AI Paper Atlas

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

Web-Based Semantic Fragment Discovery for On-Line Lingual-Visual Similarity

Xiaoshuai Sun, Jiewei Cao, Chao Li, Lei Zhu, Heng Tao Shen

AAAI 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 2 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
use CNN fc7 features instead of GIST (ablation)self-similarity quality assessment · Flickr30K-QualityAUC: 0.7376 -> 0.8537Improved
use fc6 relu instead of fc6 features (ablation)self-similarity measure · Flickr30K-QualityAUC: 0.8512 -> 0.8512No clear effect
use fc7 relu instead of fc7 (ablation)self-similarity measure · Flickr30K-QualityAUC: 0.8537 -> 0.8525No clear effect
increase object proposals from 1 to 20 (option P) (ablation)label-free retrieval · Flickr30KRecall@10: 33.5 -> 37.1Improved
increase object proposals from 1 to 20 (option T) (ablation)label-free retrieval · Flickr30KRecall@10: 26.7 -> 28.3Improved
increase object proposals from 1 to 20 (option G) (ablation)label-free retrieval · Flickr30KRecall@10: 33.7 -> 37.4Improved
use option P instead of T (20 OP) (ablation)label-free retrieval · Flickr30KRecall@1: 7.4 -> 10.4Improved
use option G instead of P (20 OP) (ablation)label-free retrieval · Flickr30KRecall@10: 37.1 -> 37.4No clear effect
use Eqn. 4 instead of Eqn. 5 option G (20 OP) (ablation)label-free retrieval · Flickr30KRecall@1: 10.5 -> 10.7No clear effect
use fc7 relu instead of fc6 CNN layer (ablation)label-free retrieval · Flickr30KRecall@10: 28.4 -> 37.4Improved
use fc7 instead of fc6 relu CNN layer (ablation)label-free retrieval · Flickr30KRecall@10: 33.6 -> 33.9No clear effect
increase top object proposals from 1 to 10 (ablation)label-free retrieval · Flickr30KRecall@10: 31.0 -> 36.7Improved

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