Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918454632644608 |
|---|---|
| author | Li, Chenxing Duan, Yiping Tao, Xiaoming |
| author_facet | Li, Chenxing Duan, Yiping Tao, Xiaoming |
| contents | Video Scene Graph Generation aims to obtain structured semantic representations of objects and their relationships in videos for high-level understanding. However, existing methods still have limitations in handling long-tail distributions. This paper proposes the Frequency-guided Relational Multi-level Reasoning (FReMuRe) model, which enhances the modeling ability of long-tail relationships from a mechanism perspective. We introduce relation-specific branches to deal gradient conflicts, yielding more balanced and tail-aware learning. And we design a frequency-aware dual-branch predicate embedding network to model high-frequency and low-frequency relationships separately and improve the recall rate of tail classes through gated fusion. Meanwhile, we propose two types of interchangeable relation classification heads: Bayesian Head for uncertainty estimation and new Gaussian Mixture Model Head to enhance intra-class diversity. Experimental results show that FReMuRe significantly improves the recall rate of long-tail relationships and overall reasoning robustness on the Action Genome dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17298 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video Li, Chenxing Duan, Yiping Tao, Xiaoming Computer Vision and Pattern Recognition Video Scene Graph Generation aims to obtain structured semantic representations of objects and their relationships in videos for high-level understanding. However, existing methods still have limitations in handling long-tail distributions. This paper proposes the Frequency-guided Relational Multi-level Reasoning (FReMuRe) model, which enhances the modeling ability of long-tail relationships from a mechanism perspective. We introduce relation-specific branches to deal gradient conflicts, yielding more balanced and tail-aware learning. And we design a frequency-aware dual-branch predicate embedding network to model high-frequency and low-frequency relationships separately and improve the recall rate of tail classes through gated fusion. Meanwhile, we propose two types of interchangeable relation classification heads: Bayesian Head for uncertainty estimation and new Gaussian Mixture Model Head to enhance intra-class diversity. Experimental results show that FReMuRe significantly improves the recall rate of long-tail relationships and overall reasoning robustness on the Action Genome dataset. |
| title | Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.17298 |