Research map / Detection and segmentation / Open-set and few-shot detection
Pointing Novel Objects in Image Captioning
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 sentence-level coverage loss to LSTM-P (ablation) | LSTM-P · held-out COCO | F1 average (%): 60.0 -> 60.9 | Helped |
| use pointing to balance word generation and object copying | LSTM-P · held-out COCO | F1 average (%): LSTM-C 55.7 -> LSTM-P− 60.0 | Helped |
| use pointing and coverage loss rather than LSTM-C | LSTM-P · ImageNet -COCO | Novel (%): 72.08 -> 90.06 | Helped |
| use pointing and coverage loss rather than LSTM-C | LSTM-P · ImageNet -COCO | F1 (%): 16.39 -> 17.67 | Helped |
| use pointing and coverage loss rather than LSTM-C | LSTM-P · ImageNet -COCO | Accuracy (%): 11.83 -> 11.91 | Helped |
| include British National Corpus and Wikipedia text for training | LSTM-P · ImageNet | F1 (%): 17.67 -> 52.07 | Helped |
Closest papers by meaning
- Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects (CVPR 2017 · similarity 0.93)
- Reference Based LSTM for Image Captioning (AAAI 2017 · similarity 0.90)
- Learning Object Context for Dense Captioning (AAAI 2019 · similarity 0.90)
- Convolutional Image Captioning (CVPR 2018 · similarity 0.89)
- EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension (CVPR 2024 · similarity 0.88)
- LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models (CVPR 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.