Research map / Video / Video segmentation and tracking
Predicting Salient Face in Multiple-Face Videos
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 temporal face-saliency transition modeling with M-LSTM to CNN face features | Proposed method · MUFVET-I | NSS: 3.14 -> 4.12 | Helped |
| Add temporal face-saliency transition modeling with M-LSTM to CNN face features | Proposed method · MUFVET-I | CC: 0.61 -> 0.74 | Helped |
| Use ground-truth face saliency weights instead of predicted M-LSTM weights (ablation) | Proposed method · MUFVET-I | NSS: 4.12 -> 4.21 | Helped |
| Use ground-truth face saliency weights instead of predicted M-LSTM weights (ablation) | Proposed method · MUFVET-I | CC: 0.74 -> 0.77 | Helped |
| Replace learned face saliency weights with a rule that assigns all weight to the face closest to the center (ablation) | Proposed method · MUFVET-I | NSS: 2.57 vs 4.12 | Hurt |
| Add a center prior to Xu et al. [41] (ablation) | Xu et al. [41] · MUFVET-I | NSS: +0.03 | Helped |
| Add a center prior to Xu et al. [41] (ablation) | Xu et al. [41] · MUFVET-I | CC: +0.007 | Helped |
Closest papers by meaning
- CaRDiff: Video Salient Object Ranking Chain of Thought Reasoning for Saliency Prediction with Diffusion (AAAI 2025 · similarity 0.87)
- Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional Push (CVPR 2018 · similarity 0.87)
- Shallow and Deep Convolutional Networks for Saliency Prediction (CVPR 2016 · similarity 0.87)
- Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (CVPR 2018 · similarity 0.86)
- Attentional Push: A Deep Convolutional Network for Augmenting Image Salience With Shared Attention Modeling in Social Scenes (CVPR 2017 · similarity 0.86)
- Understanding and Visualizing Deep Visual Saliency Models (CVPR 2019 · 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.