Anurag Arnab

3.0k total citations · 1 hit paper
28 papers, 880 citations indexed

About

Anurag Arnab is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Signal Processing. According to data from OpenAlex, Anurag Arnab has authored 28 papers receiving a total of 880 indexed citations (citations by other indexed papers that have themselves been cited), including 24 papers in Computer Vision and Pattern Recognition, 8 papers in Artificial Intelligence and 3 papers in Signal Processing. Recurrent topics in Anurag Arnab's work include Multimodal Machine Learning Applications (11 papers), Human Pose and Action Recognition (9 papers) and Advanced Neural Network Applications (7 papers). Anurag Arnab is often cited by papers focused on Multimodal Machine Learning Applications (11 papers), Human Pose and Action Recognition (9 papers) and Advanced Neural Network Applications (7 papers). Anurag Arnab collaborates with scholars based in United States, United Kingdom and Australia. Anurag Arnab's co-authors include Philip H. S. Torr, Cordelia Schmid, Paul Hongsuck Seo, Yan Shen, Arsha Nagrani, Xuehan Xiong, Mi Zhang, Chen Sun, Zhichao Lu and Li Zhang and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition and IEEE Signal Processing Magazine.

In The Last Decade

Anurag Arnab

26 papers receiving 862 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.

Multiview Transformers for Video Recognition

2022 180 citations Yan Shen, Xuehan Xiong 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
Anurag Arnab United States	12	669	364	46	45	38	28	880
Karttikeya Mangalam United States	10	589 0.9×	341 0.9×	42 0.9×	52 1.2×	24 0.6×	19	877
Renrui Zhang China	10	453 0.7×	312 0.9×	45 1.0×	22 0.5×	50 1.3×	18	732
Pengfei Xu China	16	678 1.0×	366 1.0×	76 1.7×	31 0.7×	45 1.2×	53	901
Qiu Chen Japan	16	436 0.7×	316 0.9×	81 1.8×	25 0.6×	55 1.4×	97	821
Karteek Alahari France	13	704 1.1×	273 0.8×	70 1.5×	64 1.4×	18 0.5×	26	801
Ramazan Gökberk Cinbiş Türkiye	13	669 1.0×	335 0.9×	107 2.3×	62 1.4×	54 1.4×	27	838
Anna Khoreva Germany	11	1.1k 1.7×	379 1.0×	72 1.6×	36 0.8×	59 1.6×	18	1.3k
Gedas Bertasius United States	14	823 1.2×	261 0.7×	110 2.4×	35 0.8×	46 1.2×	35	1.0k
Canlong Zhang China	18	631 0.9×	316 0.9×	65 1.4×	65 1.4×	17 0.4×	90	866

Countries citing papers authored by Anurag Arnab

Since Specialization

Citations

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

Fields of papers citing papers by Anurag Arnab

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Anurag Arnab

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

Arnab, Anurag, et al.. (2024). VicTR: Video-conditioned Text Representations for Activity Recognition. 18547–18558. 11 indexed citations

2.

Gritsenko, Alexey A., Xuehan Xiong, Josip Djolonga, et al.. (2024). End-to-End Spatio-Temporal Action Localisation with Video Transformers. 18373–18383. 5 indexed citations

3.

Hong, Sunghwan, et al.. (2024). CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation. 4113–4123. 31 indexed citations

4.

Xu, Jiarui, Xingyi Zhou, Yan Shen, et al.. (2024). Pixel Aligned Language Models. 13030–13039. 2 indexed citations

5.

Gritsenko, Alexey A., et al.. (2024). Time-, Memory- and Parameter-Efficient Visual Adaptation. 5536–5545. 5 indexed citations

6.

Zhou, Xingyi, Anurag Arnab, Yan Shen, et al.. (2024). Streaming Dense Video Captioning. 18243–18252. 9 indexed citations

7.

Vasconcelos, Cristina Nader, et al.. (2024). PLANTED: A Dataset for Planted Forest Identification from Multi-Satellite Time Series. 7066–7070. 1 indexed citations

8.

Georgescu, Mariana-Iuliana, et al.. (2023). Audiovisual Masked Autoencoders. 16098–16108. 21 indexed citations

9.

Connell, David, Derek E. Moulton, Sarah L. Waters, et al.. (2023). An automated method for tendon image segmentation on ultrasound using grey-level co-occurrence matrix features and hidden Gaussian Markov random fields. Computers in Biology and Medicine. 169. 107872–107872. 8 indexed citations

10.

Ryoo, Michael S., Keerthana Gopalakrishnan, Ted Xiao, et al.. (2023). Token Turing Machines. 19070–19081. 4 indexed citations

11.

Seo, Paul Hongsuck, Arsha Nagrani, Anurag Arnab, & Cordelia Schmid. (2022). End-to-end Generative Pretraining for Multimodal Video Captioning. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 17938–17947. 106 indexed citations

12.

Zhang, Li, Mohan Chen, Anurag Arnab, Xiangyang Xue, & Philip H. S. Torr. (2022). Dynamic Graph Message Passing Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. 45(5). 1–17. 10 indexed citations

13.

Ryoo, Michael S., AJ Piergiovanni, Anurag Arnab, Mostafa Dehghani, & Anelia Angelova. (2021). TokenLearner: Adaptive Space-Time Tokenization for Videos. Neural Information Processing Systems. 34. 52 indexed citations

14.

Nagrani, Arsha, Shan Yang, Anurag Arnab, et al.. (2021). Attention Bottlenecks for Multimodal Fusion. Neural Information Processing Systems. 34.

15.

Zhang, Li, Dan Xu, Anurag Arnab, & Philip H. S. Torr. (2020). Dynamic Graph Message Passing Networks. Rare & Special e-Zone (The Hong Kong University of Science and Technology). 3723–3732. 85 indexed citations

16.

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

17.

Arnab, Anurag, Shuai Zheng, Sadeep Jayasumana, et al.. (2018). Conditional Random Fields Meet Deep Neural Networks for Semantic Segmentation: Combining Probabilistic Graphical Models with Deep Learning for Structured Prediction. IEEE Signal Processing Magazine. 35(1). 37–52. 81 indexed citations

18.

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

19.

Larsson, Måns, Fredrik Kahl, Shuai Zheng, et al.. (2017). Learning Arbitrary Potentials in CRFs with Gradient Descent.. arXiv (Cornell University). 2 indexed citations

20.

Arnab, Anurag & Philip H. S. Torr. (2017). Pixelwise Instance Segmentation with a Dynamically Instantiated Network. 879–888. 137 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