AI Paper Atlas

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

Validated Image Caption Rating Dataset

Lothar Narins, Andrew T Scott, Aakash Gautam, Anagha Kulkarni, Mar Castanon, Benjamin Kao, Shasta Ihorn, Yue-Ting Siu, James M Mason, Alexander Mario Blum, Ilmi Yoon

NeurIPS 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Neural image captioning

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
rate with VICR 5-level scale and game instead of Flickr8k-Expert scaledataset · inter-rater agreementKendall's W: 84.0 -> 93.8Improved
rate with VICR 5-level scale and game instead of Flickr8k-Expert scaledataset · inter-rater agreementFleiss kappa: 48.8 -> 58.1Improved
rate with VICR 5-level scale and game instead of Flickr8k-Expert scaledataset · inter-rater agreementKendall tau X-YZ: 47.7 -> 75.6Improved
evaluate CIDEr on VICR rather than Flickr8k-ExpertCIDEr · test setKendall tau: 44.1 -> 66.6Improved
evaluate RefCLIPScore on VICR rather than Flickr8k-ExpertRefCLIPScore · test setKendall tau: 51.9 -> 71.7Improved
train rating predictor on VICR instead of Flickr8k-Expert (ablation)ModelVICR · VICR testKendall tau: 71.8 -> 75.8Improved
train rating predictor on VICR instead of Flickr8k-Expert (ablation)ModelVICR · Flickr8k-Expert testKendall tau: 53.7 -> 53.1Hurt
use trained ModelVICR instead of CLIPScoreModelVICR · VICR testKendall tau: 67.3 -> 75.8Improved
raise rater training score by 10%rater training · simulated rating gamerater competency (logits): +0.17 logitsImproved
use reference-free CLIPScore instead of reference-based CIDErCLIPScore · Flickr8k-Expert testKendall tau: 44.1 -> 50.7Improved

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