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.
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
20212.4k citationsPhilip H. S. Torr et al.profile →
Res2Net: A New Multi-Scale Backbone Architecture
20192.2k citationsShanghua Gao, Ming‐Ming Cheng et al.IEEE Transactions on Pattern Analysis and Machine Intelligenceprofile →
Global Contrast Based Salient Region Detection
20141.8k citationsMing‐Ming Cheng, Philip H. S. Torr et al.IEEE Transactions on Pattern Analysis and Machine Intelligenceprofile →
Struck: Structured output tracking with kernels
20111.3k citationsPhilip H. S. Torr et al.profile →
Point Transformer
20211.2k citationsPhilip H. S. Torr et al.profile →
Countries citing papers authored by Philip H. S. Torr
Since
Specialization
Citations
This map shows the geographic impact of Philip H. S. Torr'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 Philip H. S. Torr with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Philip H. S. Torr more than expected).
Fields of papers citing papers by Philip H. S. Torr
This network shows the impact of papers produced by Philip H. S. Torr. 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 Philip H. S. Torr. The network helps show where Philip H. S. Torr may publish in the future.
Co-authorship network of co-authors of Philip H. S. Torr
This figure shows the co-authorship network connecting the top 25 collaborators of Philip H. S. Torr.
A scholar is included among the top collaborators of Philip H. S. Torr 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 Philip H. S. Torr. Philip H. S. Torr is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
Torr, Philip H. S., et al.. (2021). Class-agnostic segmentation loss and its application to salient object detection and segmentation. Oxford University Research Archive (ORA) (University of Oxford).3 indexed citations
6.
Chen, Lin, et al.. (2021). A Continuous Mapping For Augmentation Design. Neural Information Processing Systems. 34.1 indexed citations
Zhang, Hongguang, Li Zhang, Xiaojuan Qi, et al.. (2020). Few-shot Action Recognition via Improved Attention with Self-supervision. arXiv (Cornell University).2 indexed citations
9.
Wang, Qiang, Li Zhang, Luca Bertinetto, Weiming Hu, & Philip H. S. Torr. (2019). Fast Online Object Tracking and Segmentation: A Unifying Approach. 1328–1338.955 indexed citations breakdown →
10.
Chaudhry, Arslan, Marcus Rohrbach, Mohamed Elhoseiny, et al.. (2019). Continual learning with tiny episodic memories. Oxford University Research Archive (ORA) (University of Oxford).100 indexed citations
11.
Gao, Shanghua, Ming‐Ming Cheng, Kai Zhao, et al.. (2019). Res2Net: A New Multi-Scale Backbone Architecture. IEEE Transactions on Pattern Analysis and Machine Intelligence. 43(2). 652–662.2229 indexed citations breakdown →
12.
Zhang, Li, Xiangtai Li, Anurag Arnab, et al.. (2019). Dual Graph Convolutional Network for Semantic Segmentation.. Oxford University Research Archive (ORA) (University of Oxford). 254.23 indexed citations
13.
Nardelli, Nantas, Gabriel Synnaeve, Zeming Lin, et al.. (2018). Value Propagation Networks.. Oxford University Research Archive (ORA) (University of Oxford).6 indexed citations
14.
de, Rodrigo, Arnab Ghosh, Thalaiyasingam Ajanthan, et al.. (2018). DGPose: Disentangled Semi-supervised Deep Generative Models for Human Body Analysis.. arXiv (Cornell University).
Hou, Qibin, Ming‐Ming Cheng, Xiaowei Hu, et al.. (2018). Deeply Supervised Salient Object Detection with Short Connections. IEEE Transactions on Pattern Analysis and Machine Intelligence. 41(4). 815–828.497 indexed citations breakdown →
17.
de, Rodrigo, Anurag Arnab, Stuart Golodetz, Michael Sapienza, & Philip H. S. Torr. (2018). Deep Fully-Connected Part-Based Models for Human Pose Estimation. Oxford University Research Archive (ORA) (University of Oxford). 327–342.8 indexed citations
18.
Bertinetto, Luca, João F. Henriques, Jack Valmadre, Philip H. S. Torr, & Andrea Vedaldi. (2016). Learning feed-forward one-shot learners. Oxford University Research Archive (ORA) (University of Oxford). 29. 523–531.88 indexed citations
19.
Bunel, Rudy, Alban Desmaison, Manish Kumar, Philip H. S. Torr, & Pushmeet Kohli. (2016). Learning to superoptimize programs. Oxford University Research Archive (ORA) (University of Oxford).3 indexed citations
20.
Criminisi, Antonio, Jamie Shotton, Andrew Blake, & Philip H. S. Torr. (2003). Gaze Manipulation for One-to-one Teleconferencing. Oxford University Research Archive (ORA) (University of Oxford). 191–198.56 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.