AI Paper Atlas

Research map / Video / Video segmentation and tracking

Ego-Exo: Transferring Visual Representations From Third-Person to First-Person Videos

Yanghao Li, Tushar Nagarajan, Bo Xiong, Kristen Grauman

CVPR 2021 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 67 citations (OpenAlex)

Check 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 Ego-Score, Object-Score, and Interaction-Map distillation to Kinetics pre-trainingSlow-only ResNet-50 · Charades-EgomAP: 24.69 -> 26.23Improved
Add Ego-Score, Object-Score, and Interaction-Map distillation to Kinetics pre-trainingSlow-only ResNet-50 · EPIC-Kitchens-100 verbstop-1 accuracy: +1.64%Improved
Add Ego-Score, Object-Score, and Interaction-Map distillation to Kinetics pre-trainingSlow-only ResNet-50 · EPIC-Kitchens-100 nounstop-1 accuracy: +1.97%Improved
Add Ego-Score distillation (ablation)Ego-Exo pre-training · EPIC-Kitchens-100top-1 accuracyImproved
Add Object-Score distillation (ablation)Ego-Exo pre-training · Charades-Ego and EPIC-Kitchens-100mAP and accuracyImproved
Add Interaction-Map distillation (ablation)Ego-Exo pre-training · Charades-Ego and EPIC-Kitchens-100mAP and accuracyImproved
Add Interaction-Map loss during fine-tuning (ablation)Third-only and Ego-Exo · EPIC-Kitchens-100 nouns top-5top-5 accuracy: 69.72 -> 68.33; 70.28 -> 70.68Mixed
Use both hand-map and object-map rather than hand-map alone (ablation)Interaction-Map pre-training · EPIC-Kitchens-100 verbstop-1 accuracy: 61.35 -> 62.55Improved
Use both hand-map and object-map rather than object-map alone (ablation)Interaction-Map pre-training · Charades-EgomAP: 26.15 -> 25.91Hurt
Distill auxiliary-task predictions instead of using auxiliary models directly as pre-trained backbones (ablation)Ego-Exo · Charades-EgomAP: 23.29 -> 25.01; 22.17 -> 25.49Improved
Distill auxiliary-task predictions instead of appending auxiliary model embeddings (ablation)Ego-Exo · Charades-EgomAP: 24.92 -> 26.23; 24.73 -> 26.23; 24.68 -> 26.23Improved
Remove implicit pairing information from training the Ego-Score teacher (ablation)Ego-Exo · Charades-EgomAP: 26.23 -> 26.29No clear effect

Later papers that compared with this method

3 later accepted papers report EgoExo as a baseline in their results tables; 2 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