Luc Van Gool

TL;DR: A new deep architecture for actionness estimation is presented, called hybrid fully convolutional network (HFCN), which is composed of appearance FCN (A-FCN) and motionFCN (M-FCNs), which leverage the strong capacity of deep models to estimate actionness maps from the perspectives of static appearance and dynamic motion.

TL;DR: This work presents a data-driven, unsupervised method for unusual scene detection from static webcams, based on simple image features that detects plausible unusual scenes, which have not been observed in the data-stream before.

TL;DR: The proposed feature detection algorithm leads to an outstanding scale-invariant feature detection quality, albeit at reduced planar rotational invariance, and is scalable with the filter order, providing many quality-complexity trade-off working points.

TL;DR: The in t gration of color distributions into particle filtering, which has typically been used in combination with edge-base d image features, is presented.

TL;DR: Zhang et al. as discussed by the authors presented the first comprehensive study and analysis of the usefulness of super-resolution for other vision applications, including edge detection, semantic image segmentation, digit recognition, and scene recognition.