AI Paper Atlas

Research map / Video / Video-language understanding

EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone

Shraman Pramanick, Yale Song, Sayan Nag, Kevin Qinghong Lin, Hardik Shah, Mike Zheng Shou, Rama Chellappa, Pengchuan Zhang

ICCV 2023 · Video › Video-language understanding · approach: Video-language pretraining · 107 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
use fusion in the backbone instead of stacked additional fusion layers (6 layers) (ablation)EgoVLPv2 · EgoMCQintra-video accuracy / compute: 60.8 -> 60.9; GMACs 437.90 -> 300.16Improved
increase number of fused layers from 3 to 6 (ablation)EgoVLPv2 fusion in backbone · EgoMCQintra-video accuracy (%): 60.0 -> 60.9Improved
increase fused layers beyond 6 (9, 12) (ablation)EgoVLPv2 fusion in backbone · EgoMCQaccuracy (%): 60.9 -> 60.9No clear effect
add VTM with hard-negative mining (ablation)EgoNCE+MLM pre-training · EgoMCQ ensembleintra-video accuracy (%): 56.8 -> 60.9Improved
add MLM objective (ablation)EgoNCE + VTM-Hard pre-training · EgoMCQ ensembleintra-video accuracy (%): 60.0 -> 60.9Improved
ensemble dual and fusion encoder inference (ablation)EgoVLPv2 · EgoMCQaccuracy (%): 59.6 -> 60.9 (intra)Improved
add fusion in the backbone pre-training vs dual-encoder EgoVLPEgoVLPv2 · EK-100 MIR zero-shotmAP: 16.6 -> 26.7Improved

Later papers that compared with this method

5 later accepted papers report EgoVLPv2 as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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