AI Paper Atlas

Research map / Video / Video segmentation and tracking

Less than Few: Self-Shot Video Instance Segmentation

Pengwan Yang, Yuki M. Asano, Pascal Mettes, Cees G. M. Snoek

ECCV 2022 · Video › Video segmentation and tracking · approach: Mask propagation for unsupervised video segmentation · 2 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
retrieve support videos with self-shot Video Rank features instead of random videosVIS transformer · Self-VIS test (1 support video)mAP@0.5: 44.3 -> 51.4Improved
use Video Rank loss instead of MIL-NCE for retrievalself-shot retrieval · Self-VIS test (1 support video)mAP@0.5: 50.1 -> 51.4Improved
finetune Inception features with MoCo instead of fixedself-shot retrieval · Self-VIS test (1 support video)mAP@0.5: 46.9 -> 49.4Improved
add 5 extra support videos at inference to 5 self-shot supportsVideo Rank self-shot · Self-VIS test (5 support videos)mAP@0.5: 54.3 -> 55.4Improved
use self-shot support instead of zero-shotVIS transformer · Self-VISmAP@0.5: 47.4 -> 51.4Improved
use self-shot support instead of zero-shottemporal action localization · Thumos14video-mAP@0.5: 43.4 -> 45.8Improved
use unlabelled pool supports instead of segments of query videoself-shot · Self-VIS test (1 support video)mAP@0.5: 44.9 -> 51.4Improved
add the query-support fuser (ablation)VIS transformer decoder · Self-VIS (1 self-shot)mAP@0.5: 40.7 -> 49.1Improved
add the transformer encoder (ablation)VIS transformer decoder · Self-VIS (1 self-shot)mAP@0.5: 40.7 -> 42.4Improved
add the encoder on top of fuser and decoder (ablation)VIS transformer · Self-VIS (1 self-shot)mAP@0.5: 49.1 -> 51.4Improved
add the fuser (ablation)VIS transformer decoder · Self-OVIS (1 self-shot)mAP@0.5: 13.7 -> 19.6Improved
add spatio-temporal positional encoding to support and query (ablation)VIS transformer (oracle one-shot) · Self-VISmAP@0.5: 49.4 -> 53.2Improved

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