Thomas Mensink

7.7k total citations · 2 hit papers
49 papers, 2.8k citations indexed

About

Thomas Mensink is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Media Technology. According to data from OpenAlex, Thomas Mensink has authored 49 papers receiving a total of 2.8k indexed citations (citations by other indexed papers that have themselves been cited), including 47 papers in Computer Vision and Pattern Recognition, 18 papers in Artificial Intelligence and 3 papers in Media Technology. Recurrent topics in Thomas Mensink's work include Advanced Image and Video Retrieval Techniques (24 papers), Multimodal Machine Learning Applications (17 papers) and Image Retrieval and Classification Techniques (16 papers). Thomas Mensink is often cited by papers focused on Advanced Image and Video Retrieval Techniques (24 papers), Multimodal Machine Learning Applications (17 papers) and Image Retrieval and Classification Techniques (16 papers). Thomas Mensink collaborates with scholars based in Netherlands, France and United States. Thomas Mensink's co-authors include Jakob Verbeek, Florent Perronnin, Jorge Sánchez, Cees G. M. Snoek, Matthieu Guillaumin, Cordelia Schmid, Amirhossein Habibian, G. Csurka, Efstratios Gavves and Jan van Gemert and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Image Processing and International Journal of Computer Vision.

In The Last Decade

Thomas Mensink

47 papers receiving 2.7k 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.

Image Classification with the Fisher Vector: Theory and Practice

2013 992 citations Florent Perronnin, Thomas Mensink et al. profile →
TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation

2009 487 citations Matthieu Guillaumin, Thomas Mensink et al. HAL (Le Centre pour la Communication Scientifique Directe) profile →

Peers

Countries citing papers authored by Thomas Mensink

Since Specialization

Citations

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

Fields of papers citing papers by Thomas Mensink

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authorship network of co-authors of Thomas Mensink

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

#	Work	Indexed citations
1	Simpler Diffusion: 1.5 FID on ImageNet512 with pixel-space diffusion 2025 ·Emiel Hoogeboom, Thomas Mensink, Jonathan Heek, (unknown), (unknown), Tim Salimans	0
2	Neural Feature Matching in Implicit 3D Representations 2021 ·UvA-DARE (University of Amsterdam) ·Yunlu Chen, Basura Fernando, Hakan Bilen, Thomas Mensink, Efstratios Gavves	2
3	3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentation 2019 ·Yunlu Chen, Thomas Mensink, Efstratios Gavves	13
4	IterGANs: Iterative GANs to learn and control 3D object transformation 2019 ·Computer Vision and Image Understanding ·(unknown), Thomas Mensink	3
5	DeepNCM: Deep Nearest Class Mean Classifiers 2018 ·International Conference on Learning Representations ·(unknown), Barbara Caputo, Thomas Mensink	16
6	Unsupervised Generation of Optical Flow Datasets from Videos in the Wild 2018 ·arXiv (Cornell University) ·(unknown), (unknown), Thomas Mensink, (unknown), Sezer Karaoğlu, Theo Gevers	1
7	Iterative GANs for Rotating Visual Objects. 2018 ·International Conference on Learning Representations ·(unknown), Thomas Mensink	2
8	Three for one and one for three: Flow, Segmentation, and Surface Normals 2018 ·arXiv (Cornell University) ·(unknown), (unknown), Thomas Mensink, Theo Gevers	2
9	Event Fisher Vectors: Robust Encoding Visual Diversity of Visual Streams 2015 ·UvA-DARE (University of Amsterdam) ·Markus Nagel, Thomas Mensink, Cees G. M. Snoek	19
10	Objects2action: Classifying and Localizing Actions without Any Video Example 2015 ·UvA-DARE (University of Amsterdam) ·Mihir Jain, Jan van Gemert, Thomas Mensink, Cees G. M. Snoek	69
11	Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks 2015 ·UvA-DARE (University of Amsterdam) ·Efstratios Gavves, Thomas Mensink, Tatiana Tommasi, Cees G. M. Snoek, Tinne Tuytelaars	34
12	COSTA: Co-Occurrence Statistics for Zero-Shot Classification 2014 ·UvA-DARE (University of Amsterdam) ·Thomas Mensink, Efstratios Gavves, Cees G. M. Snoek	140
13	MediaMill at TRECVID 2014: Searching Concepts, Objects, Instances and Events in Video 2014 ·UvA-DARE (University of Amsterdam) ·Cees G. M. Snoek, Koen E. A. van de Sande, Daniel Fontijne, (unknown), Jan van Gemert, Amirhossein Habibian, Thomas Mensink, Pascal Mettes, Ran Tao, D.C. Koelma, A.W.M. Smeulders	23
14	Robustifying Descriptor Instability Using Fisher Vectors 2014 ·IEEE Transactions on Image Processing ·(unknown), Jan van Gemert, Thomas Mensink, Theo Gevers	2
15	Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost 2013 ·IEEE Transactions on Pattern Analysis and Machine Intelligence ·Thomas Mensink, Jakob Verbeek, Florent Perronnin, G. Csurka	237
16	Tree-Structured CRF Models for Interactive Image Labeling 2013 ·IEEE Transactions on Pattern Analysis and Machine Intelligence ·Thomas Mensink, Jakob Verbeek, Gabriela Csurka	22
17	INRIA-LEAR's Participation in ImageCLEF 2009. 2009 ·HAL (Le Centre pour la Communication Scientifique Directe) ·Matthijs Douze, Matthieu Guillaumin, Thomas Mensink, Cordelia Schmid, Jakob Verbeek	3
18	TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation breakdown → 2009 ·HAL (Le Centre pour la Communication Scientifique Directe) ·Matthieu Guillaumin, Thomas Mensink, Jakob Verbeek, Cordelia Schmid	487
19	Improving people search using query expansions: How friends help to find people 2008 ·Thomas Mensink, Jakob Verbeek	9
20	Multi-Observations Newscast EM for Distributed Multi-Camera Tracking 2007 ·Thomas Mensink	2

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