ML Anthology

Beyond Photo-Domain Object Recognition: Benchmarks for the Cross-Depiction Problem

Hongping Cai, Qi Wu, Peter Hall
ICCVW 2015 pp. 74-79
doi:10.1109/ICCVW.2015.19 /iccvw/2015/cai2015iccvw-beyond/

Abstract

The cross-depiction problem is that of recognising visual objects regardless of whether they are photographed, painted, drawn, etc. It introduces great challenge as the variance across photo and art domains is much larger than either alone. We extensively evaluate classification, domain adaptation and detection benchmarks for leading techniques, demonstrating that none perform consistently well given the cross-depiction problem. Finally we refine the DPM model, based on query expansion, enabling it to bridge the gap across depiction boundaries to some extent.

ICCVW Semantic Scholar

Cite

Text

Cai et al. "Beyond Photo-Domain Object Recognition: Benchmarks for the Cross-Depiction Problem." IEEE/CVF International Conference on Computer Vision Workshops, 2015. doi:10.1109/ICCVW.2015.19

Markdown

[Cai et al. "Beyond Photo-Domain Object Recognition: Benchmarks for the Cross-Depiction Problem." IEEE/CVF International Conference on Computer Vision Workshops, 2015.](https://mlanthology.org/iccvw/2015/cai2015iccvw-beyond/) doi:10.1109/ICCVW.2015.19

BibTeX

@inproceedings{cai2015iccvw-beyond,
  title     = {{Beyond Photo-Domain Object Recognition: Benchmarks for the Cross-Depiction Problem}},
  author    = {Cai, Hongping and Wu, Qi and Hall, Peter},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2015},
  pages     = {74-79},
  doi       = {10.1109/ICCVW.2015.19},
  url       = {https://mlanthology.org/iccvw/2015/cai2015iccvw-beyond/}
}