AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views

Lorenzo Mur-Labadia, Maria Santos-Villafranca, Jesus Bermudez-Cameo, Alejandro Perez-Yus, Ruben Martinez-Cantin, Jose J. Guerrero

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Amodal and open-world instance 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
add Mask Matching contrastive loss with an MLP (ablation)k-NN baseline · Ego-Exo4D val 10% Ego2ExoIoU: 35.2 -> 42.2Improved
add Mask Matching contrastive loss with an MLP (ablation)k-NN baseline · Ego-Exo4D val 10% Exo2EgoIoU: 34.9 -> 44.7Improved
add context descriptor without adjacent negatives (ablation)O-MaMa (loss only) · Ego-Exo4D val 10% Ego2ExoIoU: 42.2 -> 42.7No clear effect
add adjacent hard negative mining (ablation)O-MaMa + context · Ego-Exo4D val 10% Ego2ExoIoU: 42.7 -> 46.9Improved
add Ego-Exo cross attention (weighted-sum union) (ablation)O-MaMa + adjacent negatives · Ego-Exo4D val 10% Ego2ExoIoU: 46.9 -> 47.3Improved
use concat instead of weighted sum for global union (ablation)O-MaMa · Ego-Exo4D val 10% Ego2ExoIoU: 47.3 -> 48.3Improved
add epipolar geometry constraint to k-NN (ablation)k-NN Avg-Pool(mask) DINOv2 · Ego-Exo4D val 10%IoU: 35.2 vs. 35.4No clear effect
average DINOv2 mask features instead of CLIP bbox pooling (ablation)k-NN baseline · Ego-Exo4D val 10% Ego2ExoIoU: 24.5 -> 35.2Improved
pool DINOv2 over mask instead of bounding box (ablation)k-NN baseline · Ego-Exo4D val 10% Ego2ExoIoU: 21.8 -> 35.2Improved
pool DINOv2 over mask instead of mask centroid (ablation)k-NN baseline · Ego-Exo4D val 10% Ego2ExoIoU: 25.6 -> 35.2Improved
full O-MaMa modules vs k-NN baselineO-MaMa · Ego-Exo4D val 10% Ego2ExoLoc.E: +67.5Improved
reformulate as mask matching vs zero-shot PSALMO-MaMa k-NN baseline · Ego-Exo4D v1 val Ego2ExoIoU: 7.9 -> 40.5Improved

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