Josef Šivic

33.6k citations
122 papers · 19.0k · 19 hit papers · h-index 57

Impact in

    • Advanced Image and Video Retrieval Techniques
    • Image Retrieval and Classification Techniques
    • Multimodal Machine Learning Applications
    • Human Pose and Action Recognition
    • Video Surveillance and Tracking Methods
    • Advanced Neural Network Applications
    • Advanced Vision and Imaging

Papers in

    • Advanced Image and Video Retrieval Techniques 55
    • Human Pose and Action Recognition 29
    • Multimodal Machine Learning Applications 29
    • Video Analysis and Summarization 25
    • Advanced Vision and Imaging 22
    • Video Surveillance and Tracking Methods 19
    • Image Retrieval and Classification Techniques 18
    • Robotics and Sensor-Based Localization 28

Josef Šivic

118 papers receiving 18.3k citations

Josef Šivic's Hit Papers

Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning 2023 · 127 citations
1270+6+12Years since publication50010001.5k2.0k

Peers

Josef Šivic
Comparison fields: 5 of 186
  • Computer Vision and Pattern Recognition 16.3k
  • Media Technology 1.8k
  • Aerospace Engineering 4.5k
  • Artificial Intelligence 4.0k
  • Geology 573
Replace Svetlana Lazebnik with:
Svetlana Lazebnik United States
Krystian Mikolajczyk United Kingdom
Haibin Ling United States
Pedro F. Felzenszwalb United States
Fahad Shahbaz Khan United Arab Emirates
Andreas Ess Switzerland
C. Schmid France
Stephen J. Maybank United Kingdom
Anton van den Hengel Australia
Vittorio Ferrari Switzerland
Josef Šivic relative to Svetlana Lazebnik United States Svetlana Lazebnik's profile →
Citations per field
00.5×3.1×
Svetlana Lazebnik · 1×
Citations per year

Countries citing papers authored by Josef Šivic

Since Specialization
Citations

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

Fields of papers citing papers by Josef Šivic

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

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

Co-authors

The 25 scholars most cited alongside Josef Šivic, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with Josef Šivic Line = papers co-authored together Josef Šivic links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown

Showing the 20 most-cited of 122 papers — load more, or switch the sort, to bring in the rest.

#Work
1
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Hit paper breakdown →
20142278
2
Object retrieval with large vocabularies and fast spatial matching
Hit paper breakdown →
20072200
3
NetVLAD: CNN architecture for weakly supervised place recognition
Hit paper breakdown →
20151275
4
Lost in quantization: Improving particular object retrieval in large scale image databases
Hit paper breakdown →
20081077
5
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Hit paper breakdown →
2019790
6
Discovering objects and their location in images
Hit paper breakdown →
2005755
7
Total Recall: Automatic Query Expansion with a Generative Feature Model for Object Retrieval
Hit paper breakdown →
2007671
8
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million\n Narrated Video Clips
Hit paper breakdown →
2019610
9
What makes Paris look like Paris?
Hit paper breakdown →
2012487
10
Using Multiple Segmentations to Discover Objects and their Extent in Image Collections
Hit paper breakdown →
2006487
11
SIFT Flow: Dense Correspondence across Different Scenes
Hit paper breakdown →
2008445
12
Hello! My name is... Buffy'' -- Automatic Naming of Characters in TV Video
Hit paper breakdown →
2006438
13
End-to-End Learning of Visual Representations From Uncurated Instructional Videos
Hit paper breakdown →
2020403
14
Non-uniform Deblurring for Shaken Images
Hit paper breakdown →
2011387
15
Efficient Visual Search of Videos Cast as Text Retrieval
Hit paper breakdown →
2009371
16
Discovering object categories in image collections
2005342
17
CosyPose: Consistent multi-view multi-object 6D pose estimation
Hit paper breakdown →
2020290
18
Seeing 3D Chairs: Exemplar Part-Based 2D-3D Alignment Using a Large Dataset of CAD Models
Hit paper breakdown →
2014287
19 2011237
20 2013223

About Josef Šivic

Josef Šivic is a scholar working on Computer Vision and Pattern Recognition, Aerospace Engineering, Artificial Intelligence, Control and Systems Engineering and Media Technology, having authored 122 papers that have together received 19.0k indexed citations. Recurring topics across this work include Advanced Image and Video Retrieval Techniques (55 papers), Human Pose and Action Recognition (29 papers), Multimodal Machine Learning Applications (29 papers), Robotics and Sensor-Based Localization (28 papers), Video Analysis and Summarization (25 papers), Advanced Vision and Imaging (22 papers), Video Surveillance and Tracking Methods (19 papers) and Image Retrieval and Classification Techniques (18 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (16.3k citations), Media Technology (1.8k citations), Aerospace Engineering (4.5k citations), Artificial Intelligence (4.0k citations) and Geology (573 citations). Josef Šivic has collaborated with scholars based in France, Czechia and United Kingdom. Frequent co-authors include Andrew Zisserman, Ivan Laptev, James Philbin, Michael Isard, Ondřej Chum, Tomáš Pajdla, Maxime Oquab, Léon Bottou, Alexei A. Efros and Akihiko Torii. Their work appears in journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, International Journal of Computer Vision, IEEE Robotics and Automation Letters, ACM Transactions on Graphics and Proceedings of the IEEE.

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