Ego4D: Around the World in 3,600 Hours of Egocentric Video

Ego4D: Around the World in 3,600 Hours of Egocentric Video

Článek WoS

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception.

Cameras, Benchmark testing, Three-dimensional displays, Task analysis, Annotations, Cultural differences, Computer vision, Video understanding, egocentric video, first-person vision, datasets and benchmarks

Cameras, Benchmark testing, Three-dimensional displays, Task analysis, Annotations, Cultural differences, Computer vision, Video understanding, egocentric video, first-person vision, datasets and benchmarks

GRAUMAN, K.; WESTBURY, A.; BYRNE, E.; CARTILLIER, V.; CHAVIS, Z.; FURNARI, A.; GIRDHAR, R.; HAMBURGER, J.; JIANG, H.; KUKREJA, D.; LIU, M.; LIU, X.; MARTIN, M.; NAGARAJAN, T.; RADOSAVOVIC, I.; RAMAKRISHNAN, S.; RYAN, F.; SHARMA, J.; WRAY, M.; XU, M.; XU, E.; ZHAO, C.; BANSAL, S.; BATRA, D.; CRANE, S.; DO, T.; DOULATY, M.; ERAPALLI, A.; FEICHTENHOFER, C.; FRAGOMENI, A.; FU, Q.; GEBRESELASIE, A.; GONZALEZ, C.; HILLIS, J.; HUANG, X.; HUANG, Y.; JIA, W.; KHOO, W.; KOLAR, J.; KOTTUR, S.; KUMAR, A.; LANDINI, F.; LI, C.; LI, Y.; LI, Z.; MANGALAM, K.; MODHUGU, R.; MUNRO, J.; MURRELL, T.; NISHIYASU, T.; PRICE, W.; RUIZ PUENTES, P.; RAMAZANOVA, M.; SARI, L.; SOMASUNDARAM, K.; SOUTHERLAND, A.; SUGANO, Y.; TAO, R.; VO, M.; WANG, Y.; WU, X.; YAGI, T.; ZHAO, Z.; ZHU, Y.; ARBELAEZ, P.; CRANDALL, D.; DAMEN, D.; FARINELLA, G.; FUEGEN, C.; GHANEM, B.; KRISHNA, V.; JAWAHAR, C.; JOO, H.; KITANI, K.; LI, H.; NEWCOMBE, R.; OLIVA, A.; PARK, H.; REHG, J.; SATO, Y.; SHI, J.; ZHENG SHOU, M.; TORRALBA, A.; TORRESANI, L.; YAN, M.; MALIK, J.

2026

01.11.2025

IEEE

IEEE Transactions on Pattern Analysis and Machine Intelligence

47

11

Spojené státy americké

9468

9509

42

https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10611736&utm_source=scopus&getft_integrator=scopus&tag=1

http://hdl.handle.net/11012/256279

landini_IEEE TPAMI_2025_Ego4D_Around_the_World_in_3600_Hours_of_Egocentric_Video