Hierarchical deformable part models for heads and tails
Tutkimustuotos › › vertaisarvioitu
Yksityiskohdat
Alkuperäiskieli | Englanti |
---|---|
Otsikko | VISIGRAPP 2018 - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications |
Kustantaja | SCITEPRESS |
Sivut | 45-55 |
Sivumäärä | 11 |
Vuosikerta | 5 |
ISBN (elektroninen) | 9789897582905 |
DOI - pysyväislinkit | |
Tila | Julkaistu - 2018 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisussa |
Tapahtuma | INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS - Kesto: 1 tammikuuta 1900 → … |
Conference
Conference | INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS |
---|---|
Ajanjakso | 1/01/00 → … |
Tiivistelmä
Imbalanced long-tail distributions of visual class examples inhibit accurate visual detection, which is addressed by a novel Hierarchical Deformable Part Model (HDPM). HDPM constructs a sub-category hierarchy by alternating bootstrapping and Visual Similarity Network (VSN) based discovery of head and tail sub-categories. We experimentally evaluate HDPM and compare with other sub-category aware visual detection methods with a moderate size dataset (Pascal VOC 2007), and demonstrate its scalability to a large scale dataset (ILSVRC 2014 Detection Task). The proposed HDPM consistently achieves significant performance improvement in both experiments.