Omni-sourced Webly-supervised Learning for Video Recognition

We introduce OmniSource, a novel framework for leveraging web data to train video recognition models. OmniSource overcomes the barriers between data formats, such as images, short videos, and long untrimmed videos for webly-supervised learning... (read more)

PDF Abstract ECCV 2020 PDF ECCV 2020 Abstract

Results from the Paper


Ranked #2 on Action Classification on Kinetics-400 (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Action Recognition HMDB-51 OmniSource (SlowOnly-8x8-R101-RGB + I3D Flow) Average accuracy of 3 splits 83.8 # 3
Action Classification Kinetics-400 OmniSource irCSN-152 (IG-Kinetics-65M pretrain) Vid acc@1 83.6 # 2
Action Recognition UCF101 OmniSource (SlowOnly-8x8-R101-RGB + I3D-Flow) 3-fold Accuracy 98.6 # 3

Methods used in the Paper


METHOD TYPE
Mixup
Image Data Augmentation