Zobrazeno 1 - 10
of 78
pro vyhledávání: '"Ryutarou Ohbuchi"'
Autor:
Takahiko Furuya, Ryutarou Ohbuchi
Publikováno v:
IEEE Access, Vol 10, Pp 116287-116301 (2022)
Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning approaches have
Externí odkaz:
https://doaj.org/article/6e41df7e137a422097b69fca11914f17
Publikováno v:
IEEE Access, Vol 8, Pp 140250-140260 (2020)
Invariance against rotation of 3D objects is one of the essential properties for 3D shape analysis. Recently proposed algorithms have achieved rotationally invariant 3D point set analysis by using inherently rotation-invariant 3D shape features, i.e.
Externí odkaz:
https://doaj.org/article/865353c6c58147589f50b1510b033c69
Publikováno v:
The Visual Computer.
3D point set reconstruction is an important and challenging 3D shape analysis task. Current state-of-the-art algorithms for 3D point set reconstruction employ a deep neural network (DNN) having an encoder–decoder architecture. Recently, the decoder
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6718a70995b1051f83d076192692a1a1
https://doi.org/10.1007/s00371-022-02652-6
https://doi.org/10.1007/s00371-022-02652-6
Publikováno v:
Scientific Programming, Vol 2020 (2020)
Object detection is one of the core tasks in computer vision. Object detection algorithms often have difficulty detecting objects with diverse scales, especially those with smaller scales. To cope with this issue, Lin et al. proposed feature pyramid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4d3a38adcc234ccb4aaeb5a9ba9cc5d3
https://doi.org/10.1155/2020/8839979
https://doi.org/10.1155/2020/8839979
Autor:
Takahiko Furuya, Ryutarou Ohbuchi
Publikováno v:
Pattern Recognition Letters. 138:146-154
Unsupervised learning of 3D shape feature is a challenging yet important problem for organizing a large collection of 3D shape models that do not have annotations. Recently proposed neural network-based approaches attempt to learn meaningful 3D shape
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7991343d01a99d2b3e9d5cbbdc8bfdae
https://doi.org/10.1016/j.patrec.2020.07.012
https://doi.org/10.1016/j.patrec.2020.07.012
Autor:
Ryutarou Ohbuchi, Takahiko Furuya
Publikováno v:
Multimedia Tools and Applications. 78:35157-35178
Unsupervised representation learning of unlabeled multimedia data is important yet challenging problem for their indexing, clustering, and retrieval. There have been many attempts to learn representation from a collection of unlabeled 2D images. In c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::59135415a11f72b8ff7176eb6e348e80
https://doi.org/10.1007/s11042-019-08078-y
https://doi.org/10.1007/s11042-019-08078-y
Publikováno v:
2020 the 3rd International Conference on Control and Computer Vision.
In this paper, we propose and evaluate a novel object detection architecture called Cascaded Multi-Channel Feature Pyramid Network, or CM-FPN. The proposed network, which is based on Feature Pyramid Network by Lin et al., employs multi-stage cascaded
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9fe86ce05708f519697255694f89e55c
https://doi.org/10.1145/3425577.3425580
https://doi.org/10.1145/3425577.3425580
Autor:
Ryutarou Ohbuchi, Takahiko Furuya
Publikováno v:
Computer Vision and Image Understanding. 166:102-114
Given a query that specifies partial 3D shape, a Part-based 3D Model Retrieval (P3DMR) system finds 3D shapes whose part or parts matches the query. An approach to P3DMR is to partition or segment whole models into sub-parts and performs query-part-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1521febff83644d4e808ae0efb16ca71
https://doi.org/10.1016/j.cviu.2017.11.007
https://doi.org/10.1016/j.cviu.2017.11.007
Publikováno v:
CW
Hand-drawn sketch is a powerful modality to query 3D shape models. However, specifying a detailed 3D shape by a sketch on the first try without reference (i.e., 3D model or real object) is difficult. In this paper, we aim at a sketch-based 3D shape r
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a391843281790826e9659b3040310f7d
https://doi.org/10.1109/cw.2019.00020
https://doi.org/10.1109/cw.2019.00020
Publikováno v:
ICME Workshops
Need to organize 3D shape data has prompted studies on comparison and retrieval of 3D shape models. Being able to query 3D shape models by words, in addition to 3D model examples and 2D sketches, would be quite beneficial. This paper proposes a metho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c87b9562a55ad4ae5781f75ce91fdc45
https://doi.org/10.1109/icmew.2019.00090
https://doi.org/10.1109/icmew.2019.00090