AI Paper Atlas

Research map / Video / Video-language understanding

AMEGO: Active Memory from long EGOcentric videos

Gabriele Goletto, Tushar Nagarajan, Giuseppe Averta, Dima Damen

ECCV 2024 · Video › Video-language understanding · approach: Egocentric video understanding · 16 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 AMEGO structured active memory instead of semantic QA baselinesAMEGO · AMBTotal accuracy (%): 23.6 -> 36.3Improved
use larger visual feature extractors (ViT-L instead of ViT-S/B) (ablation)AMEGO · AMBTotal accuracy (%): 33.8 -> 36.3Improved
use a two-stage LLM pipeline (LLoVi) instead of single-stage semantic QAS-QA baseline · AMBTotal accuracy (%): 22.9 -> 22.6Hurt
add active-object features to semantic-free QASF-QA · AMBTotal accuracy (%): 22.0 -> 21.2No clear effect
require several detections before starting a tracklet (s_o=20 instead of 1) (ablation)AMEGO HOI tracking · HOI tracklets standaloneAIoU P: 0.08 -> 0.20Improved
use hand detections to terminate tracklets (ablation)AMEGO HOI tracking · HOI tracklets standaloneAIoU P: 0.19 -> 0.20Improved
add SOT tracker (EgoSTARK) to HOI tracking (ablation)AMEGO HOI tracking · HOI tracklets standaloneAIoU GT: 0.39 -> 0.41Improved
add optical flow filter for location segments (ablation)AMEGO location segments · Location segments standaloneAIoU GT: 0.35 -> 0.50Improved
add hand detection filter for location segments (ablation)AMEGO location segments · Location segments standaloneAIoU P: 0.34 -> 0.36Improved
vary IoU threshold for spatial matching (0.3, 0.5, 0.7) (ablation)AMEGO HOI tracking · HOI tracklets standaloneAIoU GT: 0.37 / 0.41 / 0.32No clear effect
vary clustering thresholds theta and tau (ablation)AMEGO instance assignment · Two annotated videosID-switchNo clear effect

Later papers that compared with this method

1 later accepted paper reports AMEGO 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