AI Paper Atlas

Research map / Video / Video-language understanding

Egocentric Video-Language Pretraining

Kevin Qinghong Lin, Jinpeng Wang, Mattia Soldan, Michael Wray, Rui Yan, Zhongcong Xu, Difei Gao, Rong-Cheng Tu, Wenzhe Zhao, Weijie Kong, Chengfei Cai, WANG HongFa and 4 more

NeurIPS 2022 · Video › Video-language understanding · approach: Video-language pretraining · 45 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
pretrain on EgoClip instead of CC3M+WebVid-2MFrozen · EPIC-KITCHENS-100 MIR zero-shotmAP avg: 8.0 -> 15.5Improved
pretrain on EgoClip instead of HowTo100MFrozen · Ego4D NLQ val IoU=0.3R@1: 3.95 -> 10.53Improved
replace InfoNCE with EgoNCE (ablation)Frozen on EgoClip · EPIC-KITCHENS-100 MIR 4 framesnDCG avg: 54.3 -> 54.8Improved
replace InfoNCE with EgoNCE (ablation)Frozen on EgoClip · Charades-Ego fine-tunedmAP: 31.2 -> 32.1Improved
replace InfoNCE with EgoNCE (ablation)Frozen on EgoClip · Ego4D OSCC valaccuracy: 73.4 -> 73.9Improved
replace InfoNCE with EgoNCE (ablation)Frozen on EgoClip · EgoMCQ intra-videoaccuracy: 51.5 -> 57.2Improved
action-aware positives using nouns only (ablation)InfoNCE · EgoMCQ intra-videoaccuracy: 51.5 -> 42.3Hurt
action-aware positives using noun and verb together (ablation)InfoNCE · EgoMCQ intra-videoaccuracy: 51.5 -> 53.6Improved
use random negatives (ablation)InfoNCE · EgoMCQ intra-videoaccuracy: 51.5 -> 49.9Hurt
use hard negatives within 1 minute (ablation)InfoNCE · EgoMCQ intra-videoaccuracy: 51.5 -> 54.5Improved
center clip at timestamp rather than start at it (ablation)EgoClip creation · EgoMCQ intra-videoaccuracy: 39.72 -> 41.68Improved
use per-video variable clip length beta_i instead of fixed length (ablation)EgoClip creation · EgoMCQ intra-videoaccuracy: 41.68 -> 44.82Improved

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