AI Paper Atlas

Research map / Detection and segmentation / CNN features

Leveraging Long-Range Temporal Relationships Between Proposals for Video Object Detection

Mykhailo Shvets, Wei Liu, Alexander C. Berg

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 103 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 the proposal-level temporal relation block (causal, K=2) to the single-frame detectorFPN detector · ImageNet VID val (ResNet-50)mAP: 72.4 -> 78.4Improved
add zero-centered feature normalization (vs uncentered, 10-dim) (ablation)relation block · ImageNet VID val (ResNet-50)mAP: 77.7 -> 78.4Improved
add supervised graph loss on the relation matrix (ablation)relation block · ImageNet VID val (ResNet-50)mAP: 77.4 -> 78.4Improved
reduce graph embedding dimension from 1024 to 10 (uncentered) (ablation)relation block · ImageNet VID val (ResNet-50)mAP: 77.5 -> 77.7No clear effect
use two relation blocks (fc6->{fc6,fc7}) instead of one at fc7->fc7 (ablation)prediction head · ImageNet VID val (ResNet-50)mAP: 77.5 -> 78.4Improved
add second relation block on top of single fc7 block (ablation)causal model · ImageNet VID val (ResNet-101)mAP: 80.6 -> 80.7Improved
add multi-head aggregation in relation block (ablation)relation block · ImageNet VID valmAPNo clear effect
add feature normalization, graph loss and larger embedding to Non-Local style block (ablation)relation block · ImageNet VID val (ResNet-101)mAP: 79.0 -> 80.7Improved
aggregate over multiple temporal strides at inference (ablation)relation block · ImageNet VID valmAPImproved
use symmetric mode (past and future frames) instead of causal (ablation)relation block · ImageNet VID val (ResNet-101)mAP: 80.7 -> 81.0Improved
use frozen support model instead of single model (ablation)relation block · ImageNet VID val (ResNet-101)mAP: 80.7 -> 80.6No clear effect
pretrain the full system on COCO (ablation)causal ResNet-50 model · ImageNet VID valmAP: 78.4 -> 78.9Improved

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