Antoine Miech

Google (United States) — United States

Computer Science · Physical Sciences

15h-index4.1kcitations33works96.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Multimodal Machine Learning Applications(25), Human Pose and Action Recognition(20), Domain Adaptation and Few-Shot Learning(13), Video Analysis and Summarization(10), Advanced Image and Video Retrieval Techniques(6)

Publications31 total

A Simple Recipe for Contrastively Pre-Training Video-First Encoders Beyond 16 Frames
2024· 13 cited
Multi-Task Learning of Object States and State-Modifying Actions From Web Videos
IEEE Transactions on Pattern Analysis and Machine Intelligence·2024· 7 cited
A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames
arXiv (Cornell University)·2023· 1 citedOpen Access
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
2023· 192 cited
Perception Test: A Diagnostic Benchmark for Multimodal Video Models
arXiv (Cornell University)·2023· 12 citedOpen Access
Making the Most of What You Have: Adapting Pre-trained Visual Language Models in the Low-data Regime
arXiv (Cornell University)·2023Open Access
Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning
arXiv (Cornell University)·2023· 15 citedOpen Access
Zorro: the masked multimodal transformer
arXiv (Cornell University)·2023· 11 citedOpen Access
Multi-Task Learning of Object State Changes from Uncurated Videos
arXiv (Cornell University)·2022· 4 citedOpen Access
Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
arXiv (Cornell University)·2022· 64 citedOpen Access
TubeDETR: Spatio-Temporal Video Grounding with Transformers
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 87 citedOpen Access
Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)·2022· 17 cited
Learning to Answer Visual Questions from Web Videos
arXiv (Cornell University)·2022· 1 citedOpen Access
Learning to Answer Visual Questions From Web Videos
IEEE Transactions on Pattern Analysis and Machine Intelligence·2022· 25 citedOpen Access
Flamingo: a Visual Language Model for Few-Shot Learning
arXiv (Cornell University)·2022· 1.2k citedOpen Access
Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos
arXiv (Cornell University)·2022· 2 citedOpen Access
Just Ask: Learning to Answer Questions from Millions of Narrated Videos
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 14 citedOpen Access
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
2021· 4 citedOpen Access
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with\n Transformers
arXiv (Cornell University)·2021· 129 citedOpen Access
Large-scale learning from video and natural language
theses.fr (ABES)·2020Open Access
page 1 of 2Next →

Frequent Co-authors

Ivan Laptev(24), Josef Šivic(23), Jean-Baptiste Alayrac(14), Andrew Zisserman(10), Antoine Yang(7), Cordelia Schmid(7), Lucas Smaira(4), Tomáš Souček(4), Pauline Luc(3), Arsha Nagrani(3), Skanda Koppula(3), Viorica Pătrăucean(3), Jiajun Shen(3), Paul Hongsuck Seo(2), Jordi Pont-Tuset(2), Pinelopi Papalampidi(2), Shreya Pathak(2), Justin Chiu(2), Joe Heyward(2), Aida Nematzdeh(2)