Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation

CVPR 2020 Min-Hung ChenBaopu LiYingze BaoGhassan AlRegibZsolt Kira

Despite the recent progress of fully-supervised action segmentation techniques, the performance is still not fully satisfactory. One main challenge is the problem of spatiotemporal variations (e.g. different people may perform the same activity in various ways)... (read more)

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Action Segmentation 50 Salads SSTDA [email protected]% 83.0 # 1
Edit 75.8 # 1
Acc 83.2 # 2
[email protected]% 81.5 # 1
[email protected]% 73.8 # 1
Action Segmentation Breakfast SSTDA [email protected]% 75.0 # 1
[email protected]% 55.2 # 1
Acc 70.2 # 1
Edit 73.7 # 1
[email protected]% 69.1 # 1
Action Segmentation GTEA SSTDA [email protected]% 90.0 # 1
[email protected]% 78.0 # 1
Acc 79.8 # 2
Edit 86.2 # 1
[email protected]% 89.1 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet