Dima Damen

Professor of Computer Vision, School of Computer Science,
Lead of Machine Learning and Computer Vision Group, University of Bristol
EPSRC Early Career Fellow (2020-2025)

Senior Research Scientist, Google DeepMind

News

Oct 2024: Our Survey paper "An Outlook into the Future of Egocentric Vision" appeared in Vol 132 at IJCV in its final format

Sep 2024: Our ECCV 2024 paper AMEGO is now on ArXiv. Check Website for paper, code and benchmark

Sep 2024: Online Open Access of our PAMI 2024 paper is now Online

May 2024: Online Open Access of our IJCV 2024 paper is now Online

Mar 2024: Two PhD positions opened in my group. Apply by 30 April 2024.

Feb 2024: 1st EgoVis (Joint) Workshop will be held @CVPR2024 - see call for nominations for distinguished papers in Egocentric Vision

Jan 2024: Applications for Summer of Research have now closed. Results are expected 20 Feb.

Nov 2023: Applications for Summer of Research @Bristol 2024 are now open [DL 19 Jan 2024]

Oct 2023: Our BMVC'23 paper "Learning Temporal Sentence Grounding From Narrated EgoVideos" now available on ArXiv

Sep 2023: EPIC Fields paper accepted at NeurIPS 2023

Aug 2023: Survey paper "An Outlook into the Future of Egocentric Vision" open for comments on OpenReview until 15 Sep. All major corrections/suggestions will be acknowledged in revised version.

Aug 2023: Our paper "Learning Temporal Sentence Grounding From Narrated EgoVideos" was accepted ab BMVC 2023. Preprint coming soon

July 2023: Our paper "What can a cook in Italy teach a Mechanic in India?" was accepted at ICCV 2023. Dataset and Code are public

June 2023: I'll be giving a keynote at WACV 2024 next Jan.

June 2023: Winners of the 2023 EPIC-KITCHENS challenges announced

[Closed for applications]May 2023: Open PhD position on Long-Term Video Understanding in collaboration with Adobe - for a start anytime between Sep 2023 and Feb 2024. Apply here asap, open until filled or end of June.

Mar 2023: Postdoc Opportunity (26 months) open in my group - Details and Application Process - DL 23 Apri 2023

Feb 2023: Two papers accepted at CVPR 2023

Feb 2023: Two papers accepted at ICASSP 2023: Play-It-Back and EPIC-SOUNDS

Feb 2023: On a research visit to UC Berkeley

Jan 2023: EPIC-SOUNDS dataset publicly available

Oct 2022: Our paper ConTra accepted as an oral at ACCV 2022

Sep 2022: VISOR and EgoClip papers accepted at NeurIPS 2022

Sep 2022: Up to 3 open PhD positions for 2022/2023 in my group [applications closed]

Aug 2022: Rleased VISOR Benchmark: Video Segmentations and Object Relations. Watch the Trailer

June 2022: ran the Joint 10th EPIC Workshop and 1st Ego4D workshop alongside CVPR 2022 in New Orleans

Mar 2022: Two papers accepted at CVPR 2022.

Feb 2022: Ego4D Dataset is now publicly available

Jan 2022:

Dec 2021: New ArXiv Paper: UnweaveNet: Unweaving Activity Stories

Nov 2021: Our BMVC 2021 paper "With a little help from my temporal context" is now Available on ArXiv

Oct 2021: Ego4D Project and ArXiv paper now out. Reveal session during EPIC@CCV2021

Sep 2021: Our paper Rescaling Egocentric Vision accepted at IJCV

Aug 2021: Welcoming Alexandros Stergiou and Bin Zhu as postdocs to the group

July 2021: Technical report for 2021 EPIC-KITCHENS challengs is online

June 2021: Our paper Slow-Fast Auditory Streams won outstanding paper at ICASSP 2021 (3 out of 1700 papers awarded)

June 2021: EPSRC Program Grant Visual AI has a live website now

June 2021: Pleased to be outstanding reviewer for CVPR 2021

May 2021: During CVPR 2021, I'll be delivering keynotes during 2nd comprehensive tutorial on Video understanding, 8th workshop on FGVC and 2nd HVU workshop, in addition to co-organising 8th EPIC@CVPR2021

