Video Classification with Channel-Separated Convolutional Networks

Group convolution has been shown to offer great computational savings in various 2D convolutional architectures for image classification. It is natural to ask: 1) if group convolution can help to alleviate the high computational cost of video classification networks; 2) what factors matter the most in 3D group convolutional networks; and 3) what are good computation/accuracy trade-offs with 3D group convolutional networks... (read more)

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Action Classification Kinetics-400 ip-CSN-152 (Sports-1M pretraining) Accuracy 79.2 # 4
Action Recognition Kinetics-400 ir-CSN-152 (Sports-1M pretraining) Video [email protected] 78.5 # 4
Video [email protected] 93.4 # 4
Action Recognition Something-Something V1 ir-CSN-101 Top 1 Accuracy 48.4 # 24
Action Recognition Something-Something V1 ir-CSN-152 Top 1 Accuracy 49.3 # 21
Action Recognition Sports-1M ir-CSN-152 Video [email protected] 75.5 # 1
Video [email protected] 92.7 # 1

Methods used in the Paper