AI Paper Atlas

Research map / Video / Video-language understanding

FunQA: Towards Surprising Video Comprehension

Binzhu Xie, Sicheng Zhang, Zitang Zhou, Bo Li, Yuanhan Zhang, Jack Hessel, Jingkang Yang, Ziwei Liu

ECCV 2024 · Video › Video-language understanding · approach: Video question answering · 24 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 FunMentor multi-turn refinement agent to Video-ChatGPTVideo-ChatGPT · HumorQA H2 descriptionGPT-4 score: 24.3 -> 33.2Improved
add FunMentor to Video-ChatGPTVideo-ChatGPT · HumorQA H4 titleGPT-4 score: 41.2 -> 65.1Improved
add FunMentor to Video-ChatGPTVideo-ChatGPT · HumorQA H3 reasoningGPT-4 score: 24.9 -> 36.5Improved
add FunMentor to Otter (FunQA)Otter (FunQA) · HumorQA H3 reasoningGPT-4 score: 31.7 -> 45.8Improved
add FunMentor to Otter (FunQA)Otter (FunQA) · CreativeQA C5 scoringaccuracy: 69.4 -> 69.4No clear effect
add FunMentor to Otter (FunQA)Otter (FunQA) · HumorQA H2 descriptionBLEURT: 38.4 -> 33.4Hurt
fine-tune Otter on FunQA instead of Dense CaptionOtter · FunQA free-text (10% sample)GPT-4 score: 22 -> 28Improved
use timestamp-capable TimeChat versus mean time span baselinelocalization · HumorQA H1IOU: 55.5 -> 8.4Hurt
evaluate with WUPS versus GPT-4 metricOtter (FunQA) · NExT-OEWUPS vs GPT-4: 0.79 WUPS vs 73.06 GPT-4Mixed

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