Research map / Detection and segmentation / Weakly supervised detection and segmentation
Activity Driven Weakly Supervised Object Detection
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 |
|---|---|---|---|
| Use the full action-driven detector instead of PCL | Charades detection · Charades | mAP (%): 2.83 -> 8.76 | Helped |
| Use the full action-driven detector instead of PCL | EPIC KITCHENS detection · EPIC KITCHENS | mAP: 4.68 -> 9.75 | Helped |
| Use the full action-driven detector instead of PCL + prior | HICO-DET detection · HICO-DET | mAP (%): 4.19 -> 5.39 | Helped |
| Add a learned normal spatial prior to the center-prior variant (ablation) | Charades detector · Charades | mAP: 3.43 -> 8.76 | Helped |
| Learn both mean and variance rather than mean only (ablation) | Charades detector · Charades | mAP: 6.27 -> 8.76 | Helped |
| Learn both mean and variance rather than variance only (ablation) | Charades detector · Charades | mAP: 4.86 -> 8.76 | Helped |
| Add object classification loss to action classification loss (ablation) | Charades detector · Charades | mAP: 2.61 -> 8.76 | Helped |
| Add action classification loss to object classification loss (ablation) | Charades detector · Charades | mAP: 5.86 -> 8.76 | Helped |
| Add spatial prior module (ablation) | Ours-VGG-16 · Charades | mAP (%): 3.60 -> 8.76 | Helped |
| Add spatial prior module (ablation) | Ours-VGG-16 · HICO-DET | mAP (%): 3.16 -> 5.39 | Helped |
| Use ResNet-101 rather than VGG-16 as the backbone | Proposed detector · Charades | mAP (%): 8.76 -> 10.03 | Helped |
Closest papers by meaning
- Weakly-Guided Self-Supervised Pretraining for Temporal Activity Detection (AAAI 2023 · similarity 0.90)
- Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection (CVPR 2016 · similarity 0.89)
- A flexible model for training action localization with varying levels of supervision (NeurIPS 2018 · similarity 0.89)
- Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition (CVPR 2019 · similarity 0.89)
- Detector-Free Weakly Supervised Group Activity Recognition (CVPR 2022 · similarity 0.88)
- Semi-supervised Active Learning for Video Action Detection (AAAI 2024 · 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.