AI Paper Atlas

Research map / Detection and segmentation / CNN features

Object Detection in Video with Spatiotemporal Sampling Networks

Gedas Bertasius, Lorenzo Torresani, Jianbo Shi

ECCV 2018 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 262 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 temporal spatiotemporal sampling to the static baseline (ablation)SSN · ImageNet VID valmAP@0.5: 76.0 -> 78.9Improved
replace FGFA flow-based alignment with learned samplingFGFA · ImageNet VID valmAP@0.5: 78.8 -> 78.9Improved
use STSN instead of D&T without post-processingD&T · ImageNet VID valmAP@0.5: 75.8 -> 78.9Improved
add Seq-NMS temporal post-processing to STSN (ablation)STSN · ImageNet VID valmAP@0.5: 78.9 -> 80.4Improved
use STSN+ instead of D&T+D&T+ · ImageNet VID valmAP@0.5: 79.8 -> 80.4Improved
increase temporal stride from 1 to 2 (ablation)STSN · ImageNet VID valmAP@0.5: 78.9 -> 79.0Improved
increase temporal stride from 1 to 4 (ablation)STSN · ImageNet VID valmAP@0.5: 78.9 -> 77.9Hurt
add more supporting frames (ablation)STSN · ImageNet VID valmAP@0.5Improved

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