Research map / Detection and segmentation / Open-set and few-shot detection
Fast Object Class Labelling via Speech
Michael Gygli, Vittorio Ferrari
Check 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 |
|---|---|---|---|
| replace hierarchical class search with speaking class names while scanning and clicking objects | Object class labelling · COCO | time / image: 29.9s -> 13.1s | Improved |
| replace hierarchical class search with speaking class names while scanning and clicking objects | Object class labelling · ILSVRC | time / image: 31.1s -> 12.0s; ≈ 179s -> 12.0s | Improved |
| replace hierarchical class search with speech-based labelling | Object class labelling · COCO | recall: 84.7 % -> 83.9 % | Mixed |
| replace hierarchical class search with speech-based labelling | Object class labelling · ILSVRC | precision: 76.6 % -> 80.5 % | Improved |
| add vocabulary phrase hints to ASR (ablation) | Speech interface · COCO, ASR transcription | Recall@1: 70.5 % -> 93.1 % | Improved |
| add vocabulary phrase hints to ASR (ablation) | Speech interface · COCO, ASR transcription | Recall@3: 84.7 % -> 96.5 % | Improved |
| add vocabulary phrase hints to ASR (ablation) | Speech interface · ILSVRC, ASR transcription | Recall@1: 70.2 % -> 93.3 % | Improved |
| add vocabulary phrase hints to ASR (ablation) | Speech interface · ILSVRC, ASR transcription | Recall@3: 89.5 % -> 97.5 % | Improved |
| click directly on an object rather than drag a class symbol onto it | Object class labelling · COCO | click location accuracy: 90.7% -> 96.0% | Improved |
Closest papers by meaning
- Efficient Object Annotation via Speaking and Pointing (IJCV 2019 · similarity 0.92)
- Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets (CVPR 2021 · similarity 0.85)
- Scaling Up Instance Annotation via Label Propagation (ICCV 2021 · similarity 0.85)
- Optimal and Efficient Binary Questioning for Accelerated Annotation (AAAI 2025 · similarity 0.83)
- SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection (CVPR 2024 · similarity 0.83)
- Language-conditioned Detection Transformer (CVPR 2024 · similarity 0.82)
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.
