AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

COHESIV: Contrastive Object and Hand Embedding Segmentation In Video

Dandan Shan, Richard Ely Locke Higgins, David Fouhey

NeurIPS 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 9 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 embedding contrastive loss to attention-only training (ablation)COHESIV · 100DOH AllmIoU (%): 42.8 -> 51.9Improved
add embedding contrastive loss to attention-only training (ablation)COHESIV · EPIC-KITCHENS AllmIoU (%): 38.1 -> 43.2Improved
add responsibility attention loss to embeddings-only training (ablation)COHESIV · 100DOH AllmIoU (%): 25.7 -> 51.9Improved
use SE-ResNeXt backbone instead of ResNet (ablation)COHESIV · 100DOH AllmIoU (%): 45.8 -> 51.9Improved
use SE-ResNeXt backbone instead of ResNet (ablation)COHESIV · EPIC-KITCHENS HandmIoU (%): 55.2 -> 60.7Improved
use external hand detector query point instead of predicted query (ablation)COHESIV · 100DOH AllmIoU (%): 47.7 -> 51.9Improved
use external hand detector query point instead of predicted query (ablation)COHESIV · EPIC-KITCHENS ObjmIoU (%): 19.4 -> 19.5No clear effect
learn network from responsibility pseudo-labels instead of thresholding them directlyCOHESIV · 100DOH PairmIoU (%): 37.0 -> 46.5Improved
learn network from responsibility pseudo-labels instead of thresholding them directlyCOHESIV · EPIC-KITCHENS PairmIoU (%): 30.0 -> 42.1Improved
weakly supervised COHESIV vs fully supervised bounding box detectorCOHESIV · 100DOH AllmIoU (%): 56.9 -> 51.9Hurt
weakly supervised COHESIV vs fully supervised bounding box detectorCOHESIV · EPIC-KITCHENS HandmIoU (%): 53.8 -> 60.7Improved

Later papers that compared with this method

1 later accepted paper reports COHESIV 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