AI Paper Atlas

Research map / Video / Video-language understanding

Simple Baselines for Interactive Video Retrieval with Questions and Answers

Kaiqu Liang, Samuel Albanie

ICCV 2023 · Video › Video-language understanding · approach: Video question answering · 12 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
add Heuristic question-answer interaction to BLIPBLIP · MSR-VTT 1k-AR@1: 43.3 -> 67.9Improved
add Heuristic question-answer interaction to BLIPBLIP · MSVDR@1: 44.2 -> 74.2Improved
add Heuristic question-answer interaction to BLIPBLIP · AVSDR@1: 27.3 -> 39.5Improved
add Ask Object (AO) augmentation to Auto-text (ablation)Auto-text question generator · MSR-VTT 1k-AR@1: 47.6 -> 62.2Improved
add Ask Object (AO) augmentation to Auto-text-vid (ablation)Auto-text-vid question generator · MSR-VTT 1k-AR@1: 49.0 -> 57.6Improved
condition question generation on top-k retrieved video captions (Auto-text-vid vs Auto-text), with AO (ablation)Auto-text · MSR-VTT 1k-AR@1: 62.2 -> 57.6Hurt
condition question generation on top-k retrieved video captions (Auto-text-vid vs Auto-text), without AO (ablation)Auto-text · MSR-VTT 1k-AR@1: 47.6 -> 49.0Improved
answer with VideoQA model instead of caption plus language model (CAP+LM) (ablation)Interactive retrieval answer generator · 50 MSR-VTT videos, Heuristic questionsR@1: 60.0 -> 66.0Improved
answer with VideoQA model instead of caption plus language model (CAP+LM) (ablation)Interactive retrieval answer generator · 50 MSR-VTT videosavg answer time (s): 8.0 -> 0.1Improved
simulate user with VideoQA instead of human answers (ablation)Heuristic question generator · 50 MSR-VTT videosR@1: 69.0 (human) vs 66.0 (VideoQA)No clear effect
concatenate all 10 rounds of ground-truth AVSD dialog with the queryBLIP · AVSDR@1: 27.3 -> 27.4No clear effect
add Heuristic interaction to BLIP on long-form videoBLIP · ActivityNetR@1: 35.3 -> 44.8Improved

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