AI Paper Atlas

Research map / Detection and segmentation / CNN features

Mining Inter-Video Proposal Relations for Video Object Detection

Mingfei Han, Yali Wang, Xiaojun Chang, Yu Qiao

ECCV 2020 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 92 citations (OpenAlex)

Read the paperCheck 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 changedWhereMeasuredEffect
add intra-video proposal relation module (ablation)Faster-RCNN · ImageNet VID val (ResNet-101)mAP (%): 73.2 -> 80.6Improved
add inter-video proposal relation module (ablation)HVR-Net (intra only) · ImageNet VID val (ResNet-101)mAP (%): 80.6 -> 83.2Improved
use multi-level triplet selection instead of random video and all-proposal selection (ablation)HVR-Net · ImageNet VID val (ResNet-101)mAP (%): 81.0 -> 83.2Improved
add relation regularization loss (ablation)HVR-Net · ImageNet VID val (ResNet-101)mAP (%): 80.0 -> 83.2Improved
use 3 intra modules instead of 2 (ablation)HVR-Net · ImageNet VID val (ResNet-101)mAP (%): 81.8 -> 83.2Improved
use 2 inter modules instead of 1 (ablation)HVR-Net · ImageNet VID val (ResNet-101)mAP (%): 83.2 -> 82.1Hurt
increase testing frames from 5 to 31 (ablation)HVR-Net · ImageNet VID val (ResNet-101)mAP (%): 80.5 -> 83.2Improved
increase testing frames from 21 to 31 (ablation)HVR-Net · ImageNet VID val (ResNet-101)mAP (%): 82.9 -> 83.2No clear effect
remove inter-video proposal relation module at test time (ablation)HVR-Net · ImageNet VID val (ResNet-101)mAP (%)No clear effect
add Seq-NMS post-processingHVR-Net · ImageNet VID val (ResNet-101)mAP (%): 83.2 -> 83.8Improved
add Seq-NMS post-processingHVR-Net · ImageNet VID val (ResNeXt-101-32x4d)mAP (%): 84.8 -> 85.5Improved
use HVR-Net instead of LongRange on fast objectsHVR-Net · ImageNet VID val (Fast objects)mAP (%): 64.2 -> 66.6Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy