Research map / Detection and segmentation / CNN features
Object Detection From Video Tubelets With Convolutional Neural Networks
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 temporal convolution rescoring to combined tubelet proposals (ablation) | ImageNet VID tubelet detector · ImageNet VID validation | mean AP: 45.1 -> 47.5 | Helped |
| Combine random box perturbation and original-proposal replacement (ablation) | ImageNet VID tubelet detector · ImageNet VID validation | mean AP: 41.7% and 44.5% to 45.2% | Helped |
| Add overlapping original detections for spatial max-pooling (ablation) | ImageNet VID tubelet detector · ImageNet VID validation | mean AP: 37.4 -> 44.5 | Helped |
| Randomly perturb tubelet boxes using 20 samples at ratio 0.2 (ablation) | ImageNet VID tubelet detector · ImageNet VID validation | mean AP: 37.4 -> 41.7 | Helped |
| Use an overly strict IOU threshold of 0.9 to add original proposals (ablation) | ImageNet VID tubelet detector · ImageNet VID validation | mean AP: 37.4 -> 37.2 | Hurt |
| Apply the full framework instead of the baseline | VID-trained detector · YTO | average CorLoc: 74.9 -> 76.8 | Helped |
Closest papers by meaning
- Object Detection in Videos With Tubelet Proposal Networks (CVPR 2017 · similarity 0.89)
- R-FCN: Object Detection via Region-based Fully Convolutional Networks (NeurIPS 2016 · similarity 0.88)
- SCNN: A General Distribution Based Statistical Convolutional Neural Network with Application to Video Object Detection (AAAI 2019 · similarity 0.87)
- Temporal Object-Aware Vision Transformer for Few-Shot Video Object Detection (AAAI 2026 · similarity 0.87)
- TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection (AAAI 2025 · similarity 0.86)
- Context Enhanced Transformer for Single Image Object Detection in Video Data (AAAI 2024 · similarity 0.85)
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.