AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

JourneyDB: A Benchmark for Generative Image Understanding

Keqiang Sun, Junting Pan, Yuying Ge, Hao Li, Haodong Duan, Xiaoshi Wu, Renrui Zhang, Aojun Zhou, Zipeng Qin, Yi Wang, Jifeng Dai, Yu Qiao and 2 more

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 11 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
fine-tune on JourneyDB for 20 epochsUni-Perceiver v2 · JourneyDB prompt inversion testCIDEr: 15.45 -> 34.01Improved
fine-tune on JourneyDBUni-Perceiver v2 · JourneyDB image captioning valCIDEr: 21.88 -> 50.72Improved
fine-tune on JourneyDBUni-Perceiver v2 · JourneyDB image captioning testCIDEr: 20.13 -> 31.76Mixed
fine-tune on JourneyDBUni-Perceiver v2 · JourneyDB prompt inversion testSimilarity: 0.34 -> 0.51Improved
restrict style retrieval to per-category space instead of overallCLIP-ViT-L/14 · JourneyDB style retrieval testrecall: 0.47 -> 41.33Improved
evaluate on style questions instead of content questionsBLIP-2 FlanT5 · JourneyDB MC-VQA testaccuracy (%): 69.7 -> 57.4Hurt
evaluate generated images instead of real COCO imagesBLIP-2 OPT · captioning CIDErCIDEr: 145.8 -> 37.60Hurt

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