AI Paper Atlas

Research map / Video / Video segmentation and tracking

MoNet: Deep Motion Exploitation for Video Object Segmentation

Huaxin Xiao, Jiashi Feng, Guosheng Lin, Yu Liu, Maojun Zhang

CVPR 2018 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 162 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 motion-aligned features from adjacent frames (ablation)MoNet VGG16 DeepLab · DAVIS validationGlobal mean: 75.7 -> 80.2Improved
Add the DT-based motion prior after feature alignment (ablation)MoNet VGG16 DeepLab · DAVIS validationGlobal mean: 80.2 -> 83.8Improved
Add fully-connected CRF post-processing (ablation)MoNet with feature alignment and motion prior · DAVIS validationGlobal mean: 83.8 -> 84.7Improved
Add feature alignment using both past and future neighbors instead of past only (ablation)MoNet VGG16 DeepLab · DAVIS validationGlobal mean: 79.9 -> 80.2Improved
Use conv5_3 rather than conv4_3 for feature alignment (ablation)MoNet feature alignment · DAVIS validationGlobal mean: 79.5 -> 80.2Improved
Increase the feature-alignment neighborhood from 3 to 5 frames (ablation)MoNet conv5_3 feature alignment · DAVIS validationGlobal mean: 80.2 -> 80.9Improved
Increase the feature-alignment neighborhood from 5 to 10 frames (ablation)MoNet conv5_3 feature alignment · DAVIS validationGlobal mean: 80.9 -> 79.6Hurt
Add motion-based alignment rather than directly combining neighboring features (ablation)MoNet conv5_3 feature aggregation · DAVIS validationGlobal mean: 77.4 -> 80.2Improved
Use the DT layer instead of MPNet to produce motion prior (ablation)MoNet with feature alignment · DAVIS validationJ mean: 81.8 -> 81.6No clear effect
Use the DT layer instead of MPNet with LDOF (ablation)Motion-prior extraction · DAVIS validationJ mean: 52.4 -> 50.8Hurt
Use the DT layer instead of MPNet with EpicFlow (ablation)Motion-prior extraction · DAVIS validationJ mean: 56.9 -> 55.4Hurt
Use MoNet's motion exploitation rather than OSVOSVideo object segmentation · DAVIS validationJ mean: 79.8 -> 84.7Improved

Later papers that compared with this method

1 later accepted paper reports MONet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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