Makarand Tapaswi

2.4k total citations · 1 hit paper
39 papers, 1.2k citations indexed

About

Makarand Tapaswi is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Signal Processing. According to data from OpenAlex, Makarand Tapaswi has authored 39 papers receiving a total of 1.2k indexed citations (citations by other indexed papers that have themselves been cited), including 34 papers in Computer Vision and Pattern Recognition, 15 papers in Artificial Intelligence and 11 papers in Signal Processing. Recurrent topics in Makarand Tapaswi's work include Video Analysis and Summarization (12 papers), Multimodal Machine Learning Applications (12 papers) and Human Pose and Action Recognition (11 papers). Makarand Tapaswi is often cited by papers focused on Video Analysis and Summarization (12 papers), Multimodal Machine Learning Applications (12 papers) and Human Pose and Action Recognition (11 papers). Makarand Tapaswi collaborates with scholars based in Germany, India and France. Makarand Tapaswi's co-authors include Rainer Stiefelhagen, Ivan Laptev, Martin Bäuml, Josef Šivic, Jean-Baptiste Alayrac, Antoine Miech, Dimitri Zhukov, Shizhe Chen, Cordelia Schmid and Ziad Al-Halah and has published in prestigious journals such as Computer Vision and Image Understanding, IEEE Transactions on Biometrics Behavior and Identity Science and International Journal of Multimedia Information Retrieval.

In The Last Decade

Makarand Tapaswi

37 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.

HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million\n Narrated Video Clips

2019 521 citations Antoine Miech, Dimitri Zhukov et al. arXiv (Cornell University) profile →

Peers — A (Enhanced Table)

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

Name	h						Papers	Cites
Makarand Tapaswi Germany	14	1.1k	526	133	28	28	39	1.2k
Anna Rohrbach United States	16	1.0k 0.9×	616 1.2×	67 0.5×	24 0.9×	17 0.6×	33	1.2k
Mannat Singh United States	6	647 0.6×	464 0.9×	71 0.5×	38 1.4×	19 0.7×	9	938
Srirangaraj Setlur United States	17	732 0.7×	205 0.4×	119 0.9×	11 0.4×	64 2.3×	81	948
Hao Tan United States	12	1.4k 1.3×	1.3k 2.4×	40 0.3×	28 1.0×	14 0.5×	28	1.7k
Fernando Díaz-de-María Spain	15	430 0.4×	319 0.6×	449 3.4×	17 0.6×	13 0.5×	92	810
Saurabh Singh India	9	500 0.5×	246 0.5×	165 1.2×	41 1.5×	23 0.8×	33	740
Giridharan Iyengar United States	18	573 0.5×	204 0.4×	334 2.5×	8 0.3×	18 0.6×	45	786
Shizhe Chen China	19	1.1k 1.0×	631 1.2×	249 1.9×	26 0.9×	49 1.8×	66	1.6k
Xitong Yang United States	12	615 0.6×	285 0.5×	34 0.3×	12 0.4×	20 0.7×	29	810

Countries citing papers authored by Makarand Tapaswi

Since Specialization

Citations

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

Fields of papers citing papers by Makarand Tapaswi

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Makarand Tapaswi

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

Tapaswi, Makarand, et al.. (2025). The Sound of Water: Inferring Physical Properties from Pouring Liquids. 1–5. 1 indexed citations

2.

Singh, Aditya, et al.. (2024). “Previously on…” from Recaps to Story Summarization. 13635–13646.

3.

Tapaswi, Makarand, et al.. (2024). MICap: A Unified Model for Identity-Aware Movie Descriptions. 14011–14021. 1 indexed citations

4.

Sundar, Krishna M., Shubham Toshniwal, Makarand Tapaswi, & Vineet Gandhi. (2024). Major Entity Identification: A Generalizable Alternative to Coreference Resolution. 11679–11695.

5.

Tapaswi, Makarand, et al.. (2023). How You Feelin’? Learning Emotions and Mental States in Movie Scenes. 195. 2517–2528. 5 indexed citations

6.

Gupta, Anchit, et al.. (2023). Unsupervised Audio-Visual Lecture Segmentation. 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 5221–5230. 2 indexed citations

7.

Tapaswi, Makarand, et al.. (2023). Test of Time: Instilling Video-Language Models with a Sense of Time. 2503–2516. 7 indexed citations

8.

Tapaswi, Makarand, et al.. (2021). Airbert: In-domain Pretraining for Vision-and-Language Navigation. 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 1614–1623. 82 indexed citations

9.

Miech, Antoine, Dimitri Zhukov, Jean-Baptiste Alayrac, et al.. (2019). HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million\n Narrated Video Clips. arXiv (Cornell University). 521 indexed citations breakdown →

10.

Tapaswi, Makarand, et al.. (2018). Now You Shake Me: Towards Automatic 4D Cinema. 7425–7434. 13 indexed citations

11.

Al-Halah, Ziad, Makarand Tapaswi, & Rainer Stiefelhagen. (2016). Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning. 5975–5984. 51 indexed citations

12.

Tapaswi, Makarand, Martin Bäuml, & Rainer Stiefelhagen. (2015). Book2Movie: Aligning video scenes with book chapters. 1827–1835. 49 indexed citations

13.

Tapaswi, Makarand, et al.. (2015). KIT at MediaEval 2015 - Evaluating Visual Cues for Affective Impact of Movies Task. MediaEval. 20 indexed citations

14.

Tapaswi, Makarand, Martin Bäuml, & Rainer Stiefelhagen. (2015). Improved weak labels using contextual cues for person identification in videos. 1–8. 11 indexed citations

15.

Tapaswi, Makarand, et al.. (2014). Cleaning up after a face tracker: False positive removal. Istanbul Technical University Academic Open Archive (Istanbul Technical University). 253–257. 4 indexed citations

16.

Tapaswi, Makarand, Omkar Parkhi, Esa Rahtu, et al.. (2014). Total Cluster. 1–8. 19 indexed citations

17.

Tapaswi, Makarand, Martin Bäuml, & Rainer Stiefelhagen. (2014). StoryGraphs: Visualizing Character Interactions as a Timeline. 827–834. 41 indexed citations

18.

Bredin, Hervé, Guillaume Fortier, Makarand Tapaswi, et al.. (2013). QCompere @ REPERE 2013. SPIRE - Sciences Po Institutional REpository. 49–54. 3 indexed citations

19.

Tapaswi, Makarand, et al.. (2012). KIT at MediaEval 2012 - Content - based Genre Classification with Visual Cues.. MediaEval. 2 indexed citations

20.

Das, Amitava & Makarand Tapaswi. (2010). Direct modeling of spoken passwords for Text-Dependent Speaker Recognition by compressed time-feature representations. 4510–4513. 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