Mar 2021: CVPR 2021 paper "On Semantic Similarity in Video Retrieval" now on ArXiv

Mar 2021: CVPR 2021 paper "Temporal-Relational CrossTransformers for Few-Shot Action Recognition" now on ArXiv

Feb 2021: Will be delivering keynotes at two CVPR2021 workshops: Fine-grained visual categorisation (FGVC8) and Holistic Video Understanding (HVU)

Jan 2021: Slides for my talk at HAU@ICPR 2021 workshop can be found here

Nov 2020: Two papers presented at ACCV 2020: Play Fair: Frame Attributions in Video Models (Project) and
Meta-Learning with Context-Agnostic Initialisations (Project)

Nov 2020: Excited to start active work as Program Chair for ICCV 2021 in Montreal

Sep 2020: Glad to join the ELLIS (European Laboratory for Learning and Intelligent Systems) Society as a member

Sep 2020: Will be giving a keynote at the Deep Video Understanding workshop alongside ICMI 2020

Sep 2020: Will be giving a keynote at the HCMA workshop alongside ACM MM on 12 Oct

Aug 2020: Final program for our EPIC@ECCV Workshop is now available online

1 July 2020: EPIC-KTICHESN-100 Dataset Now Released - Download, webinar

June 2020: ArXiv Manuscript "Rescaling Egocentric Vision" is now online

June 2020: Will be happy to deliver keynotes in August at ECCV workshops: Women in Computer Vision and Compositional and Multimodal Video Perception Challenge

Jun 2020: Proud to be an Outstanding Reviewer for CVPR 2020.

Jun 2020: My talk on "Learning from Narrated Videos of Everyday Tasks" at the CVPR2020 workshop on Instructional Videos is now available online

Jun 2020: Deadline for the 7th EPIC@ECCV2020 Workshop is 10th of July - published proceedings included

Apr 2020: EPSRC Program Grant Visual AI approved for funding.

Mar 2020: I join the editorial board of IJCV as an associate editor.

Mar 2020: Our paper "Action Modifers: Learning from Adverbs in Instructional Videos", accepted at CVPR 2020 is now on ArXiv - watch the video that explains the method here

Mar 2020: Our paper "Multi-Modal Domain Adaptation for Fine-Grained Action Recognition", accepted for Oral at CVPR 2020 is now on Arxiv - see project details

Feb 2020: Two papers accepted in CVPR 2020 - available in Arxiv already (see publications)

Dec 2019: Jade-2 HPC Cluster has been accepted for funding

Dec 2019: My talk at NCVPRIPG2019 in Hubli India is available here

Dec 2019: I start EPSRC Early Career Fellowship UMPIRE this Jan. 5-Years Funding to expand my research activities in object interaction understanding.

Nov 2019: I join the editorial board of IEEE TPAMI as associate editor

Nov 2019: Congrats to Davide Moltisanti and Michael Wray for passing their PhD vivas

Oct 2019: My talk from the Extreme Vision ICCV workshop is available here

Oct 2019: Videos of all talks in our BMVA symposium are on available on YouTube

Oct 2019: Videos of my 4-hour tutorial at North African Summer School in Machine Learning are now on YouTube: Part1, Part2

Sep 2019: Our paper "Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos" (ICCVW) is now on Arxiv - Details

Aug 2019: We release pretrained models and technical report for action recognition on EPIC-Kitchens

July 2019: Our paper "Learning Visual Actions Using Multiple Verb-Only Labels" accepted for presentation at BMVC2019 is available on Arxiv

July 2019: Two papers accepted at ICCV 2019, "EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition" with Evangelos Kazakos (Bristol), Arsha Nagrani and Andrew Zisserman (Oxford), and "Fine-Grained Action Retrieval through Multiple Parts-of-Speech Embeddings" with Mike Wray (Bristol), Gabriela Csurka and Diane Larlus (Naver Labs)

July 2019: I'll be giving keynotes at the ICCV2019 workshop YouTube8M, ICCV2019 workshop ACVR, and at the BMVC2019 workshop EgoApp

July 2019: CFP BMVA symposium on Video Understanding in London - 25 Sep

June 2018: Slides from my tutorial at North African Summer School in Machine Learning (NASSMA) are now online

Apr 2019: Camera ready version and details of our paper Dual-Domain LSTM for Cross-Dataset Action Recognition - CVPR 2019 now online

Apr 2019: Camera ready version and details of our paper The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos - CVPR 2019 now online

Apr 2019: Fifth EPIC workshop accepted - EPIC@ICCV2019 will be held in Seoul this Oct/Nov

Apr 2019: Will be giving a keynote at the 7th Workshop on Assistive Computer Vision and Robotics alongside ICCV in Seoul this October.

