by No License
by Unknown License
The Twitter100k is a A Real-world Dataset for Weakly Supervised Cross-Media Retrieval by Yuting Hu, Liang Zheng, Yi Yang, and Yongfeng Huang.This contributes a new large-scale dataset for weakly supervised cross-media retrieval, named Twitter100k. It is characterized by two aspects: 1) it has 100,000 image-text pairs randomly crawled from Twitter and thus has no constraint in the image categories; 2) text in Twitter100k is written in informal language by the users.Since strongly supervised methods leverage the class labels that may be missing in practice, this paper focuses on weakly supervised learning for cross-media retrieval, in which only text-image pairs are exploited during training. We extensively benchmark the performance of four subspace learning methods and three variants of the Correspondence AutoEncoder, along with various text features on Wikipedia, Flickr30k and Twitter100k.As a minor contribution, inspired by the characteristic of Twitter100k, we propose an OCR-based cross-media retrieval method. In experiment, we show that the proposed OCR-based method improves the baseline performance.
CategoriesTwitter, Text, Image, Sentence, Pair, Multimodal, Weakly, Supervision