Toward Fine-Grained Sketch-Based 3D Shape Retrieval

Qi, Anran; Gryaditskaya, Yulia; Song, Jifei; Yang, Yongxin; Qi, Yongsheng; Hospedales, Timothy M.; Xiang, Tao; Song, Yi-Zhe

doi:10.1109/tip.2021.3118975

Cited by 35 publications

(21 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Searching for 3D shapes from a sketch has been accelerated by the SHREC challenges [22][23][24]. A recent trend is to perform cross-domain retrieval from 2D image domain to the 3D shape domain [4,8,40,47,48,52]. In this setting, Wang et al [48] map both sketches and 3D shapes in a similar feature space with a Siamese network [6,17], while Tasse et al [47] learn to regress to a semantic space with a ranking loss [14].…”

Section: Related Workmentioning

confidence: 99%

“…Xie et al [52] employ the Wasserstein distance to create a barycentric representation of 3D shapes. Qi et al [40] apply loss functions on the label space rather than the feature space. Chen et al [4] propose an advanced sampling of 2D views for unaligned shapes.…”

Section: Related Workmentioning

confidence: 99%

“…Chen et al [4] propose an advanced sampling of 2D views for unaligned shapes. Akin to [40,47], we place a central role on semantics for cross-domain search. In this paper, we go beyond searching for only 3D shapes to searching among any number of available target domains.…”

Section: Related Workmentioning

confidence: 99%

“…The training and testing splits of sketches follow the same protocol as SHREC13. We also report on the recently outlined Part-SHREC14 [40], which contains 3,840 sketches and 7,238 3D shapes from 48 classes. The sketch splits also follow the same protocol, while the 3D shapes are now split into 5,812 for training and 1,426 for testing to avoid overlap.…”

Section: Many-shot Sketch-based 3d Shape Retrievalmentioning

confidence: 99%

“…Siamese [48] 0.405 0.403 0.548 0.287 0.607 0.469 Shape2Vec [47] 0.620 0.628 0.684 0.354 0.741 0.650 DCML [8] 0.650 0.634 0.719 0.348 0.766 0.674 LWBR [52] 0.712 0.725 0.785 0.369 0.814 0.752 DCA [3] 0.783 0.796 0.829 0.376 0.856 0.813 SEM [40] 0.823 0.828 0.860 0.403 0.884 0.843 DSSH [4] 0 (c) Part-SHREC14.…”

Section: Many-shot Sketch-based 3d Shape Retrievalmentioning

confidence: 99%

See 4 more Smart Citations

Open Cross-Domain Visual Search

Thong¹,

Mettes²,

Snoek³

2019

Preprint

View full text Add to dashboard Cite

This paper introduces open cross-domain visual search, where categories in any target domain are retrieved based on queries from any source domain. Current works usually tackle cross-domain visual search as a domain adaptation problem. This limits the search to a closed setting, with one fixed source domain and one fixed target domain. To make the step towards an open setting where multiple visual domains are available, we introduce a simple yet effective approach. We formulate the search as one of mapping examples from every visual domain to a common semantic space, where categories are represented by hyperspherical prototypes. Cross-domain search is then performed by searching in the common space, regardless of which domains are used as source or target. Having separate mappings for every domain allows us to search in an open setting, and to incrementally add new domains over time without retraining existing mapping functions. Experimentally, we show our capability to perform open cross-domain visual search. Our approach is competitive with respect to traditional closed settings, where we obtain state-of-the-art results on six benchmarks for three sketch-based search tasks.

show abstract