Hao Cheng

3.6k total citations · 1 hit paper
44 papers, 1.8k citations indexed

About

Hao Cheng is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Signal Processing. According to data from OpenAlex, Hao Cheng has authored 44 papers receiving a total of 1.8k indexed citations (citations by other indexed papers that have themselves been cited), including 30 papers in Artificial Intelligence, 16 papers in Computer Vision and Pattern Recognition and 7 papers in Signal Processing. Recurrent topics in Hao Cheng's work include Topic Modeling (16 papers), Natural Language Processing Techniques (13 papers) and Advanced Image and Video Retrieval Techniques (9 papers). Hao Cheng is often cited by papers focused on Topic Modeling (16 papers), Natural Language Processing Techniques (13 papers) and Advanced Image and Video Retrieval Techniques (9 papers). Hao Cheng collaborates with scholars based in United States, Singapore and China. Hao Cheng's co-authors include Jianfeng Gao, Hoifung Poon, Tristan Naumann, 裕二池谷, Robert Tinn, Naoto Usuyama, Xiaodong Liu, Michael Lucas, Mari Ostendorf and Kien A. Hua and has published in prestigious journals such as Information Sciences, Remote Sensing and IEEE Transactions on Neural Networks and Learning Systems.

In The Last Decade

Hao Cheng

43 papers receiving 1.7k citations

Hit Papers

align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing

2021 1.0k citations 裕二池谷, Robert Tinn et al. arXiv (Cornell University) profile →

Peers

Hao Cheng

AI

MB

CVPR

HI

RNMI

Yingce Xia China

Chengsheng Mao United States

Alberto Lavelli Italy

Liang Yao China

Pengtao Xie United States

Zhicheng Cui United States

Been Kim United States

Yacine Jernite United States

Anand D. Sarwate United States

Yingce Xia China

Hao Cheng

985 ×0.8

AI

287 ×0.6

MB

383 ×1.1

CVPR

151 ×0.9

HI

89 ×0.8

RNMI

Citations per year, relative to Hao Cheng Hao Cheng (= 1×) peers Yingce Xia

Countries citing papers authored by Hao Cheng

Since Specialization

Citations

This map shows the geographic impact of Hao Cheng's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Hao Cheng with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Hao Cheng more than expected).

Fields of papers citing papers by Hao Cheng

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Hao Cheng. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Hao Cheng. The network helps show where Hao Cheng may publish in the future.

Co-authorship network of co-authors of Hao Cheng

This figure shows the co-authorship network connecting the top 25 collaborators of Hao Cheng. A scholar is included among the top collaborators of Hao Cheng based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with Hao Cheng. Hao Cheng is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

1.

Cheng, Hao, et al.. (2024). Lattice-Aided Extraction of Spread-Spectrum Hidden Data. IEEE Transactions on Information Forensics and Security. 19. 5684–5695.

2.

Tinn, Robert, Hao Cheng, 裕二池谷, et al.. (2023). Fine-tuning large neural language models for biomedical natural language processing. Patterns. 4(4). 100729–100729. 72 indexed citations

3.

Cheng, Hao, Joey Tianyi Zhou, Wee Peng Tay, & Bihan Wen. (2023). Graph Neural Networks With Triple Attention for Few-Shot Learning. IEEE Transactions on Multimedia. 25. 8225–8239. 18 indexed citations

4.

Ma, Kaixin, Hao Cheng, Yu Zhang, et al.. (2023). Chain-of-Skills: A Configurable Model for Open-Domain Question Answering. 1599–1618. 3 indexed citations

5.

Cheng, Hao, Kim–Hui Yap, & Bihan Wen. (2023). Reconciliation of statistical and spatial sparsity for robust visual classification. Neurocomputing. 529. 140–151. 1 indexed citations

6.

Cheng, Hao, et al.. (2023). Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding. 12259–12275. 4 indexed citations

7.

Cheng, Wei, Yan Wang, Peng Zheng, et al.. (2022). High precision reconstruction of silicon photonics chaos with stacked CNN-LSTM neural networks. Chaos An Interdisciplinary Journal of Nonlinear Science. 32(5). 53112–53112. 8 indexed citations

8.

Cheng, Hao, Joey Tianyi Zhou, Wee Peng Tay, & Bihan Wen. (2022). Attentive Graph Neural Networks for Few-Shot Learning. 152–157. 5 indexed citations

9.

Cheng, Hao, et al.. (2021). Mixture of Robust Experts (MoRE): A Flexible Defense Against Multiple Perturbations.. arXiv (Cornell University). 1 indexed citations

10.

Cheng, Hao, Yelong Shen, Xiaodong Liu, et al.. (2021). UnitedQA: A Hybrid Approach for Open Domain Question Answering. 3080–3090. 21 indexed citations

11.

Lee, Chia‐Hsuan, Hao Cheng, & Mari Ostendorf. (2021). Dialogue State Tracking with a Language Model using Schema-Driven Prompting. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 4937–4949. 61 indexed citations

12.

Cheng, Hao, et al.. (2021). Posterior Differential Regularization with f-divergence for Improving Model Robustness. 1078–1089. 14 indexed citations

13.

Cheng, Hao, Hao Fang, & Mari Ostendorf. (2019). A Dynamic Speaker Model for Conversational Interactions. 9 indexed citations

14.

Fang, Hao, Hao Cheng, & Mari Ostendorf. (2016). Learning Latent Local Conversation Modes for Predicting Comment Endorsement in Online Discussions. 55–64. 7 indexed citations

15.

Cheng, Hao, et al.. (2016). Scalable and Sound Low-Rank Tensor Learning. International Conference on Artificial Intelligence and Statistics. 1114–1123. 6 indexed citations

16.

Devlin, Jacob, Hao Cheng, Hao Fang, et al.. (2015). Language Models for Image Captioning: The Quirks and What Works. 100–105. 131 indexed citations

17.

Yu, Yaoliang, Hao Cheng, Dale Schuurmans, & Csaba Szepesvári. (2013). Characterizing the Representer Theorem. International Conference on Machine Learning. 570–578. 6 indexed citations

18.

Yu, Ning, Kien A. Hua, & Hao Cheng. (2011). A Multi-Directional Search technique for image annotation propagation. Journal of Visual Communication and Image Representation. 23(1). 237–244. 7 indexed citations

19.

Cheng, Hao, Kien A. Hua, & Ning Yu. (2009). An automatic feature generation approach to multiple instance learning and its applications to image databases. Multimedia Tools and Applications. 47(3). 507–524. 6 indexed citations

20.

Vu, Khanh, et al.. (2006). A non-linear dimensionality-reduction technique for fast similarity search in large databases. Journal of International Crisis and Risk Communication Research. 527–538. 15 indexed citations

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact