AI Paper Atlas

Research map / Video / Video segmentation and tracking

CompFeat: Comprehensive Feature Aggregation for Video Instance Segmentation

Yang Fu, Linjie Yang, Ding Liu, Thomas S. Huang, Humphrey Shi

AAAI 2021 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 49 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 attention at frame level (ablation)Baseline + MSCOCO · YouTube-VIS validationAP: 24.1 -> 25.2Improved
Add spatial attention at frame level (ablation)Baseline + MSCOCO · YouTube-VIS validationAP: 24.1 -> 24.9Improved
Add temporal and spatial attention at frame level (ablation)Baseline + MSCOCO · YouTube-VIS validationAP: 24.1 -> 25.8Improved
Add temporal and spatial attention at object level (ablation)Baseline + MSCOCO · YouTube-VIS validationAP: 24.1 -> 26.1Improved
Add temporal and spatial attention at both frame and object levels (ablation)Baseline + MSCOCO · YouTube-VIS validationAP: 24.1 -> 27.5Improved
Add correlation-map tracking (ablation)Baseline + MSCOCO · YouTube-VIS validationAP: 24.1 -> 25.1Improved
Add frame-level dual attention to correlation-map tracking (ablation)Baseline + CM · YouTube-VIS validationAP: 25.1 -> 26.3Improved
Add object-level dual attention to correlation-map tracking (ablation)Baseline + CM · YouTube-VIS validationAP: 25.1 -> 26.7Improved
Combine correlation-map tracking with frame- and object-level dual attention (ablation)Baseline + MSCOCO · YouTube-VIS validationAP: 24.1 -> 28.4Improved
Use random instead of uniform training-frame sampling (ablation)CompFeat · YouTube-VIS validationAP: 27.8 -> 28.4Improved
Increase training frames from 2 to 3 with random sampling (ablation)CompFeat · YouTube-VIS validationAP: 28.4 -> 26.8Hurt
Use CompFeat rather than MaskTrack R-CNNYouTube-VIS comparison · YouTube-VIS validationAP: 30.3 -> 35.3Improved

Later papers that compared with this method

2 later accepted papers report CompFeat as a baseline in their results tables; 2 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