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.
Coordinate Attention for Efficient Mobile Network Design
20213.5k citationsQibin Hou, Daquan Zhou et al.profile →
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
20211.4k citationsTao Wang, Francis E. H. Tay et al.profile →
This map shows the geographic impact of Jiashi Feng'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 Jiashi Feng with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Jiashi Feng more than expected).
This network shows the impact of papers produced by Jiashi Feng. 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 Jiashi Feng. The network helps show where Jiashi Feng may publish in the future.
Co-authorship network of co-authors of Jiashi Feng
This figure shows the co-authorship network connecting the top 25 collaborators of Jiashi Feng.
A scholar is included among the top collaborators of Jiashi Feng 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 Jiashi Feng. Jiashi Feng is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Zhang, Jianfeng, Xuecheng Nie, & Jiashi Feng. (2020). Inference Stage Optimization for Cross-scenario 3D Human Pose Estimation. Neural Information Processing Systems. 33. 2408–2419.4 indexed citations
8.
Wang, Kaixin, Bingyi Kang, Jie Shao, & Jiashi Feng. (2020). Improving Generalization in Reinforcement Learning with Mixture Regularization. Neural Information Processing Systems. 33. 7968–7978.1 indexed citations
9.
Li, Guilin, Junlei Zhang, Yunhe Wang, et al.. (2020). Residual Distillation: Towards Portable Deep Neural Networks without Shortcuts. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 33. 8935–8946.7 indexed citations
10.
Zhou, Daquan, Xiaojie Jin, Qibin Hou, et al.. (2020). Neural Epitome Search for Architecture-Agnostic Network Compression. International Conference on Learning Representations.3 indexed citations
Zhang, Mengmi, Tao Wang, Joo‐Hwee Lim, & Jiashi Feng. (2019). Prototype Reminding for Continual Learning.. arXiv (Cornell University).3 indexed citations
15.
Li, Yuan, Tao Wang, Xiaopeng Zhang, et al.. (2019). Central Similarity Hashing via Hadamard matrix.. arXiv (Cornell University).2 indexed citations
16.
Zhou, Pan & Jiashi Feng. (2018). Understanding Generalization and Optimization Performance of Deep CNNs. Singapore Management University Institutional Knowledge (InK) (Singapore Management University). 5960–5969.3 indexed citations
17.
Zhang, Mengmi, Jiashi Feng, Joo‐Hwee Lim, Qi Zhao, & Gabriel Kreiman. (2018). What am I searching for. DSpace@MIT (Massachusetts Institute of Technology).1 indexed citations
18.
Kang, Bingyi, Zequn Jie, & Jiashi Feng. (2018). Policy Optimization with Demonstrations. International Conference on Machine Learning. 2469–2478.37 indexed citations
19.
Fu, Jie, Danlu Chen, Miao Liu, et al.. (2016). Deep Reinforcement Learning for Accelerating the Convergence Rate. arXiv (Cornell University).
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.