Apr 2019: Camera ready version and details of our paper Action Recognition from Single Timestamp Supervision in Untrimmed Videos - CVPR 2019 now online and on Arxiv

Mar 2019: Looking forward to returning as a speaker for the 2019 BMVA summer school in Lincoln this June

Mar 2019: Slides for my keynote at VISAPP now online

Mar 2019: Invited as one of the speakers at the First North African summer school in Machine Learning NASSMA

Feb 2019: Three papers accepted at CVPR 2019 (coming soon on Arxiv)

Feb 2019: Keynote at VISAPP 2019 in Prague

Dec 2018: EPIC@CVPR2019 Workshop to take place in Long Beach

Oct 2018: Scheduled talk at MPI Tubingen - details

Sep 2018: EPIC-KITCHENS presented as Oral at ECCV 2018 - camera ready available Arxiv, Webpage

Sep 2018: Leaderboards for the EPIC-KITCHENS challenges on CodaLab are now open

Sep 2018: Two papers presented at BMVC 2018. Action Completion (Dataset) and CaloriNet

Aug 2018: EPIC-SKILLS dataset, for our CVPR2018 paper is now online

Aug 2018: Programme for EPIC@ECCV2018 workshop is now available. Join us in Munich on Sep 9th

July 2018: Looking forward to giving a tutorial on egocentric vision as part of the BMVA Summer School on July 5th, University of East Anglia.

Apr 2018: EPIC-KITCHENS 2018 goes live today: 11.5M Frames, full HD, 60fps, head-mounted, 32 kitchens from 4 cities (in North America and Europe), 10 nationalities. FULLY annotated: 40K action segments, 454K object bounding boxes. Dataset: http://epic-kitchens.github.io Details at: Arxiv

Apr 2018: Our paper "Human Routine Change Detection using Bayesian Modelling" accepted at ICPR2018, to be presented in Beijing this August. Details

Feb 2018: Our paper "Who's Better, Who's Best" accepted at CVPR2018, to be presented in Salt Lake city this June. Details

Feb 2018: Congrats to Yangdi Xu for passing his PhD viva with minor corrections

Jan 2018: Serving on the High Performance Computing exec board at UoB

Oct 2017: Selected as outstanding reviewer at ICCV 2017

Oct 2017: Well-attended Second Int. Egocentric Perception Interaction and Computing (EPIC) workshop alongside ICCV in Venice

Oct 2017: Our paper "Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video" was presented in ICCV - details

Oct 2017: Our paper "Recurrent Assistance: Cross-Dataset Training of LSTMs on Kitchen Tasks" was presented at ACVR - pdf

Sep 2017: Unit details for the new Applied Deep Learning M level unit - Uni Catalogue

Sep 2017: Serving as associate editor for Pattern Recognition

Aug 2017: Happy to be working as a consultant with Bristol's Cookpad on developing their Computer Vision and Machine Learning agenda

Apr 2017: 6 July - Lincoln, BMVA summer school, will be giving a tutorial on Egocentric Vision

Apr 2017: 15 May - Bristol, will be giving a public talk on 'What can a wearable camera know about me?'

Mar 2017: Slides from my talk on Challenges and Opportunities for Action and Activity Recognition using RGBD Data, BMVA Symposium are now available

Feb 2017: Videos from BMVA symposium on Transfer Learning now available

Dec 2016: Final programme for BMVA Symposium on Transfer Learning now available

Oct 2016: Code Released for 3DV paper on acquisition and registration of point clouds using two facing Kinects

Sep 2016: 3D Data Acquisition and Registration Using Two Opposing Kinects - Paper accepted at 3DV

Aug 2016: Action Completion paper accepted at BMVC and dataset released - Project Webpage

Aug 2016: Nokia Technologies donation of €50K Press release

Aug 2016: Action Completion paper accepted at BMVC, York, Sep 2016. project

July 2016: PhD students Michael Wray and Davide Moltisanti awarded second poster prize at BMVA summer school news

July 2016: CFP: Transfer Learning in Computer Vision - BMVA Symposium [details, dates and submission]

Jun 2016: PhD opening in Computer Vision and Machine Learning (Home/EU students) - Open Until , ad on jobs.ac.uk

Jun 2016: CVPR 2016 Demo for GlaciAR

May 2016: EPIC@ECCV2016 Workshop (Egocentric Perception, Interaction and Computing) Accepted.

