Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2407.05916 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911948452397056 |
|---|---|
| author | Wang, Tinghuai Wang, Huiling |
| author_facet | Wang, Tinghuai Wang, Huiling |
| contents | We propose a novel approach for modeling semantic contextual relationships in videos. This graph-based model enables the learning and propagation of higher-level spatial-temporal contexts to facilitate the semantic labeling of local regions. We introduce an exemplar-based nonparametric view of contextual cues, where the inherent relationships implied by object hypotheses are encoded on a similarity graph of regions. Contextual relationships learning and propagation are performed to estimate the pairwise contexts between all pairs of unlabeled local regions. Our algorithm integrates the learned contexts into a Conditional Random Field (CRF) in the form of pairwise potentials and infers the per-region semantic labels. We evaluate our approach on the challenging YouTube-Objects dataset which shows that the proposed contextual relationship model outperforms the state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_05916 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Non-parametric Contextual Relationship Learning for Semantic Video Object Segmentation Wang, Tinghuai Wang, Huiling Computer Vision and Pattern Recognition We propose a novel approach for modeling semantic contextual relationships in videos. This graph-based model enables the learning and propagation of higher-level spatial-temporal contexts to facilitate the semantic labeling of local regions. We introduce an exemplar-based nonparametric view of contextual cues, where the inherent relationships implied by object hypotheses are encoded on a similarity graph of regions. Contextual relationships learning and propagation are performed to estimate the pairwise contexts between all pairs of unlabeled local regions. Our algorithm integrates the learned contexts into a Conditional Random Field (CRF) in the form of pairwise potentials and infers the per-region semantic labels. We evaluate our approach on the challenging YouTube-Objects dataset which shows that the proposed contextual relationship model outperforms the state-of-the-art methods. |
| title | Non-parametric Contextual Relationship Learning for Semantic Video Object Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.05916 |