Semantic Segmentation with

By Second-Order Pooling, Rui Caseiro, Jorge P. Batista, Cristian Sminchisescu. 2012

269 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks (2019, background): “The ﬁrst branch of 3D-convolutional neural networks uses a rectangular grid and a dense representation [30, 5] where the empty space is represented either as 0 or the signed distance function.”
The ApolloScape Open Dataset for Autonomous Driving and Its Application (2018, methodology): “In our current version released online [19], [20], we have 143,906 video frames and their corresponding pixel-level semantic labelling, from which 89,430 images contain instance-level annotations where movable objects are further separated.”
A High Performance CRF Model for Clothes Parsing (2014, methodology): “In particular, we use eSIFT and eMSIFT proposed by [27] for region description.”
FSDR: Frequency Space Domain Randomization for Domain Generalization (2021, background): “One way of circumventing this constraint is to employ synthetic images with automatically generated labels [47, 46] in network training.”
Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection (2016, methodology): “The strongest competitors are INRIA (89.5%, Maggiori et al., 2016), using a variant of fcn, and ONERA (89.8%, Audebert et al., 2016), with a variant of segnet.”
Survey on semantic segmentation using deep learning techniques (2019, methodology): “The earlier approaches used for semantic segmentation were textonforest [12], random-forest based classiﬁers [13], whereas deep learning techniques allowed precise and much faster segmentation [14].”