TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection

ICCV 2019 Kyle MinJason J. Corso

TASED-Net is a 3D fully-convolutional network architecture for video saliency detection. It consists of two building blocks: first, the encoder network extracts low-resolution spatiotemporal features from an input clip of several consecutive frames, and then the following prediction network decodes the encoded features spatially while aggregating all the temporal information... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.