Apr 2016: EPSRC Project LOCATE to be funded starting July 2016

Mar 2016: You-Do, I-Learn: Egocentric Unsupervised Discovery of Objects and their Modes of Interaction Towards Video-Based Guidance accepted at CVIU

Nov 2015: EPSRC Project GLANCE to be funded starting March 2016

Sep 2015: Paper "Unsupervised Daily Routine Modelling from a Depth Sensor using Bottom-Up and Top-Down Hierarchies" accepted at ACPR

Sep 2015: Paper "Estimating Visual Attention from a Head Mounted IMU" presented at ISWC in Okasa, Japan

Sep 2015: Paper "Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling" Presented at BMVC

Aug 2015: PhD Student Vahid Soleiman publishes paper on Remote Pulmonary Function Testing using a Depth Sensor at BIOCAS 2015. Demo Video

June 2015: PLOSONE article available online

June 2015: SI on cognitive robotics systems: concepts and applications at the Journal of Intelligent & Robotic Systems is online

Mar 2015: Interdisciplinary research internship awarded for CS student Hazel Doughty.

Sep 2014: Paper "You-Do, I-Learn: Discovering Task Relevant Objects and their Modes of Interaction from Multi-User Egocentric Video" presented at BMVC

Sep 2014: Paper "Online quality assessment of human movement from skeleton data" presented at BMVC

Sep 2014: Paper "Multi-user egocentric Online System for Unsupervised Assistance on Object Usage" presented at ECCVW (ACVR 2014)

Aug 2014: C++ code (improved performance v 1.2) and Android apk for real-time object detector available.

July 2014: The Bristol Egocentric Object Interactions Dataset has now been released

July 2014: Book review published in IAPR newsletter

July 2014: Video lectures from BMVC 2013 are now available online.

July 2014: Sphere project's website irc-sphere.ac.uk has now been released (2013-2018).

May 2014: Project Ideas for 3G403 and 2G400 students available.

Feb 2014: PhD Opening in Ego-centric Vision - apply as soon as possible...

Nov 2013: Project GlaciAR is starting funded by Samsung's GRO 2013 Awards

Nov 2013: Cognitive Robotics Systems (CRS 2013) (IROS 2013 workshop), successfully concludes at Tokyo, Japan.

Sep 2013: BMVC 2013 successfully concluded at Bristol

Aug 2013: Outstanding Reviewer award at IEEE AVSS 2013.

June 2013: Outstanding Reviewer award at IEEE CVPR 2013.

May 2013: New bug-fixed version (v1.1) of our Multi-Object Detector (MOD) code is now available online

Research Projects

It's Just Another Day

T Perrett, T Han, D Damen, A Zisserman (2024). It's Just Another Day: Unique Video Captioning by Discriminitave Prompting. ACCV (Oral Presentation) ArXiv | Website | Code and Benchmark

AMEGO: Active Memory from long EGOcentric videos

G Goletto, T Nagarajan, G Averta, D Damen (2024). AMEGO: Active Memory from long EGOcentric videos. ECCV ArXiv | Website | AMB Benchmark | Code

HOI-Ref: Hand-Object Interaction Referral

S Bansal, M Wray, D Damen (2024). HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision. ArXiv | Website | HOI-QA Dataset | Models and Code

TIM: A Time Interval Machine

TIM: A Time Interval Machine for Audio-Visual Action Recognition. Jacob Chalk, Jaesung Huh, Evangelos Kazakos, Andrew Zisserman, Dima Damen (2024). IEEE/CVF Computer Vision and Pattern Recognition (CVPR). Webpage | Code and Models | ArXiv | < a href="https://openaccess.thecvf.com/content/CVPR2024/papers/Chalk_TIM_A_Time_Interval_Machine_for_Audio-Visual_Action_Recognition_CVPR_2024_paper.pdf">CVF PDF

