Predcnn: Predictive learning with cascade convolutions

Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18} 2018 Ziru XuYunbo WangMingsheng LongJianmin Wang

Predicting future frames in videos remains an unsolved but challenging problem. Mainstream recurrent models suffer from huge memory usage and computation cost, while convolutional models are unable to effectively capture the temporal dependencies between consecutive video frames... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Pose Prediction Filtered NTU RGB+D PredCNN MSE 0.1665 # 3
MAE 1.6394 # 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