Temporal Convolutional Networks for Action Segmentation and Detection

The ability to identify and temporally segment fine-grained human actions throughout a video is crucial for robotics, surveillance, education, and beyond. Typical approaches decouple this problem by first extracting local spatiotemporal features from video frames and then feeding them into a temporal classifier that captures high-level temporal patterns... (read more)

PDF Abstract CVPR 2017 PDF CVPR 2017 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Action Segmentation GTEA ED-TCN [email protected]% 72.2 # 6
[email protected]% 56.0 # 6
Acc 64.0 # 6
Edit - # 6
[email protected]% 69.3 # 6
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton TCN Accuracy (CS) 56% # 6
Accuracy (CV I) 16% # 4
Accuracy (CV II) 43% # 5
Accuracy (AV I) 43% # 4
Accuracy (AV II) 64% # 4

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