Research map / Detection and segmentation / Open-set and few-shot detection
Paying Attention to Descriptions Generated by Image Captioning Models
Hamed R. Tavakoli, Rakshith Shetty, Ali Borji, Jorma Laaksonen
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 GBVS saliency boosting to visual features (ablation) | LSTM captioner · MS COCO eval set | CIDEr: 0.837 -> 0.841 | No clear effect |
| add VGG-based saliency boosting to visual features (ablation) | LSTM captioner · MS COCO eval set | CIDEr: 0.837 -> 0.836 | No clear effect |
| add GBVS saliency boosting to visual features (ablation) | LSTM captioner · Augmented PASCAL50S (trained on MS COCO) | CIDEr: 0.585 -> 0.615 | Improved |
| add VGG-based saliency boosting to visual features (ablation) | LSTM captioner · Augmented PASCAL50S (trained on MS COCO) | CIDEr: 0.585 -> 0.614 | Improved |
| add GBVS saliency boosting to visual features (ablation) | LSTM captioner · Augmented PASCAL50S (trained on MS COCO) | BLEU4: 0.375 -> 0.400 | Improved |
| add GBVS saliency boosting to visual features (ablation) | LSTM captioner · Augmented PASCAL50S (trained on MS COCO) | METEOR: 0.293 -> 0.302 | Improved |
| use captioning models with higher quality (Microsoft vs Neural Talk) | captioning models · PASCAL50S | AUC attention agreement: 0.6663 -> 0.6707 | Improved |
| use captioning models with higher quality (Microsoft vs Neural Talk) | captioning models · PASCAL50S | CIDEr: 0.503 -> 0.664 | Improved |
Closest papers by meaning
- Human Attention in Image Captioning: Dataset and Analysis (ICCV 2019 · similarity 0.92)
- Language-Guided Salient Object Ranking (CVPR 2025 · similarity 0.88)
- Revealing the Gap in Human and VLM Scene Perception through Counterfactual Semantic Saliency (NeurIPS 2026 · similarity 0.87)
- Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception (CVPR 2026 · similarity 0.87)
- What's in the Image? A Deep-Dive into the Vision of Vision Language Models (CVPR 2025 · similarity 0.87)
- Explainable Saliency: Articulating Reasoning with Contextual Prioritization (CVPR 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.
