Research map / Video / Video segmentation and tracking
Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional Push
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 |
|---|---|---|---|
| Augment SAM-ResNet with dynamic Attentional Push | SAM-ResNet · DIEM, HOLLYWOOD2, and UCF-Sports test sets | NSS: 1.98 -> 2.34; 1.96 -> 2.29; 2.01 -> 2.31 | Helped |
| Add dynamic Attentional Push recurrence (ablation) | eDN-augmented saliency · DIEM test | NSS: 1.53 -> 2.21 | Helped |
| Add gaze following (ablation) | eDN-augmented saliency · DIEM test | NSS: 1.63 -> 2.21 | Helped |
| Add attentional bounce (ablation) | eDN-augmented saliency · DIEM test | NSS: 2.06 -> 2.21 | Helped |
| Add rapid scene-change cues (ablation) | eDN-augmented saliency · DIEM test | NSS: 2.01 -> 2.21 | Helped |
| Add the saliency pathway (ablation) | eDN-augmented saliency · DIEM test | NSS: 1.89 -> 2.21 | Helped |
| Add the Attentional Push pathways to the saliency pathway (ablation) | eDN · DIEM test | NSS: 1.57 -> 2.21 | Helped |
| Augment eDN with static Attentional Push cues, without dynamic recurrence (ablation) | eDN · DIEM test | NSS: 1.43 -> 1.53 | Helped |
Closest papers by meaning
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (CVPR 2018 · similarity 0.93)
- Attentional Push: A Deep Convolutional Network for Augmenting Image Salience With Shared Attention Modeling in Social Scenes (CVPR 2017 · similarity 0.92)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.89)
- A Motion-aware Spatio-temporal Graph for Video Salient Object Ranking (NeurIPS 2024 · similarity 0.89)
- Recurrent Mixture Density Network for Spatiotemporal Visual Attention (ICLR 2017 · similarity 0.89)
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · similarity 0.88)
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.