Out of Sight, not Out of Mind

ESpatial Cognition from Egocentric Video: Out of Sight, Not Out of Mind. Chiara Plizzari, Shubham Goel, Toby Perrett, Jacob Chalk, Angjoo Kanazawa, Dima Damen (2024). Webpage | ArXiv | Video

Every Shot Counts

Every Shot Counts: Using Exemplars for Repetition Counting in Videos. Saptarshi Sinha, Alexandros Stergiou, Dima Damen (2024). Asian Conference on Computer Vision (ACCV). Webpage | Code | ArXiv

We propose an exemplar-based approach that discovers visual correspondence of video exemplars across repetitions within target videos. Our proposed Every Shot Counts (ESCounts) model is an attention-based encoder-decoder that encodes videos of varying lengths alongside exemplars from the same and different videos.

GenHowTo

GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos. Tomas Soucek, Dima Damen, Michael Wray, Ivan Laptev, Josef Sivic (2024). IEEE/CVF Computer Vision and Pattern Recognition (CVPR). Webpage | Code | ArXiv | CVF PDF

Get A Grip

Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videos. Zhifan Zhu and Dima Damen (2024). ArXiv. Webpage | EPIC-Grasps Dataset and Code | ArXiv (v2)

Rank2Reward

Rank2Reward: Learning Shaped Reward Functions from Passive Video. Daniel Yang, Davin Tjia, Jacob Berg, Dima Damen, Pulkit Agrawal and Abhishek Gupta (2024). IEEE International Conference on Robotics and Automation (ICRA).Webpage | ArXiv

Ego-Exo4D

Webpage and Dataset |Video

Ego-Exo4D : Understanding Skilled Human Activity from First- and Third-Person Perspectives. K Grauman et al. (2024). IEEE/CVF Computer Vision and Pattern Recognition (CVPR). ArXiv, Webpage, PDF | CVF PDF

The Future of Egocentric Vision.

An Outlook into the Future of Egocentric Vision. C Plizzari*, G Goletto*, A Furnari*, S Bansal*, F Ragusa*, GM Farinella, D Damen, T Tommasi. (2024). International Journal of Computer Vision (IJCV). PDF | Open Review Preprint | ArXiv

Learning Temporal Sentence Grounding From Narrated EgoVideos

Learning Temporal Sentence Grounding From Narrated EgoVideos. K Flanagan, D Damen, M Wray (2023). British Machine Vision Conference (BMVC). ArXiv Camera Ready | Project Webpage | Code and Models

EPIC Fields: Marrying 3D Geometry and Video Understanding

Trailer | Download

EPIC Fields: Marrying 3D Geometry and Video Understanding. V Tschernezki*, A Darkhalil*, Z Zhu*, D Fouhey, I Laina, D Larlus, D Damen, A Vedaldi (2023). Neural Information Processing Systems (NeurIPS) Preprint, Webpage

What can a cook in Italy teach a mechanic in India?

What can a cook in Italy teach a mechanic in India? Action Recognition Generalisation Over Scenarios and Locations. C Plizzari, T Perrett, B Caputo, D Damen. ICCV 2023 Preprint | Webpage | Dataset | Code

Use Your Head: Improving Long-Tail Video Recognition

CVF PDF | CVF Supp | ArXiv | Webpage | Benchmarks, Code and Models

Use Your Head: Improving Long-Tail Video Recognition. T Perrett, S Sinha, T Perrett, M Mirmehdi, D Damen. CVPR 2023.

Temporal Progressive Attention for Early Action Prediction

CVF PDF | CVF Supp | ArXiv | Webpage | Code

The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction. A Stergiou, D Damen. CVPR 2023.

