Research map / Video / Video segmentation and tracking
Saliency Detection in 360° Videos
Ziheng Zhang, Yanyu Xu, Jingyi Yu, Shenghua Gao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add spherical convolution (vs standard conv) (ablation) | Spherical U-Net · 360 video saliency dataset (ablation) | CC: 0.2877 -> 0.6246 | Improved |
| add spherical convolution (vs standard conv) (ablation) | Spherical U-Net · 360 video saliency dataset (ablation) | NSS: 1.6145 -> 3.5340 | Improved |
| add spherical MSE loss (vs standard MSE) (ablation) | Spherical U-Net · 360 video saliency dataset (ablation) | CC: 0.6189 -> 0.6246 | Improved |
| add spherical MSE loss (vs standard MSE) (ablation) | Spherical U-Net · 360 video saliency dataset (ablation) | NSS: 3.1620 -> 3.5340 | Improved |
| use larger spherical kernels (vs smaller) (ablation) | Spherical U-Net · 360 video saliency dataset (ablation) | NSS: 3.219 -> 3.5340 | Improved |
| use spherical pooling instead of planar pooling (ablation) | Spherical U-Net · 360 video saliency dataset (ablation) | CC: 0.6246 -> 0.6253 | No clear effect |
| add previous-frame saliency as input (ablation) | Spherical U-Net · 360 video saliency dataset (24 test videos) | CC | Improved |
| use Spherical U-Net vs best image baseline SALICON | saliency prediction · Salient360! (360 images) | CC: 0.3233 -> 0.4087 | Improved |
| use Spherical U-Net vs Wang et al. dynamic saliency | saliency prediction · 360 video saliency dataset (24 test videos) | CC: 0.2929 -> 0.6246 | Improved |
Closest papers by meaning
- Spherical DNNs and Their Applications in 360 Images and Videos (TPAMI 2021 · similarity 0.93)
- Cube Padding for Weakly-Supervised Saliency Prediction in 360° Videos (CVPR 2018 · similarity 0.87)
- Learning Spherical Convolution for Fast Features from 360° Imagery (NeurIPS 2017 · similarity 0.87)
- Rethinking 360deg Image Visual Attention Modelling With Unsupervised Learning. (ICCV 2021 · similarity 0.87)
- SphereNet: Learning Spherical Representations for Detection and Classification in Omnidirectional Images (ECCV 2018 · similarity 0.86)
- Unified Spherical Frontend: Learning Rotation-Equivariant Representations of Spherical Images from Any Camera (CVPR 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
