Semantic Scholar Open Access 2020 133 sitasi

Detecting Human-Object Interactions with Action Co-occurrence Priors

Dong-Jin Kim Xiao Sun Jinsoo Choi Stephen Lin I. Kweon

Abstrak

A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples, resulting in training sets with a long-tailed distribution. The lack of positive labels can lead to low classification accuracy for these classes. Towards addressing this issue, we observe that there exist natural correlations and anti-correlations among human-object interactions. In this paper, we model the correlations as action co-occurrence matrices and present techniques to learn these priors and leverage them for more effective training, especially in rare classes. The utility of our approach is demonstrated experimentally, where the performance of our approach exceeds the state-of-the-art methods on both of the two leading HOI detection benchmark datasets, HICO-Det and V-COCO.

Topik & Kata Kunci

Computer Science

Penulis (5)

Dong-Jin Kim

Xiao Sun

Jinsoo Choi

Stephen Lin

I. Kweon

Format Sitasi

APA MLA BibTeX

Kim, D., Sun, X., Choi, J., Lin, S., Kweon, I. (2020). Detecting Human-Object Interactions with Action Co-occurrence Priors. https://doi.org/10.1007/978-3-030-58589-1_43

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1007/978-3-030-58589-1_43

Informasi Jurnal

Tahun Terbit: 2020
Bahasa: en
Total Sitasi: 133×
Sumber Database: Semantic Scholar
DOI: 10.1007/978-3-030-58589-1_43
Akses: Open Access ✓