EPIC-SOUNDS: A Large-Scale Dataset of Actions that Sound

Trailer | Download

EPIC-SOUNDS: A Large-Scale Dataset of Actions that Sound. J Huh*, J Chalk*, E Kazakos, D Damen, A Zisserman. ICASSP 2023. ArXiv, Webpage

Play It Back: Iterative Attention for Audio Recognition

Code

Play It Back: Iterative Attention for Audio Recognition. A Stergiou, D Damen. ICASSP 2023. ArXiv, Webpage

VISOR: Video Segmentations and Object Relations

Trailer | Reveal @EPIC2022 | Download

EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations. A Darkhalil, D Shan, B Zhu, J Ma, A Kar, R Higgins, S Fidler, D Fouhey, D Damen. NeurIPS 2022. PDF, Webpage

ConTra: Context Transformer for Cross-Modal Retrieval

Video

ConTra: Context Transformer for Cross-Modal Retrieval. A Fragomeni, M Wray, D Damen. ACCV (2022) Oral. ArXiv | PDF Preprint | Project Webpage | Code

Egocentric Video-Language PreTraining

Egocentric Video-Language Pretraining. KQ Lin, AJ Wang, M Soldan, M Wray, R Yan, EZ Xu, D Gao, R Tu, W Zhao, W Kong, C Cai, H Wang, D Damen, B Ghanem, W Liu, MZ Shou. NeurIPS (2022). ArXiv | PDF Preprint | Project Webpage | Code

UnweaveNet: Unweaving Activity Stories

Video

UnweaveNet: Unweaving Activity Stories. W Price, C Vondrick, D Damen. CVPR (2022). ArXiv Paper | Project Webpage | Annotations

Ego4D: Around the World in 3,000 Hours of Egocentric Video

Ego4D Project and Dataset | Reveal Session Video | Trailer Video

Around the World in 3,000 Hours of Egocentric Video. K Grauman (+83 Authors) et al. CVPR (2022). ArXiv

Temporal Context in Egocentric Video

Video

With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition. E Kazakos, J Huh, A Nagrani, A Zisserman, D Damen. BMVC (2021). ArXiv Paper | Project Webpage | Code, features and models

Rescaling Egocentric Vision

Trailer | Video Demonstration | Webinar | Download

Rescaling Egocentric Vision. D Damen, H Doughty, G Farinella, A Furnari, E Kazakos, J Ma, D Moltisanti, J Munro, T Perrett, W Price, M Wray. IJCV. IJCV paper, ArXiv, Webpage

The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines. D Damen, H Doughty, GM Farinella, S Fidler, A Furnari, E Kazakos, D Moltisanti, J Munro, T Perrett, W Price, M Wray. IEEE Transactions on Pattern Analysis and Machine Intelligence 43(11) pp 4125-4141 (2021). IEEE, Arxiv Preprint

Domain Adaptation in Video Retrieval

Domain Adaptation in Multi-View Embedding for Cross-Modal Video Retrieval. J Munro, M Wray, D Larlus, G Csurka, D Damen. ArXiv (2021). ArXiv Paper

Semantic Similarity in Video Retrieval

On Semantic Similarity in Video Retrieval. M Wray, H Doughty, D Damen. CVPR (2021). CVF PDF | ArXiv Preprint | Project Webpage | Video

Temporal-Relational CrossTransformers

Temporal-Relational CrossTransformers for Few-Shot Action Recognition. T Perrett, A Masullo, T Burghardt, M Mirmehdi, D Damen. CVPR (2021). CVF PDF | ArXiv Preprint | Code and Model | Project Webpage

Slow-Fast Auditory Streams

Slow-Fast Auditory Streams For Audio Recognition. E Kazakos, A Nagrani, A Zisserman, D Damen. ICASSP (2021). ArXiv Preprint | IEEE PDF | Code and Models | Project Webpage [Outstanding Paper]

Frame Attributions in Video Models

Interactive Dashboard | Teaser Video | Code

Play Fair: Frame Attributions in Video Models. W Price, D Damen. ACCV (2020). ArXiv Preprint | Project Details | CVF | CVF PDF

MetaLearning with Context-Agnostic Initialisation

Talk Video

MetaLearning with Context-Agnostic Initialisation. T Perrett, A Masullo, T Burghard, M Mirmehdi, D Damen. ACCV (2020). ArXiv Preprint | CVF | CVF PDF | Project Details

Action Modifiers: Learning from Adverbs in Instructional Videos

Video, Talk Video

Action Modifiers: Learning from Adverbs in Instructional Videos. H Doughty, I Laptev, W Mayol-Cuevas, D Damen. CVPR (2020). ArXiv Preprint, CVF PDF, Project Details

Multi-Modal Domain Adaptation for Fine-Grained Action Recognition

Video, Oral Presentation Video

Multi-modal Domain Adaptation for Fine-grained Action Recognition. J Munro, Dima Damen. CVPR (2020). ArXiv Preprint, CVF PDF, Project Details, Code

