TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Rethinking the Evaluation of Video Summaries

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
KustantajaIEEE
Sivut7588-7596
Sivumäärä9
ISBN (elektroninen)978-1-7281-3293-8
ISBN (painettu)978-1-7281-3294-5
DOI - pysyväislinkit
TilaJulkaistu - kesäkuuta 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE/CVF Conference on Computer Vision and Pattern Recognition -
Kesto: 1 tammikuuta 2000 → …

Julkaisusarja

NimiIEEE/CVF Conference on Computer Vision and Pattern Recognition
ISSN (painettu)1063-6919
ISSN (elektroninen)2575-7075

Conference

ConferenceIEEE/CVF Conference on Computer Vision and Pattern Recognition
LyhennettäCVPR
Ajanjakso1/01/00 → …

Tiivistelmä

Video summarization is a technique to create a short skim of the original video while preserving the main stories/content. There exists a substantial interest in automatizing this process due to the rapid growth of the available material. The recent progress has been facilitated by public benchmark datasets, which enable easy and fair comparison of methods. Currently the established evaluation protocol is to compare the generated summary with respect to a set of reference summaries provided by the dataset. In this paper, we will provide in-depth assessment of this pipeline using two popular benchmark datasets. Surprisingly, we observe that randomly generated summaries achieve comparable or better performance to the state-of-the-art. In some cases, the random summaries outperform even the human generated summaries in leave-one-out experiments. Moreover, it turns out that the video segmentation, which is often considered as a fixed pre-processing method, has the most significant impact on the performance measure. Based on our observations, we propose alternative approaches for assessing the importance scores as well as an intuitive visualization of correlation between the estimated scoring and human annotations.

Tutkimusalat

Julkaisufoorumi-taso