Di Hu

2.3k total citations · 1 hit paper
62 papers, 1.2k citations indexed

About

Di Hu is a scholar working on Signal Processing, Computer Vision and Pattern Recognition and Artificial Intelligence. According to data from OpenAlex, Di Hu has authored 62 papers receiving a total of 1.2k indexed citations (citations by other indexed papers that have themselves been cited), including 27 papers in Signal Processing, 23 papers in Computer Vision and Pattern Recognition and 12 papers in Artificial Intelligence. Recurrent topics in Di Hu's work include Music and Audio Processing (23 papers), Speech and Audio Processing (20 papers) and Video Analysis and Summarization (8 papers). Di Hu is often cited by papers focused on Music and Audio Processing (23 papers), Speech and Audio Processing (20 papers) and Video Analysis and Summarization (8 papers). Di Hu collaborates with scholars based in China, United States and Hong Kong. Di Hu's co-authors include Xuelong Li, Feiping Nie, Yake Wei, Dong Wang, Xiaokang Peng, Xiaoqiang Lu, Yingfeng Zhang, Yang Liu, Geng Zhang and Chi‐Ming Che and has published in prestigious journals such as Angewandte Chemie International Edition, IEEE Transactions on Pattern Analysis and Machine Intelligence and IEEE Transactions on Image Processing.

In The Last Decade

Di Hu

57 papers receiving 1.2k 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.

Balanced Multimodal Learning via On-the-fly Gradient Modulation

2022 154 citations Yake Wei, Di Hu et al. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) profile →

Peers — A (Enhanced Table)

Peers by citation overlap · career bar shows stage (early→late) cites · hero ref

Name	h						Papers	Cites
Di Hu China	18	576	283	269	107	102	62	1.2k
Siyu Xia China	14	603 1.0×	161 0.6×	141 0.5×	36 0.3×	33 0.3×	85	899
Xiaobo Wang China	15	532 0.9×	248 0.9×	239 0.9×	87 0.8×	25 0.2×	41	983
Kunhong Liu China	21	397 0.7×	474 1.7×	153 0.6×	223 2.1×	25 0.2×	101	1.5k
Minghao Yang China	22	303 0.5×	265 0.9×	148 0.6×	99 0.9×	20 0.2×	118	1.5k
Shanmugasundaram Hariharan India	17	138 0.2×	253 0.9×	47 0.2×	26 0.2×	28 0.3×	210	1.2k
N. Sudha India	20	654 1.1×	145 0.5×	216 0.8×	55 0.5×	9 0.1×	132	1.3k
Furao Shen China	17	421 0.7×	613 2.2×	91 0.3×	86 0.8×	20 0.2×	57	1.1k
Jiajun Lin China	15	162 0.3×	193 0.7×	88 0.3×	27 0.3×	15 0.1×	85	622
Lijuan Luo China	14	137 0.2×	131 0.5×	46 0.2×	204 1.9×	21 0.2×	42	908
Zhongnan Zhang China	19	71 0.1×	143 0.5×	87 0.3×	407 3.8×	32 0.3×	74	1.4k

Countries citing papers authored by Di Hu

Since Specialization

Citations

This map shows the geographic impact of Di Hu'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 Di Hu with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Di Hu more than expected).

Fields of papers citing papers by Di Hu

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Di Hu. 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 Di Hu. The network helps show where Di Hu may publish in the future.

Co-authorship network of co-authors of Di Hu

This figure shows the co-authorship network connecting the top 25 collaborators of Di Hu. A scholar is included among the top collaborators of Di Hu 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 Di Hu. Di Hu 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.

Hu, Di, et al.. (2025). Phoenix: A Motion-Based Self-Reflection Framework for Fine-Grained Robotic Action Correction. 6981–6990.

2.

Huang, Xinlei, Di Hu, Wei Zhang, et al.. (2025). The priority effect of microbial community on the initiation of Chinese rice wine fermentation and flavor formation. Food Bioscience. 69. 106771–106771. 2 indexed citations

3.

Wei, Yake, et al.. (2025). Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition. 25854–25863.

4.

He, Haiying, et al.. (2025). Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception. 3963–3973. 1 indexed citations

5.

Wang, Dong, et al.. (2024). Kinematic-aware Prompting for Generalizable Articulated Object Manipulation with LLMs. 2073–2080. 8 indexed citations

6.

Zhang, Honggang, et al.. (2024). Unveiling and Mitigating Bias in Audio Visual Segmentation. 7259–7268.

7.

Li, Guangyao, et al.. (2024). Boosting Audio Visual Question Answering via Key Semantic-Aware Cues. 5997–6005. 3 indexed citations

8.

Chen, Yuanyuan, Wen Liu, Di Hu, et al.. (2022). Abnormal developmental trends of functional connectivity in young children with infantile esotropia. Frontiers in Neuroscience. 16. 972882–972882. 2 indexed citations

9.

Li, Guangyao, Yake Wei, Yapeng Tian, et al.. (2022). Learning to Answer Questions in Dynamic Audio-Visual Scenarios. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 19086–19096. 49 indexed citations

10.

Heidler, Konrad, Lichao Mou, Di Hu, et al.. (2022). Self-supervised audiovisual representation learning for remote sensing data. International Journal of Applied Earth Observation and Geoinformation. 116. 103130–103130. 32 indexed citations

11.

Zhou, Dongzhan, Xinchi Zhou, Di Hu, et al.. (2022). SepFusion: Finding Optimal Fusion Structures for Visual Sound Separation. Proceedings of the AAAI Conference on Artificial Intelligence. 36(3). 3544–3552. 10 indexed citations

12.

Bai, Zechen, Zhigang Wang, Jian Wang, Di Hu, & Errui Ding. (2021). Unsupervised Multi-Source Domain Adaptation for Person Re-Identification. 12909–12918. 67 indexed citations

13.

Hu, Di, Xuhong Li, Lichao Mou, et al.. (2020). Cross-Task Transfer for Multimodal Aerial Scene Recognition.. arXiv (Cornell University). 2 indexed citations

14.

Wang, Yunxiao, Zheng Liu, Di Hu, & Mian Zhang. (2019). Multivariate Time Series Prediction Based on Optimized Temporal Convolutional Networks with Stacked Auto-encoders.. Asian Conference on Machine Learning. 157–172. 5 indexed citations

15.

Hu, Di, Feiping Nie, & Xuelong Li. (2018). Deep Co-Clustering for Unsupervised Audiovisual Learning.. arXiv (Cornell University). 4 indexed citations

16.

Hu, Di, Feiping Nie, & Xuelong Li. (2018). Deep Binary Reconstruction for Cross-Modal Hashing. IEEE Transactions on Multimedia. 21(4). 973–985. 106 indexed citations

17.

Hu, Di, Feiping Nie, & Xuelong Li. (2018). Discrete Spectral Hashing for Efficient Similarity Retrieval. IEEE Transactions on Image Processing. 28(3). 1080–1091. 30 indexed citations

18.

Long, Yi, et al.. (2017). A survey on social image understanding. 2. 1–5. 2 indexed citations

19.

Hu, Di. (2015). Research on Service Encapsulation Method of Geographical Model. Acta Geodaetica et Cartographica Sinica. 44(11). 1298. 1 indexed citations

20.

Hu, Di, Yungen Liu, Yau‐Tsz Lai, et al.. (2015). Anticancer Gold(III) Porphyrins Target Mitochondrial Chaperone Hsp60. Angewandte Chemie. 128(4). 1409–1413. 20 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