I am an Assistant Professor at Leiden University in the Leiden Institute for Advanced Computer Science (LIACS). Previously I was a postdoctoral researcher at the University of Amsterdam, working with with Prof. Cees Snoek. I completed my PhD at the University of Bristol, advised by Prof. Dima Damen and Prof. Walterio Mayol-Cuevas. My area of interest is Video Understanding, with my PhD thesis (which you can find here) focussing on Skill Determination. I am particularly interested in fine-grained and detailed video understanding with weak, noisy or other forms of incomplete supervision.

Contact: h.r.doughty *at* liacs.leidenuniv.nl

News & Activities

October: Welcome to Luc Sträter who started his PhD at LIACS
September: Two papers accepted to ACCV as orals. Details coming soon.
September: I'll be serving as area chair for CVPR 2025
July 2024: I gave a talk at the African Summer School on Computer Vision
July 2024: Our paper SelEx: Self-Expertise in Fine-Grained Generalized Category Discovery is accepted to ECCV 2024, more details coming soon.
May 2024: I have a PhD vacancy on 'Detailed Video Understanding'
April 2024: I gave a talk in the Visipedia workshop at the University of Copenhagen
April 2024: Welcome to Kaiting Liu who started her PhD at LIACS
March 2024: I gave a talk at the University of Bath
February 2024: Our paper Low-Resource Vision Challenges for Foundational Models is accepted to CVPR 2024
February 2024: I'm co-organizing the CVPR 2024 workshop on What is Next in Video Understanding?
January 2024: I am organizing NCCV 2024
December 2023: Congratulations to Dr. Fida Mohammad Thoker who successfully defended his thesis titled Video-Efficient Foundation Models
Novemeber 2023: Happy to be a top reviewer for NeurIPS 2023.
October 2023: I'm hiring for two PhD positions in 'Detailed Video Understanding'
September 2023: Two papers accepted to NeurIPS
September 2023: I joined Leiden University as an Assistant Professor
August 2023: I'm thrilled to receive a Veni grant for my project "From What to How: Perceiving Subtle Details in Videos"
July 2023: Our paper "Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization" was accepted to ICCV, pre-print available here
July 2023: In September I'll join Leiden University as an Assistant Professor, look out for PhD openings!
June 2023: I gave a talk at the CVPR 2023 workshop on Learning with Limited Labelled Data for Image and Video Understanding
April 2023: I became an associate editor of CVIU
February 2023: I gave a talk at the Rising Stars in AI Symposium 2023 in KAUST
December 2022: Excited to be a Workshop Chair for BMVC 2023
December 2022: I'm honored to serve as an Area Chair for ICCV 2023
December 2022: I gave a guest lecture at the University of Catania
October 2022: Happy to be an outstanding reviewer for ECCV 2022
September 2022: I became an ELLIS member
September 2022: I gave a talk at the 2022 Video Understanding Symposium
July 2022: 'How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?' is accepted to ECCV
June 2022: I was a panelist at Women in Computer Vision CVPR 2022
May 2022: I gave a talk at the Computer Vision by Learning Summer School
March 2022: Our papers on Pseudo Adverbs and Audio-Adaptive Action Recognition are accepted to CVPR.
September 2021: Our paper Rescaling Egocentric Vision is accepted for publication in IJCV
September 2021: I'm an Outstanding Reviewer for ICCV 2021
August 2021: Our paper Skeleton-Contrastive 3D Action Representation Learning was accepted at ACM Multimedia 2021
July 2021: I'm co-organizing the NeurIPS'21 Workshop on Pre-registration in ML
May 2021: Happy to be an outstanding reviewer for CVPR 2021
April 2021: I'm co-organizing the Workshop on Structured Representations for Video Understanding at ICCV.
March 2021: Our paper On Semantic Similarity in Video Retrieval got accepted at CVPR 2021.
February 2021: I gave a talk at the University of Toronto's AI in Robotics Seminar Series.
October 2020: Successfully defended my PhD thesis "Skill Determination from Long Videos". Thank you to my examiners Josef Sivic and Bill Freeman.
August 2020: Proud to be an Outstanding Reviewer for ECCV 2020
July 2020: EPIC-Kitchens-100 released. This is an extension of the original EPIC-Kitchens, now up 100 hours of video and 90,000 action segments.
June 2020: I presented our CVPR paper Action Modifers: Learning from Adverbs in Instructional Videos at the Video Pentathlon workshop.
April 2020: The journal paper EPIC-KITCHENS Dataset: Collection Challenges and Baselines has been accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence
Feb 2020: Action Modifers: Learning from Adverbs in Instructional Videos is accepted in CVPR 2020.
Jan 2020: I'm co-organizing the Women in Computer Vision and Egocentric Perception, Interaction and Computing workshops at CVPR 2020.
Dec 2019: Our new paper on 'Action Modifiers' is available on arXiv
June 2019: We're presenting our paper on rank-aware temporal attention for skill determination at CVPR 2019.

