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

HD-EPIC (2025 -) [CVPR 2025]

The most highly detailed evaluation dataset on egocentric vision with a 3D digital twin https://hd-epic.github.io/site/

Ego-Exo4D (2024-) [CVPR 2025, IJCV 2025]

Ego-Exo4D offers highly skilled recordings from multiple cameras (ego and exo) https://ego-exo4d-data.org/

Ego4D (2022-) [CVPR 2022, TPAMI 2024]

Ego4D: 3,025 hours of egocentric video captured in 74 cities in 9 countries by 855 participants - a consortium of 13 universities in partnership with Facebook AI Research https://ego4d-data.org/ **Data available end of Nov 2021**

EPIC-KITCHENS (2018-) [ECCV 2018, IJCV 2021]

EPIC-KITCHENS: 20M Frames, full HD, head-mounted, 45 kitchens from 4 cities (in North America and Europe). FULLY annotate.
Dataset from: http://epic-kitchens.github.io

The dataset is the first of its kind, in size, annotations, diversity and unscripted nature of its collection. It is accompanied by challenge leaderboards to allow comparative evaluation of methods on 6 benchmarks. Since its first-version release in 2018, the dataset has: 2.4K unique downloads from 54 countries (most downloaded dataset from UoB data.bris), 1.5K submissions to challenge leaderboards (by May 2021), 410 peer-reviewed citations.

Published Datasets with Papers

• EPIC-SKILLS (2018)
• Moment of Completion in Actions - 16 action labels for UCF101, HMDB and RGBD-AC (2018)
• RGB-D Action Completion Dataset (2016)
• Bristol Egocentric Object Interactions Dataset (2014)
• Quality of Motion - Staircase Dataset (2014)
• 30 Textureless Tools and Objects Dataset (2012)
• Annotations of the PETS 2006 dataset for carried objects (2008)

Published Code

• Data Acquisition and Registration from two facing Microsoft Kinects

  C++ implementation for capturing and registrating 3D models from two frontly facing Kinects [Author: Vahid Soleimani].

  Version 1.0 is now available [Oct 2016]

• Real-Time Learning and Detection of Texture-Minimal Objects

  C++ Linux-based code for real-time learning and detection of texture-minimal objects.

  Video on how to run the detector is available on Youtube

  Version 1.2 (bug-fixed and performance improved) C++ Source code - Aug 2014

  Android (4.0+) .apk file is now available [Aug 2014]

• Carried Object Detector

  MATLAB code is available with details of how to use it download (3.0MB)

  A short sequence from PETS2006 to test the code - download (3.9MB)

• DS-KCF Real-Time RGB-D Tracker

  (Developed by: Massimo Camplani)

  MATLAB code is available with details of how to use it

  C++ code coming soon...