YHYuting Hu

Yuting Hu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuting Hu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    VAE-Stega: Linguistic Steganography Based on Variational Auto-Encoder

    by Zhong-Liang Yang, Si-Yu Zhang, Yu-Ting Hu, Zhi-Wen Hu, Yong-Feng Huang

    In recent years, linguistic steganography based on text auto-generation technology has been greatly developed, which is considered to be a very promising but also a very challenging research topic. Previous works mainly focus on optimizing the language model and conditional probability coding methods, aiming at generating steganographic sentences with better quality. In this paper, we first report some of our latest experimental findings, which seem to indicate that the quality of the generated steganographic text cannot fully guarantee its steganographic security, and even has a prominent perceptualimperceptibility and statistical-imperceptibility conflict (Psic) effect. To further improve the imperceptibility and security of generated steganographic texts, in this paper, we propose a new linguistic steganography based on Variational Auto- Encoder (VAE), which can be called VAE-Stega. We use the encoder in VAE-Stega to learn the overall statistical distribution characteristics of a large number of normal texts, and then use the decoder in VAE-Stega to generate steganographic sentences which conform to both of the statistical language model as well as the overall statistical distribution of normal sentences, so as to guarantee both the perceptual-imperceptibility and statisticalimperceptibility of the generated steganographic texts at the same time. We design several experiments to test the proposed method. Experimental results show that the proposed model can greatly improve the imperceptibility of the generated steganographic sentences when comparing with the previous methods, which achieves the state of the art performance.


  • Twitter100k: A Real-World Dataset for Weakly Supervised Cross-Media Retrieval

    by Yuting Hu, Liang Zheng, Yi Yang, Yongfeng Huang

    This paper contributes a new large-scale dataset for weakly supervised cross-media retrieval, named Twitter100k. Current datasets, such as Wikipedia, NUS Wide and Flickr30k, have two major limitations. First, these datasets are lacking in content diversity, i.e., only some pre-defined classes are covered. Second, texts in these datasets are written in well-organized language, leading to inconsistency with realistic applications. To overcome these drawbacks, the proposed Twitter100k dataset 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, we also design a deep neural network to learn cross-modal embeddings for Twitter100k. Inspired by the characteristic of Twitter100k, we propose a method to integrate Optical Character Recognition (OCR) into cross-media retrieval. The experiment results show that the proposed method improves the baseline performance.


  • Open Access

    Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval

    by Yuting Hu, Liang Zheng, Yi Yang, Yongfeng Huang

    This paper contributes a new large-scale dataset for weakly supervised cross-media retrieval, named Twitter100k. Current datasets, such as Wikipedia, NUS Wide and Flickr30k, have two major limitations. First, these datasets are lacking in content diversity, i.e., only some pre-defined classes are covered. Second, texts in these datasets are written in well-organized language, leading to inconsistency with realistic applications. To overcome these drawbacks, the proposed Twitter100k dataset 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. Novel insights are provided. 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.