AI Paper Atlas

Research map / Video / Video-language understanding

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering

Ziyi Bai, Ruiping Wang, Xilin CHEN

NeurIPS 2023 · Video › Video-language understanding · approach: Video question answering

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 dynamic event memories as prompts and add multi-level attention (ablation)Glance-Focus · STARAccuracy: 53.12 -> 53.94Improved
Use dynamic event memories as prompts and add multi-level attention (ablation)Glance-Focus · EgoTaskQAAccuracy: 42.70 -> 44.27Improved
Learn event memories instead of using a frozen action detector (ablation)Glance-Focus · STARAccuracy: 49.85 -> 53.94Improved
Learn event memories instead of using a frozen action detector (ablation)Glance-Focus · EgoTaskQAAccuracy: 42.62 -> 44.27Improved
Add unsupervised semantic diversity loss L_cls (ablation)GF(uns) · AGQAAccuracy: 54.27 -> 54.59Improved
Add temporal overlap loss L_iou (ablation)GF(uns) · AGQAAccuracy: 52.89 -> 54.59Improved
Add individual certainty loss L_cert (ablation)GF(uns) · AGQAAccuracy: 54.12 -> 54.59Improved
Add supervised event classification loss L_cls (ablation)GF(sup) · AGQAAccuracy: 53.19 -> 55.08Improved
Add supervised temporal span L1 loss (ablation)GF(sup) · AGQAAccuracy: 54.26 -> 55.08Improved
Train event-memory generation without event labels rather than with supervisionGlance-Focus · STARMean accuracy: 53.86 vs 53.94No clear effect
Train event-memory generation without event labels rather than with supervisionGlance-Focus · EgoTaskQAAll accuracy: 43.06 vs 44.27Mixed

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