AI Paper Atlas

Research map / Video / Video segmentation and tracking

Fully Motion-Aware Network for Video Object Detection

Shiyao Wang, Yucong Zhou, Junjie Yan, Zhidong Deng

ECCV 2018 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 213 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 pixel-level calibration to multi-frame aggregation (ablation)multi-frame aggregation · ImageNet VID valmAP (%): 73.4 -> 76.5Improved
add instance-level calibration to multi-frame aggregation (ablation)multi-frame aggregation · ImageNet VID valmAP (%): 73.4 -> 77.1Improved
aggregate multi-frame features by plain averaging without motion guidance (ablation)single-frame R-FCN · ImageNet VID valmAP (%): 73.6 -> 73.4Hurt
add motion pattern reasoning combining pixel and instance calibration (ablation)instance-level calibration · ImageNet VID valmAP (%): 77.1 -> 78.1Improved
combine pixel and instance calibration (ablation)pixel-level calibration · ImageNet VID valmAP (%): 76.5 -> 78.1Improved
plain averaging of frames on fast-moving objects (ablation)single-frame R-FCN · ImageNet VID val (fast)mAP (%): 52.2 -> 45.2Hurt
use instance-level instead of pixel-level calibration on occluded objects (ablation)MANet · ImageNet VID val (occlusion subset)mAP (%): 73.0 -> 74.1Improved
use instance-level instead of pixel-level calibration on non-rigid motion (ablation)MANet · ImageNet VID val (non-rigid subset)mAP (%): 52.8 -> 51.6Hurt
use instance-level instead of pixel-level calibration on rigid motion (ablation)MANet · ImageNet VID val (rigid subset)mAP (%): 81.0 -> 81.9Improved
combine both calibrations instead of best single one on non-rigid motion (ablation)MANet · ImageNet VID val (non-rigid subset)mAP (%): 52.8 -> 53.2Improved
aggregate 4 nearby frames instead of single frame at inference (ablation)MANet · ImageNet VID valmAP (%): 73.57 -> 77.58Improved
increase aggregated frames k from 4 to 12 (ablation)MANet · ImageNet VID valmAP (%): 77.58 -> 78.09Improved

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