Marcus Rohrbach, Shreyank Gowda, Frank Keller, Laura Sevilla-Lara
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
We address the problem of data augmentation for video action recognition. Standard augmentation strategies in video are handdesigned and sample the space of possible augmented data points either at random, without knowing which augmented points will be better, or through heuristics. We propose to learn what makes a "good" video for action recognition and select only high-quality samples for augmentation. In particular, we choose video compositing of a foreground and a background video as the data augmentation process, which results in diverse and realistic new samples. We learn which pairs of videos to augment without having to actually composite them. This reduces the space of possible augmentations, which has two advantages: it saves computational cost and increases the accuracy of the final trained classifier, as the augmented pairs are of higher quality than average. We present experimental results on the entire spectrum of training settings: few-shot, semisupervised and fully supervised. We observe consistent improvements across all of them over prior work and baselines on Kinetics, UCF101, HMDB51, and achieve a new state-of-the-art on settings with limited data. We see improvements of up to 8.6% in the semi-supervised setting. Project Page: https://sites.google.com/view/learn2augment/home Fig. 1. Standard video augmentation techniques generate data using hand-designed heuristics (left). We propose to learn to select videos for augmentation, based on how effective they will be for learning to classify (middle). Our approach, Learn2Augment, improves classification across datasets and settings, including UCF101 (right).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2206.04790")
get_code_for_paper("2206.04790")
have("2206.04790")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2206.04790.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2206.04790)
Connect an agent — have() is free.