summaries than unsupervised approaches that are blind to the video category. Given a video from a known category, our approach first efficiently performs a temporal segmentation into semantically-consistent segments, delimited not only by shot boundaries but also general change points. Then, equipped with an SVM classifier, our approach assigns importance scores to each segment. The resulting video assembles the sequence of segments with the highest scores. The obtained video summary is therefore both short and highly informative. Experimental results on videos from the multimedia event detection (MED) dataset of TRECVID'11 show that our approach produces video summaries with higher relevance than the state of the art.
Document type :
Conference papers
Complete list of metadatas

Cited literature [37 references]  Display  Hide  Download


https://hal.inria.fr/hal-01022967
Contributor : Thoth Team <>
Submitted on : Friday, July 11, 2014 - 12:19:11 PM
Last modification on : Monday, December 17, 2018 - 11:22:02 AM
Long-term archiving on : Saturday, October 11, 2014 - 12:05:11 PM

Files

video_summarization.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Danila Potapov, Matthijs Douze, Zaid Harchaoui, Cordelia Schmid. Category-specific video summarization. ECCV - European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. pp.540-555, ⟨10.1007/978-3-319-10599-4_35⟩. ⟨hal-01022967⟩

Share

Metrics

Record views

2781

Files downloads

11906