Research map / Detection and segmentation / CNN features
Exploit Bounding Box Annotations for Multi-Label Object Recognition
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 label-view features derived from bounding boxes for 20 categories (ablation) | FeV multi-view multi-instance framework · VOC 2007 test | mAP: 83.7 -> 86.2; 2.5% | Helped |
| Add label-view features derived from bounding boxes for 10 categories (ablation) | FeV multi-view multi-instance framework · VOC 2007 test | mAP: 83.7 -> 85.0; 1.3% | Helped |
| Add label-view features derived from bounding boxes for 20 categories (ablation) | FeV multi-view multi-instance framework · VOC 2012 test | mAP: 84.0 -> 86.0; 2% | Helped |
| Use bounding boxes from 10 categories rather than all 20 (ablation) | FeV multi-view multi-instance framework · VOC 2012 test | mAP: 84.0 -> 85.7 | Helped |
| Represent proposal bags with Fisher vectors rather than max-pooling proposal scores | Proposal-based multi-label recognition · VOC 2007 test | mAP: 81.5 -> 83.7; 2.2% | Helped |
| Add bounding-box-derived local label relationships from 10 categories (ablation) | FeV multi-view multi-instance framework · Unseen VOC 2007 categories | classification accuracy | Helped |
| Average scores from VeryDeep and FeV+LV-20-VD | VOC 2007 classification · VOC 2007 test | mAP: 90.6 -> 92.0 | Helped |
| Average scores from the very-deep CNN method and the proposal-based representation | VOC 2012 classification · VOC 2012 test | mAP: 89.4 -> 90.7 | Helped |
Closest papers by meaning
- Multi-Label Learning From Single Positive Labels (CVPR 2021 · similarity 0.88)
- Multi-Label Image Recognition With Graph Convolutional Networks (CVPR 2019 · similarity 0.88)
- [CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation (ICML 2026 · similarity 0.87)
- Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations (CVPR 2019 · similarity 0.87)
- Open-Vocabulary Object Detection Using Captions (CVPR 2021 · similarity 0.87)
- Multi-View Multi-Label Classification via View-Label Matching Selection (AAAI 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.