Research map / Detection and segmentation / CNN features
TempSAL - Uncovering Temporal Information for Deep Saliency Prediction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use temporal saliency predictions with SMM to refine image saliency | TempSAL · SALICON test | CC: 0.899 -> 0.911 | Helped |
| Use temporal saliency predictions with SMM to refine image saliency | TempSAL · SALICON test | KL: 0.201 -> 0.195 | Helped |
| Use temporal saliency predictions with SMM to refine image saliency | TempSAL · SALICON test | sAUC: 0.767 -> 0.745 | Hurt |
| Use temporal saliency predictions with SMM to refine image saliency | TempSAL · SALICON test | NSS: 2.058 -> 1.967 | Hurt |
| Use TempSAL rather than MD-SEM | CodeCharts1k · CodeCharts1k average | CC: 0.765 -> 0.797 | Helped |
| Use TempSAL rather than MD-SEM | CodeCharts1k · CodeCharts1k average | KL: 0.430 -> 0.493 | Hurt |
| Add the image saliency decoder (ablation) | TempSAL temporal-decoder-only model · SALICON validation | NSS: 1.973 -> 1.943 | Hurt |
| Add the image saliency decoder (ablation) | TempSAL temporal-decoder-only model · SALICON validation | CC: 0.852 -> 0.857 | Helped |
| Add the spatiotemporal mixing module (ablation) | TempSAL with temporal and image saliency decoders · SALICON validation | CC: 0.857 -> 0.906 | Helped |
| Add the spatiotemporal mixing module (ablation) | TempSAL with temporal and image saliency decoders · SALICON validation | NSS: 1.943 -> 1.930 | Hurt |
| Use shared temporal modeling instead of separate SimpleNet models per slice (ablation) | TempSAL · SALICON temporal slices average | CC: 0.848 -> 0 . 8 5 2 | Helped |
| Use equal-duration rather than equal-distribution temporal slices (ablation) | TempSAL temporal slicing · SALICON | saliency prediction performance | Helped |
Closest papers by meaning
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · similarity 0.89)
- A Deeper Look at Saliency: Feature Contrast, Semantics, and Beyond (CVPR 2016 · similarity 0.89)
- What Do Deep Saliency Models Learn about Visual Attention? (NeurIPS 2023 · similarity 0.89)
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (CVPR 2018 · similarity 0.89)
- Predicting When Saliency Maps Are Accurate and Eye Fixations Consistent (CVPR 2016 · similarity 0.88)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · 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.