Documentdetail
ID kaart
oai:arXiv.org:2409.10917
Onderwerp
Computer Science - Computer Vision...Auteur
Goletto, Gabriele Nagarajan, Tushar Averta, Giuseppe Damen, DimaCategorie
Computer Science
Jaar
2024
vermelding datum
25-09-2024
Trefwoorden
queries egocentric amegoBeschrijving
Egocentric videos provide a unique perspective into individuals' daily experiences, yet their unstructured nature presents challenges for perception.
In this paper, we introduce AMEGO, a novel approach aimed at enhancing the comprehension of very-long egocentric videos.
Inspired by the human's ability to maintain information from a single watching, AMEGO focuses on constructing a self-contained representations from one egocentric video, capturing key locations and object interactions.
This representation is semantic-free and facilitates multiple queries without the need to reprocess the entire visual content.
Additionally, to evaluate our understanding of very-long egocentric videos, we introduce the new Active Memories Benchmark (AMB), composed of more than 20K of highly challenging visual queries from EPIC-KITCHENS.
These queries cover different levels of video reasoning (sequencing, concurrency and temporal grounding) to assess detailed video understanding capabilities.
We showcase improved performance of AMEGO on AMB, surpassing other video QA baselines by a substantial margin.
;Comment: Accepted to ECCV 2024.
Project webpage: https://gabrielegoletto.github.io/AMEGO/
Goletto, Gabriele,Nagarajan, Tushar,Averta, Giuseppe,Damen, Dima, 2024, AMEGO: Active Memory from long EGOcentric videos
Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering
evaluation computer dataset images tti generation i-halla
Role of Repetitive Transcranial Magnetic Stimulation in Treatment of Fibromyalgia: A Randomized Controlled Trial
significant following stimulation fms treatment
