Gedas Bertasius

4.0k total citations · 1 hit paper
35 papers, 1.0k citations indexed

About

Gedas Bertasius is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Signal Processing. According to data from OpenAlex, Gedas Bertasius has authored 35 papers receiving a total of 1.0k indexed citations (citations by other indexed papers that have themselves been cited), including 30 papers in Computer Vision and Pattern Recognition, 15 papers in Artificial Intelligence and 3 papers in Signal Processing. Recurrent topics in Gedas Bertasius's work include Human Pose and Action Recognition (16 papers), Multimodal Machine Learning Applications (14 papers) and Video Analysis and Summarization (11 papers). Gedas Bertasius is often cited by papers focused on Human Pose and Action Recognition (16 papers), Multimodal Machine Learning Applications (14 papers) and Video Analysis and Summarization (11 papers). Gedas Bertasius collaborates with scholars based in United States, Israel and United Kingdom. Gedas Bertasius's co-authors include Lorenzo Torresani, Jianbo Shi, Jianbo Shi, Stella X. Yu, Hyun Soo Park, Mohit Bansal, Marc Niethammer, Jue Wang, Shih‐Fu Chang and Xudong Lin and has published in prestigious journals such as Information Retrieval, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) and arXiv (Cornell University).

In The Last Decade

Gedas Bertasius

31 papers receiving 999 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.

DeepEdge: A multi-scale bifurcated deep network for top-down contour detection

2015 341 citations Gedas Bertasius, Jianbo Shi et al. profile →

Peers — A (Enhanced Table)

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

Name	h						Papers	Cites
Gedas Bertasius United States	14	823	261	110	58	50	35	1.0k
Zhijiang Zhang China	9	510 0.6×	238 0.9×	86 0.8×	87 1.5×	38 0.8×	24	721
Chenxi Liu United States	6	693 0.8×	412 1.6×	92 0.8×	34 0.6×	25 0.5×	12	916
Zhongying Deng China	6	506 0.6×	218 0.8×	83 0.8×	27 0.5×	43 0.9×	15	632
Cheng-Ze Lu China	4	477 0.6×	157 0.6×	158 1.4×	46 0.8×	37 0.7×	8	758
Pengfei Xiong China	11	756 0.9×	175 0.7×	106 1.0×	52 0.9×	22 0.4×	21	912
Xuansong Xie China	17	790 1.0×	141 0.5×	87 0.8×	28 0.5×	42 0.8×	50	957
Guangliang Cheng China	17	731 0.9×	341 1.3×	159 1.4×	47 0.8×	22 0.4×	33	988
Ambrish Tyagi United States	9	954 1.2×	413 1.6×	160 1.5×	52 0.9×	45 0.9×	13	1.2k
Satoshi Iizuka Japan	9	1.4k 1.7×	122 0.5×	132 1.2×	31 0.5×	53 1.1×	26	1.6k

Countries citing papers authored by Gedas Bertasius

Since Specialization

Citations

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

Fields of papers citing papers by Gedas Bertasius

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Gedas Bertasius

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

Wang, Ziyang, et al.. (2025). Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning. 28114–28128.

2.

Zhu, Xinghao, et al.. (2025). ReBot: Scaling Robot Learning with Real-to-Sim-to-Real Robotic Video Synthesis. 11351–11358.

3.

Islam, Md. Mohaiminul, et al.. (2025). ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos. 19012–19022. 1 indexed citations

4.

Islam, Md. Mohaiminul, Tushar Nagarajan, Huiyu Wang, Gedas Bertasius, & Lorenzo Torresani. (2025). BIMBA: Selective-Scan Compression for Long-Range Video Question Answering. 29096–29107.

5.

Zhang, Ce, et al.. (2025). Basket: A Large-Scale Video Dataset for Fine-Grained Skill Estimation. 28952–28962. 1 indexed citations

6.

Wang, Ziyang, et al.. (2025). VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos. 3272–3282. 5 indexed citations

7.

Cheng, Feng, et al.. (2025). Dam: Dynamic Adapter Merging for Continual Video QA Learning. 6805–6817. 1 indexed citations

8.

Bertasius, Gedas, et al.. (2024). ARCADE: Scalable Demonstration Collection and Generation via Augmented Reality for Imitation Learning. 2855–2861. 2 indexed citations

9.

Cheng, Feng, et al.. (2024). LoCoNet: Long-Short Context Network for Active Speaker Detection. 18462–18472. 8 indexed citations

10.

Yang, Xitong, et al.. (2024). Video ReCap: Recursive Captioning of Hour-Long Videos. 18198–18208. 10 indexed citations

11.

Wang, Xiyao, Jaehong Yoon, Fuxiao Liu, et al.. (2024). Mementos: A Comprehensive Benchmark for Multimodal Large Language Model Reasoning over Image Sequences. 416–442. 6 indexed citations

12.

Zhang, C., et al.. (2024). A Simple LLM Framework for Long-Range Video Question-Answering. 21715–21737. 9 indexed citations

13.

Bertasius, Gedas, et al.. (2023). MuMUR: Multilingual Multimodal Universal Retrieval. Information Retrieval. 26(1-2). 1 indexed citations

14.

Islam, Md. Mohaiminul, et al.. (2023). Efficient Movie Scene Detection using State-Space Transformers. 18749–18758. 26 indexed citations

15.

Lin, Xudong, Fabio Petroni, Gedas Bertasius, et al.. (2022). Learning To Recognize Procedural Activities with Distant Supervision. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13843–13853. 24 indexed citations

16.

Wang, Jue, Gedas Bertasius, Du Tran, & Lorenzo Torresani. (2022). Long-Short Temporal Contrastive Learning of Video Transformers. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 13990–14000. 27 indexed citations

17.

Bertasius, Gedas, Heng Wang, & Lorenzo Torresani. (2021). Is Space-Time Attention All You Need for Video Understanding?. International Conference on Machine Learning. 813–824. 8 indexed citations

18.

Shi, Jianbo & Gedas Bertasius. (2017). Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention. 2355–2363. 3 indexed citations

19.

Bertasius, Gedas, Stella X. Yu, & Jianbo Shi. (2016). Exploiting Visual-Spatial First-Person Co-Occurrence for Action-Object Detection without Labels.. arXiv (Cornell University). 2 indexed citations

20.

Bertasius, Gedas, Stella X. Yu, Hyun Soo Park, & Jianbo Shi. (2016). Am I a Baller? Basketball Skill Assessment using First-Person Cameras.. arXiv (Cornell University). 1 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