Research map / 3D vision / Depth and stereo
Learning Gaze Transitions From Depth to Improve Video Saliency Estimation
George Leifman, Dmitry Rudoy, Tristan Swedish, Eduardo Bayro-Corrochano, Ramesh Raskar
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 depth input to the saliency network (ablation) | Our approach · DAViS test (16 videos) | 1-chi2: 0.60 -> 0.70 | Improved |
| add depth input to the saliency network (ablation) | Our approach · DAViS test (16 videos) | AUC: 0.68 -> 0.75 | Improved |
| our network versus Rudoy et al. video saliency | Our approach (w/ depth) · DAViS test (16 videos) | 1-chi2: 0.61 -> 0.70 | Improved |
| our network versus depth-extended hand-crafted baseline | Our approach (w/ depth) · DAViS test (16 videos) | AUC: 0.70 -> 0.75 | Improved |
| add depth to the Rudoy et al. style baseline algorithm | Extended baseline · DAViS test (16 videos) | 1-chi2: 0.61 -> 0.64 | Improved |
| our network without depth versus extended baseline with depth | Our approach (w/o depth) · DAViS test (16 videos) | 1-chi2: 0.64 -> 0.60 | Hurt |
Closest papers by meaning
- Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (ICCV 2019 · similarity 0.90)
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (CVPR 2018 · similarity 0.89)
- Learning to Explore Intrinsic Saliency for Stereoscopic Video (CVPR 2019 · similarity 0.89)
- Saliency Prediction in the Deep Learning Era: Successes and Limitations (TPAMI 2019 · similarity 0.89)
- Revisiting Video Saliency Prediction in the Deep Learning Era (TPAMI 2019 · similarity 0.89)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · 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.
