We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of
semantic segmentation. Unlike the conventional model cascade (MC) that is composed of …

We investigate a novel approach for image restoration by reinforcement learning. Unlike
existing studies that mostly train a single large network for a specialized task, we prepare a …

This paper presents a novel relational network for group activity recognition. The core of our
network is to augment the conditional random fields (CRF), amenable to learning inter …

Semantically labeling every pixel in a video is a very challenging task as video is an
information-intensive media with complex spatio-temporal dependence. We present in this …

In this work, we study a poorly understood trade-off between accuracy and runtime costs for
deep semantic video segmentation. While recent work has demonstrated advantages of …

This paper presents a new relational network for group activity recognition. The essence of
the network is to integrate conditional random fields (CRFs) with self-attention to infer the …

Anytime inference requires a model to make a progression of predictions which might be
halted at any time. Prior research on anytime visual recognition has mostly focused on …

In background subtraction tasks, spatial and temporal contexts are beneficial in detecting
moving objects. The methods based on Deep Neural Networks in this task has explored …

Abstract Semantic segmentation with Convolutional Neural Networks is a memory-intensive
task due to the high spatial resolution of feature maps and output predictions. In this paper …

Background subtraction is an important task in computer vision. Traditional approaches
usually utilize low-level visual features like color, texture, or edge to build background …