ECCV 2018 Tutorial on

Visual Recognition and Beyond

Location: Room N1179 (TUM map, google maps)
Munich, Germany
Sep 8th, 2018



This tutorial covers topics at the frontier of research on visual recognition. The talks cover methods and principles behind image classification, object detection, instance segmentation, semantic segmentation, panoptic segmentation and dense pose estimation.


14:00 - 14:45 . Learning Deep Representations for Visual Recognition by Kaiming He (slides)

14:45 - 15:30 . The Generalized R-CNN Framework for Object Detection by Ross Girshick (slides)

15:30 - 16:15 . Panoptic Segmentation: Unifying Semantic and Instance Segmentations by Alexander Kirillov (slides)

16:15 - 16:45 . Coffee Break.

16:45 - 17:30 . Deep Insights into Convolutional Networks for Video Recognition by Christoph Feicthenhofer (slides)

17:30 - 18:15 . DensePose: Learning Dense Correspondences in the Wild by Natalia Neverova (slides)

Contact: Georgia Gkioxari