AI Paper Atlas

Research map / Video / Video-language understanding

Vamos: Versatile Action Models for Video Understanding

Shijie Wang, Qi Zhao, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, Chen Sun

ECCV 2024 · Video › Video-language understanding · approach: Long video understanding · 34 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 caption text instead of CLIP visual embeddings (ablation)Vamos · NeXT-QA valaccuracy (All): 69.6 -> 75.0Improved
add visual embeddings to caption text (ablation)Vamos · NeXT-QA valaccuracy (All): 75.0 -> 74.5No clear effect
add visual embeddings to caption text (ablation)Vamos · IntentQA testaccuracy (All): 73.2 -> 71.7Hurt
add visual embeddings to action text on Ego4D LTA (ablation)Vamos · Ego4D LTA testaction edit distance: 0.878 -> 0.868Improved
use token bottleneck selecting 40 of 644 tokens (ablation)Vamos · NeXT-QA valaccuracy (All): 77.3 -> 69.6Mixed
increase selected tokens from 20 to 40 (ablation)Token bottleneck model · NeXT-QA valaccuracy (All): 67.4 -> 69.6Improved
use LLaVA-1.5 captions instead of BLIP-2 (ablation)Vamos · NeXT-QA valaccuracy (All): 72.4 -> 75.0Improved
scale caption model from LLaVA 7B to 13B (ablation)Vamos · NeXT-QA valaccuracy (All): 75.1 -> 75.0No clear effect
increase captioned frames from 1 to 6 (ablation)Vamos · NeXT-QA valaccuracy (All): 69.8 -> 75.0Improved
increase captioned frames from 1 to 12 (ablation)Vamos (GPT-3.5) · EgoSchema zero-shotaccuracy: 37.83% -> 41.24%Improved
upgrade LLM from LLaMA1-7B to LLaMA3-8B (ablation)Vamos · NeXT-QA valaccuracy (All): 75.0 -> 77.3Improved
use captions instead of action labels as text representation (ablation)Vamos (GPT-4) · EgoSchema zero-shotaccuracy: 38.12% -> 48.26%Improved

Later papers that compared with this method

1 later accepted paper reports Vamos as a baseline in their results tables; 0 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 2 of 2 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