Research map / Label-efficient and robust learning / Domain adaptation and generalization
Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction
Giovanni Bellitto, Federica Proietto Salanitri, Simone Palazzo, Francesco Rundo, Daniela Giordano, Concetto Spampinato
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 Conspicuity-net 3 to the encoder-decoder baseline (ablation) | HD2S · DHF1K val | NSS: 2.602 -> 2.612 | Improved |
| add Conspicuity-net 2 (ablation) | HD2S · DHF1K val | NSS: 2.612 -> 2.699 | Improved |
| add Conspicuity-net 1 (ablation) | HD2S · DHF1K val | NSS: 2.699 -> 2.743 | Improved |
| add multi-level loss on conspicuity maps (ablation) | HD2S · DHF1K val | NSS: 2.743 -> 2.806 | Improved |
| use only the first conspicuity net instead of the third (ablation) | HD2S single-branch · DHF1K val | NSS: 2.191 vs 2.663 | Mixed |
| add hierarchical gradient reversal domain adaptation (source DHF1K) | HD2S · DHF1K to UCF Sports | NSS: 2.483 -> 2.514 | Improved |
| add hierarchical gradient reversal domain adaptation (source UCF Sports) | HD2S · UCF Sports to DHF1K | NSS: 2.237 -> 2.160 | Hurt |
| add hierarchical gradient reversal domain adaptation (source Hollywood2) | HD2S · Hollywood2 to UCF Sports | NSS: 2.476 -> 2.389 | Hurt |
| add domain adaptation on DHF1K test benchmark | HD2S · DHF1K test | NSS: 2.781 -> 2.709 | Hurt |
| add domain-specific learning modules | HD2S · DHF1K test | NSS: 2.781 -> 2.812 | Improved |
| add domain-specific learning modules | HD2S · UCF Sports | AUC-J: 0.913 -> 0.904 | Mixed |
| train on multiple datasets (multi-source) vs single source | HD2S · DHF1K val | NSS: 2.806 -> 2.811 | No clear effect |
Closest papers by meaning
- Saliency Prediction in the Deep Learning Era: Successes and Limitations (TPAMI 2019 · similarity 0.88)
- Saliency Hierarchy Modeling via Generative Kernels for Salient Object Detection (ECCV 2022 · similarity 0.88)
- Revisiting Video Saliency Prediction in the Deep Learning Era (TPAMI 2019 · similarity 0.88)
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (CVPR 2018 · similarity 0.88)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.87)
- Energy-Based Generative Cooperative Saliency Prediction (AAAI 2022 · similarity 0.87)
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.