Publications

	LocoMotion: Learning Motion-Focused Video-Language Representations Hazel Doughty, Fida Mohammad Thoker, Cees Snoek Asian Conference on Computer Vision (ACCV), 2024. (Oral) [Webpage] [ArXiv]
	Beyond Coarse-Grained Matching in Video-Text Retrieval Aozhu Chen, Hazel Doughty, Xirong Li, Cees Snoek Asian Conference on Computer Vision (ACCV), 2024. (Oral) [ArXiv]
	SelEx: Self-Expertise In Fine-Grained Generalized Category Discovery Sarah Rastegar, Mohammadreza Salehi, Yuki Asano, Hazel Doughty, Cees Snoek European Conference on Computer Vision (ECCV), 2024. [arXiv] [Code]
	Low-Resource Vision Challenges for Foundation Models Yunhua Zhang, Hazel Doughty, Cees Snoek Conference on Computer Vision and Pattern Recognition (CVPR), 2024. [Webpage] [arXiv]
	Learning Unseen Modality Interaction Yunhua Zhang, Hazel Doughty, Cees Snoek Advances in Neural Information Processing Systems (NeurIPS), 2023. [Webpage] [arXiv] [Code]
	Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery Sarah Rastegar, Hazel Doughty, Cees Snoek Advances in Neural Information Processing Systems (NeurIPS), 2023. [arXiv] [Code]
	Tubelet-Contrastive Self-Supervision for Video-Efficient Generalization Fida Mohammad Thoker, Hazel Doughty, Cees Snoek International Conference on Computer Vision (ICCV), 2023. [Webpage] [arXiv] [Code]
	Day2Dark: Pseudo-Supervised Activity Recognition beyond Silent Daylight Yunhua Zhang, Hazel Doughty, Cees Snoek ArXiv, 2022. [arXiv]
	How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning? Fida Mohammad Thoker, Hazel Doughty, Piyush Bagad, Cees Snoek European Conference on Computer Vision (ECCV), 2022. [Webpage] [arXiv] [Code]
	How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs Hazel Doughty and Cees Snoek Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Webpage] [arXiv] [Dataset and Code]
	Audio-Adaptive Activity Recognition Across Video Domains Yunhua Zhang, Hazel Doughty, Ling Shao, Cees Snoek Conference on Computer Vision and Pattern Recognition (CVPR), 2022. [Webpage] [arXiv] [Code]
	Skeleton-Contrastive 3D Action Representation Learning Fida Mohammad Thoker, Hazel Doughty, Cees Snoek ACM International Conference on Multimedia (ACMMM), 2021 [arXiv] [Code]
	On Semantic Similarity in Video Retrieval Michael Wray, Hazel Doughty and Dima Damen Conference on Computer Vision and Pattern Recognition (CVPR), 2021. [Webpage] [arXiv]
	Rescaling Egocentric Vision: EPIC-KITCHENS-100 Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Antonino Furnari, Evangelos Kazakos, Jian Ma, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray International Journal of Computer Vision (IJCV), 2021. [Webpage] [arXiv] [Dataset and Code]
	Action Modifiers: Learning from Adverbs in Instructional Videos Hazel Doughty, Ivan Laptev, Walterio Mayol-Cuevas and Dima Damen Conference on Computer Vision and Pattern Recognition (CVPR), 2020. [Webpage] [arXiv] [Dataset and Code]
	The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2020. [arXiv Preprint]
	The Pros and Cons: Rank-Aware Temporal Attention for Skill Determination in Long Videos Hazel Doughty, Walterio Mayol-Cuevas and Dima Damen Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [Webpage] [arXiv] [Dataset & Code]
	Scaling Egocentric Vision: The EPIC-Kitchens Dataset Dima Damen, Hazel Doughty, Giovanni Maria Farinella, Sanja Fidler, Antonino Furnari, Evangelos Kazakos, Davide Moltisanti, Jonathan Munro, Toby Perrett, Will Price, Michael Wray European Conference on Computer Vision (ECCV), 2018. (Oral) [arXiv] [Webpage & Dataset]
	Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination Hazel Doughty, Dima Damen and Walterio Mayol-Cuevas Conference on Computer Vision and Pattern Recognition (CVPR), 2018. (Spotlight) [arXiv] [Bibtex] [Dataset]

People

2024-present - Luc Sträter
2024-present - Kaiting Liu
2024-present - Omar Emara (PhD with Dima Damen at University of Bristol)
2023-2024 Aozhu Chen (Visting PhD student from Renmin University of China)
2021-present - Yunhua Zhang (PhD with Cees Snoek)
2021-2023 - Fida Mohammad Thoker (PhD student) now postdoc at KAUST
2020-present - Sarah Rastegar (PhD with Cees Snoek)
2021-2022 - Piyush Bagad (MS intern) now PhD student at University of Oxford

Academic Service

Organizer: What is Next in Video Understanding? CVPR 2024 Workshop, Workshop Chair for BMVC 2023, Netherlands Conference on Computer Vision 2022 and 2024, NeurIPS'21 Workshop on Pre-registration in ML, ICCV'21 Workshop on Structured Representations for Video Understanding, WiCV@CVPR2020, EPIC@CVPR2020, EPIC@ECCV2020
Area Chair: CVPR 2025, NeurIPS 2024, ECCV 2024, ACCV 2024, AAAI 2024, ICCV 2023, WACV 2023
Associate Editor: CVIU since 2023
Reviewer: CVPR since 2020, ICCV since 2019, ECCV since 2020, TPAMI 2020-2022, IJCV 2021-2022, NeurIPS 2022, ACCV 2020, WACV 2020-2021, AAAI 2020
Outstading Reviewer: CVPR 2024, NeurIPS 2023, CVPR 2023, ECCV 2022, ICCV 2021, CVPR 2021, ECCV 2020, ACCV 2020

Teaching

Computer Vision, 2024 (3rd Year Bachelors), Leiden University
Seminar in Advances of Deep Learning, 2024 (Masters), Leiden University.
Leren en Beslissen (Learning and Decision Making), 2022 (BSc AI, Y2), University of Amsterdam.