AI Paper Atlas

Research map / Video / Video segmentation and tracking

LVOS: A Benchmark for Long-term Video Object Segmentation

Lingyi Hong, Wenchao Chen, Zhongying Liu, Wei Zhang, Pinxue Guo, Zhaoyu Chen, Wenqiang Zhang

ICCV 2023 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 76 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 local memory to reference memory (ablation)DDMemory · LVOS validationJ&F: 44.2 -> 57.9Improved
add global memory to reference and local memory (ablation)DDMemory · LVOS validationJ&F: 57.9 -> 61.9Improved
add reference memory to global and local memory (ablation)DDMemory · LVOS validationJ&F: 54.9 -> 61.9Improved
use local memory alone (ablation)DDMemory · LVOS validationJ&F: 61.9 -> 18.3Hurt
finetune on LVOS training setexisting VOS models and DDMemory · LVOS validationJ&F: 60.7 -> 61.9 (DDMemory); 59.4 -> 60.9 (AOT-L)Improved
provide oracle bounding boxDDMemory · LVOS validationJ&F: 61.9 -> 70.2Improved
provide oracle mask for memory updateDDMemory · LVOS validationJ&F: 61.9 -> 82.7Improved
evaluate DDMemory on short videos with global memoryDDMemory · DAVIS 2017 validationJ&F: 84.2 vs XMem 86.2No clear effect
use compressed memory bank or online adaptation models on scale variationVOS models on LVOS attributes · LVOS validation attributesJ: LRA 44.3 (AOT-B) vs FM 54.3Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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