Retro-Actions

Video

Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos. W Price, Dima Damen. ICCV (2019). ArXiv Preprint, Project Details

Fine-Grained Action Retrieval

Video

Fine-Grained Action Retrieval through Multiple Parts-of-Speech Embeddings. Michael Wray, Diane Larlus, Gabriela Csurka, Dima Damen. ICCV (2019). CVF PDF, ArXiv Preprint, Project Details

Audio-Visual Temporal Binding for Egocentric Action Recognition

Talk Video, Video

EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition. Evangelos Kazakos, Arsha Nagrani, Andrew Zisserman, Dima Damen. ICCV (2019). Project Details, CVF PDF, Arxiv Preprint

Learning Visual Actions Using Multiple Verb-Only Labels

Video

Learning Visual Actions Using Multiple Verb-Only Labels. M Wray, D Damen. BMVC (2019). ArXiv Preprint, Project Details

DDLSTM: Dual-Domain LSTM

Video

DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition. T Perrett and D Damen. CVPR (2019). pdf preprint, Arxiv Project Details

The Pros and Cons: Rank-Aware Attention Modules

Teaser Video

Results Video

The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos. H Doughty, W Mayol-Cuevas, D Damen. CVPR (2019). pdf preprint, Arxiv, Project Details

Action Recognition from Single Timestamps

Results Video

Action Recognition from Single Timestamp Supervision in Untrimmed Videos. D Moltisant, S Fidler and D Damen. CVPR (2019). pdf preprint, Project Details

Tent Assembly Egocentric Dataset

Video

(2021) B Sullivan, C Ludwig, D Damen, W Mayol-Cuevas, I Gilchrist. Look-Ahead Fixations During Visuomotor Behavior: Evidence from Assembling a Camping Tent. Journal of Vision 21(3):13. PDF

EPIC-Tent: An Egocentric Video Dataset for Camping Tent Assembly. Y Jang, B Sullivan, C Ludwig, I.D. Gilchrist, D Damen and W Mayol-Cuevas. ICCV Workshops (2019). pdf, Project Details, Dataset, Annotations

Scaling Egocentric Vision: EPIC-KITCHENS 2018

Video

Scaling Egocentric Vision: The EPIC-KITCHENS Dataset. D Damen, H Doughty, G Farinella, S Fidler, A Furnari, E Kazakos, D Moltisanti, J Munro, T Perrett, W Price, M Wray. ECCV (2018). Webpage | Dataset | arxiv

An Evaluation of Action Recognition Models on EPIC-Kitchens. W Price, D Damen. Arxiv (2019) Arxiv | Github | PDF

The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines. D Damen, H Doughty, GM Farinella, S Fidler, A Furnari, E Kazakos, D Moltisanti, J Munro, T Perrett, W Price, M Wray. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020). Arxiv Preprint

Skill Determination in Video

Video

Who's Better? Who's Best? Pairwise Deep Ranking for Skill Determination. H Doughty, D Damen, W Mayol-Cuevas. CVPR (2018). PDF | arxiv | Dataset

Action Completion: A Temporal Model for Moment Detection

Weakly-Supervised Completion Moment Detection using Temporal Attention. F Heidarivincheh, M Mirmehdi, D Damen. ICCV Workshop on Human Behaviour Understanding. Arxiv | CVF PDF, Oct 2019.

Video2018, Video2016

Action Completion: A Temporal Model for Moment Detection. F Heidarivincheh, M Mirmehdi, D Damen. British Machine Vision Conference (BMVC), Sep 2018. Arxiv PDF | Dataset

Beyond Action Recognition: Action Completion in RGB-D Data. F Heidarivincheh, M Mirmehdi, D Damen. British Machine Vision Conference (BMVC), Sep 2016. pdf | abstract | Dataset

Human Routine Modelling and Change Detection

Human Routine Change Detection using Bayesian Modelling. Y Xu, D Damen. ICPR (2018). PDF

Unsupervised Long-Term Routine Modelling using Dynamic Bayesian Networks. Y Xu, D Bull, D Damen. DICTA (2017). PDF

