Research map / Video / Video segmentation and tracking
SalSAC: A Video Saliency Prediction Model with Shuffled Attentions and Correlation-Based ConvLSTM
Xinyi Wu, Zhenyao Wu, Jinglin Zhang, Lili Ju, Song Wang
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 attention (ablation) | SalSAC · DHF1K val | NSS: 2.580 -> 2.624 | Improved |
| add random shuffling of multi-level attention maps (vs unshuffled multi-scale) (ablation) | SalSAC · DHF1K val | NSS: 2.613 -> 2.624 | Improved |
| add random shuffling of multi-level attention maps (ablation) | SalSAC · DHF1K val | s-AUC: 0.700 -> 0.729 | Improved |
| use multi-scale instead of single-scale attention (ablation) | SalSAC · DHF1K val | NSS: 2.600 -> 2.613 | Improved |
| add ConvLSTM (ablation) | SalSAC · DHF1K val | NSS: 2.461 -> 2.624 | Improved |
| correlation-based ConvLSTM instead of traditional ConvLSTM (ablation) | SalSAC · DHF1K val | NSS: 2.547 -> 2.624 | Improved |
| balance both input and output of ConvLSTM (vs v1 output only) (ablation) | SalSAC · DHF1K val | s-AUC: 0.709 -> 0.729 | Improved |
| balance both input and output (vs v2 input only) (ablation) | SalSAC · DHF1K val | s-AUC: 0.696 -> 0.729 | Improved |
| add SALICON image pre-training (ablation) | SalSAC · DHF1K val | AUC-J: 0.890 -> 0.898 | Improved |
| SalSAC vs STRA-Net | SalSAC · Hollywood-2 | NSS: 3.478 -> 3.356 | Mixed |
Closest papers by meaning
- Revisiting Video Saliency Prediction in the Deep Learning Era (TPAMI 2019 · similarity 0.89)
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (CVPR 2018 · similarity 0.88)
- DeepVS: A Deep Learning Based Video Saliency Prediction Approach (ECCV 2018 · similarity 0.88)
- Recurrent Mixture Density Network for Spatiotemporal Visual Attention (ICLR 2017 · similarity 0.87)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.86)
- A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking (NeurIPS 2024 · similarity 0.83)
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.
