AI Paper Atlas

Research map / Video / Video segmentation and tracking

Fast Video Object Segmentation using the Global Context Module

Yu Li, Zhuoran Shen, Ying Shan

ECCV 2020 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 144 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
enlarge the global context feature from 512x128 to 512x512 (ablation)GC · DAVIS 2016 testJ&F: 86.6 -> 86.1No clear effect
enlarge the global context feature from 512x128 to 512x512 (ablation)GC · DAVIS 2016 testtime (s): 0.040 -> 0.046Hurt
replace space-time memory with fixed-size global contextSTM · Memory read, t=100FLOPS: 21.2 G -> 0.04 GImproved
replace space-time memory with fixed-size global contextSTM · Memory read, t=100memory: 394 MB -> 1 MBImproved
replace space-time memory with global contextSTM* · DAVIS 2016 valtime per frame: 0.15 -> 0.04Improved
replace space-time memory with global contextSTM* · DAVIS 2016 valJ&F mean: 86.5 -> 86.6No clear effect
replace space-time memory with global contextSTM* · DAVIS 2017 valJ&F mean: 71.6 -> 71.4No clear effect
replace space-time memory with global contextSTM · YouTube-VOS valoverall: 79.4 -> 73.2Hurt
use equal test protocol (stride 5, no soft aggregation) for STM and GCSTM vs GC · YouTube-VOS valJ&F mean: 73.7 -> 73.2No clear effect
add soft aggregation and test input stride 1 to STMSTM · YouTube-VOS valJ&F mean: 73.7 -> 79.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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