AI Paper Atlas

Research map / Video / Video segmentation and tracking

ActionVOS: Actions as Prompts for Video Object Segmentation

Liangyang Ouyang, Ruicong Liu, Yifei Huang, Ryosuke Furuta, Yoichi Sato

ECCV 2024 · Video › Video segmentation and tracking · approach: Matching-based video object segmentation · 5 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
use ActionVOS setting with action prompts instead of conventional RVOSReferFormer-R101 · VISOR valn-mIoU: 54.2 -> 19.0Improved
use ActionVOS instead of RVOSReferFormer-R101 · VISOR valp-mIoU: 67.7 -> 65.4Hurt
add action prompts to object names in training and inference (ablation)ActionVOS (RF-R101) · VISOR valp-mIoU: 56.3 -> 65.4Improved
train ActionVOS without action prompts (object names only) (ablation)ActionVOS · VOST valp-mIoU: 29.3 -> 9.0Hurt
use ActionVOS with action prompts instead of RVOS on state-changed objectsReferFormer-R101 · VOST valp-mIoU: 29.3 -> 32.3Improved
add classification head with threshold 0.75 (ablation)ActionVOS (RF-R101) · VISOR valgIoU: 63.2 -> 70.9Improved
raise classification threshold from 0.25 to 0.75 (ablation)ActionVOS (RF-R101) · VISOR valn-mIoU: 32.7 -> 19.0Improved
use natural-sentence action prompt instead of comma-joined prompt (ablation)ActionVOS (RF-R101) · VISOR valp-cIoU: 70.9 -> 72.4Improved
use action-guided focal loss instead of standard focal loss (ablation)ActionVOS (RF-R101) · VISOR valn-cIoU: 36.2 -> 32.7Improved
use action-guided focal loss instead of standard focal loss (ablation)ActionVOS (RF-R101) · VISOR valp-mIoU: 65.4 -> 65.4No clear effect
apply labeling module rules as post-process to RVOS (RVOS+S4.2) (ablation)ReferFormer-R101 · VISOR valn-mIoU: 19.0 -> 35.2Hurt

Later papers that compared with this method

1 later accepted paper reports ActionVOS 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