Projects per year
Abstract
This paper presents an investigation into long-tail
video recognition. We demonstrate that, unlike naturallycollected
video datasets and existing long-tail image benchmarks,
current video benchmarks fall short on multiple
long-tailed properties. Most critically, they lack few-shot
classes in their tails. In response, we propose new video
benchmarks that better assess long-tail recognition, by sampling
subsets from two datasets: SSv2 and VideoLT.
We then propose a method, Long-Tail Mixed Reconstruction
(LMR), which reduces overfitting to instances
from few-shot classes by reconstructing them as weighted
combinations of samples from head classes. LMR then
employs label mixing to learn robust decision boundaries.
It achieves state-of-the-art average class accuracy
on EPIC-KITCHENS and the proposed SSv2-LT and
VideoLT-LT. Benchmarks and code at: github.com/
tobyperrett/lmr
video recognition. We demonstrate that, unlike naturallycollected
video datasets and existing long-tail image benchmarks,
current video benchmarks fall short on multiple
long-tailed properties. Most critically, they lack few-shot
classes in their tails. In response, we propose new video
benchmarks that better assess long-tail recognition, by sampling
subsets from two datasets: SSv2 and VideoLT.
We then propose a method, Long-Tail Mixed Reconstruction
(LMR), which reduces overfitting to instances
from few-shot classes by reconstructing them as weighted
combinations of samples from head classes. LMR then
employs label mixing to learn robust decision boundaries.
It achieves state-of-the-art average class accuracy
on EPIC-KITCHENS and the proposed SSv2-LT and
VideoLT-LT. Benchmarks and code at: github.com/
tobyperrett/lmr
| Original language | English |
|---|---|
| Number of pages | 12 |
| Publication status | Published - 23 Jun 2023 |
| Event | IEEE/CVF Computer Vision and Pattern Recognition - Vancouver, Canada Duration: 18 Jun 2023 → 23 Jun 2023 |
Conference
| Conference | IEEE/CVF Computer Vision and Pattern Recognition |
|---|---|
| Abbreviated title | CVPR |
| Country/Territory | Canada |
| City | Vancouver |
| Period | 18/06/23 → 23/06/23 |
Fingerprint
Dive into the research topics of 'Use Your Head: Improving Long-Tail Video Recognition'. Together they form a unique fingerprint.-
Visual AI - Full Programme Grant Extension
Damen, D. (Principal Investigator)
1/06/23 → 30/11/25
Project: Research
-
UMPIRE: United Model for the Perception of Interactions for visual Recognition
Damen, D. (Principal Investigator)
1/02/20 → 31/01/25
Project: Research
-
SPHERE2
Craddock, I. J. (Principal Investigator), Mirmehdi, M. (Co-Investigator), Piechocki, R. J. (Co-Investigator), Flach, P. A. (Co-Investigator), Oikonomou, G. (Co-Investigator), Burghardt, T. (Co-Investigator), Damen, D. (Co-Investigator), Santos-Rodriguez, R. (Co-Investigator), O'Kane, A. A. (Co-Investigator), McConville, R. (Co-Investigator), Masullo, A. (Co-Investigator) & Gooberman-Hill, R. (Co-Investigator)
1/10/18 → 31/01/23
Project: Research, Parent
Datasets
-
EPIC-KITCHENS-100
Aldamen, D. (Creator), Kazakos, E. (Creator), Doughty, H. (Creator), Munro, J. (Creator), Price, W. (Creator), Wray, M. (Creator), Perrett, T. (Creator) & Ma, J. (Creator), University of Bristol, 15 May 2020
DOI: 10.5523/bris.2g1n6qdydwa9u22shpxqzp0t8m, http://data.bris.ac.uk/data/dataset/2g1n6qdydwa9u22shpxqzp0t8m
Dataset