AI Paper Atlas

Research map / Video / Video segmentation and tracking

Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation

Tianrui Hui, Shaofei Huang, Si Liu, Zihan Ding, Guanbin Li, Wenguan Wang, Jizhong Han, Fei Wang

CVPR 2021 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 49 citations (OpenAlex)

Check 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
Combine the spatial target-frame encoder with the temporal video encoder (ablation)single-encoder segmentation model · A2D SentencesMean IoU: 47.7/48.2 -> 51.7Improved
Add LGFS to the combined spatial-temporal encoders (ablation)spatial-temporal model without LGFS · A2D SentencesMean IoU: 51.7 -> 52.9Improved
Add CMAM to the encoders (ablation)spatial-temporal model with LGFS · A2D SentencesMean IoU: 52.9 -> 56.1Improved
Use LGFS rather than elementwise addition for spatial-temporal fusion (ablation)spatial-temporal decoder without CMAM · A2D SentencesAP 0.5:0.95: 34.5 -> 36.0Improved
Use LGFS rather than elementwise maximum for spatial-temporal fusion (ablation)spatial-temporal decoder without CMAM · A2D SentencesAP 0.5:0.95: 34.8 -> 36.0Improved
Add CMAM at I4 alongside I5 (ablation)CMAM inserted at I5 · A2D SentencesMean IoU: 53.3 -> 55.0Improved
Extend CMAM insertion from I5/I4 to include I3, I2, and I1 (ablation)spatial-temporal encoders with CMAM · A2D SentencesMean IoU: 55.0 -> 56.1Improved
Use ResNet-50 + I3D instead of Inception V3 + I3D (ablation)collaborative spatial-temporal framework · A2D SentencesMean IoU: 56.1 -> 56.4Improved
Replace I3D with S3D while using Inception V3 (ablation)collaborative spatial-temporal framework · A2D SentencesMean IoU: 56.1 -> 55.0Hurt
Use the proposed collaborative framework rather than the strongest reported baselineA2D Sentences segmentation · A2D SentencesMean IoU: 53.1 -> 56.1Improved
Use the proposed collaborative framework rather than CMDycross-dataset evaluation without finetuning · J-HMDB SentencesAP 0.5:0.95: 30.1 -> 33.5Improved

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