We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
The recent success in human action recognition with deep learning methods mostly adopt the supervised learning paradigm, which requires significant amount of manually labeled data to achieve good performance. However, label collection is an expensive and time-consuming process. In this work, we propose an unsupervised learning framework, which exploits unlabeled data to learn video representations. Different from previous works in video representation learning, our unsupervised learning task is to predict 3D motion in multiple target views using video representation from a source view. By learning to extrapolate cross-view motions, the representation can capture view-invariant motion dynamics which is discriminative for the action. In addition, we propose a view-adversarial training method to enhance learning of view-invariant features. We demonstrate the effectiveness of the learned representations for action recognition on multiple datasets.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1809.01844")
get_code_for_paper("1809.01844")
have("1809.01844")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/1809.01844.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/1809.01844)
Connect an agent — have() is free.