Research map / Detection and segmentation / CNN features
Attentional Push: A Deep Convolutional Network for Augmenting Image Salience With Shared Attention Modeling in Social Scenes
Check 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 |
|---|---|---|---|
| Add Attentional Push and head-location inputs to BMS saliency | BMS · SALICON test | NSS: 1.28 -> 2.94 | Helped |
| Add Attentional Push and head-location inputs to BMS saliency | BMS · CAT2000 Action and Social | NSS: 1.18 -> 1.68 | Helped |
| Add Attentional Push and head-location inputs to BMS saliency | BMS · iSUN social images | NSS: 0.72 -> 1.15 | Helped |
| Add Attentional Push (ablation) | augmented BMS · SALICON test | NSS: 2.30 -> 2.94 | Helped |
| Add head-location input (ablation) | augmented BMS · SALICON test | NSS: 2.13 -> 2.94 | Helped |
| Use BMS rather than SalNet saliency as input (ablation) | augmented BMS · SALICON test | NSS: 2.79 -> 2.94 | Helped |
| Add saliency input (ablation) | augmented BMS · SALICON test | NSS: 2.30 -> 2.94 | Helped |
Closest papers by meaning
- Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional Push (CVPR 2018 · similarity 0.92)
- A Deeper Look at Saliency: Feature Contrast, Semantics, and Beyond (CVPR 2016 · similarity 0.90)
- Inferring Shared Attention in Social Scene Videos (CVPR 2018 · similarity 0.90)
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (CVPR 2018 · similarity 0.89)
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.88)
- DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images (NeurIPS 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.