SlowFast Networks for Video Recognition

ICCV 2019 Christoph FeichtenhoferHaoqi FanJitendra MalikKaiming He

We present SlowFast networks for video recognition. Our model involves (i) a Slow pathway, operating at low frame rate, to capture spatial semantics, and (ii) a Fast pathway, operating at high frame rate, to capture motion at fine temporal resolution... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Action Recognition In Videos AVA v2.1 SlowFast mAP (Val) 28.2 # 1
Action Classification Charades SlowFast MAP 45.2 # 2
Action Classification Kinetics-400 SlowFast, R101 + NL Accuracy 79.8 # 3
Action Recognition In Videos Kinetics-400 SlowFast+NL Video [email protected] 79.8 # 2
Video [email protected] 93.9 # 2
Action Recognition In Videos Kinetics-400 SlowFast Video [email protected] 78.9 # 3
Video [email protected] 93.5 # 3

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