Trespassing the Boundaries of Object Interactions

Video

Trespassing the Boundaries: Labeling Temporal Bounds for Object Interactions in Egocentric Video. D Moltisanti, M Wray, W Mayol-Cuevas, D Damen. International Conference on Computer Vision (ICCV), 2017. pdf (camera ready) | arxiv

Semantic Embedding for Egocentric Actions

Video

SEMBED: Semantic Embedding of Egocentric Action Videos. M Wray, D Moltisanti, W Mayol-Cuevas, D Damen. Egocentric Interaction, Perception and Computing (EPIC), European Conference on Computer Vision Workshops (ECCVW), Oct 2016. pdf | Dataset

You-Do, I-Learn

Video1 (2014), Video2 (2017)

Automated capture and delivery of assistive task guidance with an eyewear computer: The GlaciAR system. T Leelasawassuk, D Damen, W Mayol-Cuevas. Augmented Human, Mar 2017 pdf

You-Do, I-Learn: Discovering Task Relevant Objects and their Modes of Interaction from Multi-User Egocentric Video. D Damen, T Leelasawassuk, O Haines, A Calway, W Mayol-Cuevas. British Machine Vision Conference (BMVC), Sep 2014. PDF | Abstract | Dataset

Multi-user egocentric Online System for Unsupervised Assistance on Object Usage. D Damen, O Haines, T Leelasawassuk, A Calway, W Mayol-Cuevas. ECCV Workshop on Assistive Computer Vision and Robotics (ACVR), Sep 2014. PDF Preprint

Estimating Visual Attention from a Head Mounted IMU. T Leelasawassuk, D Damen, W Mayol-Cuevas. International Symposium on Wearable Computers (ISWC), Sep 2015. PDF

DS-KCF: Depth-Based Real-Time Single Object Tracker

Video 1 | Video 2 | Code

Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling. M Camplani, S Hannuna, M Mirmehdi, D Damen, L Tao, T Burghardt and A Paiment. British Machine Vision Conference (BMVC), Sep 2015. PDF.

Real-time Learning and Detection of 3D Texture-minimal Objects

Video | Code

Real-time Learning and Detection of 3D Texture-minimal Objects: A Scalable approach. D Damen, P Bunnun, A Calway, W Mayol-Cuevas. British Machine Vision Conference (BMVC), Sep 2012. PDF | Abstract | Code | Video | Dataset.

Efficient Texture-less Object Detection for Augmented Reality Guidance. T Hodan, D Damen, W Mayol-Cuevas, J Matas. IEEE Int. Symposium on Mixed and Augmented Reality (ISMAR) Workshop on Visual Recognition and Retrieval for Mixed and Augmented Reality, Sep 2015.

Egocentric Real-time Industrial Workflow

Video 1 | Video 2

Cognitive Learning, Monitoring and Assistance of Industrial Workflows Using Egocentric Sensor Networks. G Bleser, D Damen, A Behera, et al. PLOSONE, June 2015 PDF.

Egocentric Real-time Workspace Monitoring using an RGB-D Camera. D Damen, A Gee, W Mayol-Cuevas, A Calway. Intelligent Robotics and Systems (IROS), Oct 2012. PDF | Video.

Online Quality Assessment for Human Motion

Code

Online quality assessment of human movement from skeleton data. A Paiment, L Tao, S Hannuna, M Camplani, D Damen and M Mirmehdi. British Machine Vision Conference (BMVC), Sep 2014. PDF | Dataset.

The Bicycle Problem

Explaining Activities as Consistent Groups of Events - A Bayesian Framework using Attribute Multiset Grammars. D Damen and D Hogg International Journal of Computer Vision (IJCV), 2012. PDF.

Recognizing Linked Events: Searching the Space of Feasible Explanations. D Damen and D Hogg. Computer Vision and Pattern Recognition (CVPR), Miami, Florida, June 2009. PDF | Poster

Detecting Carried Objects from Walking Pedestrians

Video | Code

Detecting Carried Objects from Sequences of Walking Pedestrians. D Damen and D Hogg. Pattern Analysis and Machine Intelligence (PAMI), 2012. PDF.

Detecting Carried Objects in Short Video Sequences. D Damen and D Hogg. European Conference on Computer Vision (ECCV), Marseille, France, Oct 2008 PDF | Poster

Research Group Members

Previous Students, and Postdocs