… a novel algorithm for interactive object selection (Fig. 1). To select an object in an image, users
… • We propose an effective transformation to incorporate user interaction with current deep …

Existing deep learning based interactive segmentation methods have achieved remarkable
performance with only a few user clicks, eg DEXTR attaining 91.5% IoU on PASCAL VOC …

… Interactive object cutout tools are the cornerstone of the image editing workflow. … Recent
deep-learning based interactive segmentation algorithms are capable of rough binary selections …

… We argue that both the visual interface and model structure of deep learning systems need
to take into account interaction design. We propose a framework of collaborative semantic …

… We evaluate both our performance as an interactive selection tool on the GrabCut dataset
[19] as well as our performance segmenting objects from detections on the SBD dataset [20]. …

… of joint active search of multiple objects. In order to exploit beneficial contextual information
among differnt objects, we present collaborative multi-agent deep RL. We instantiate our …

… We implemented other deep learning methods but due to space limitation, we only report
results of the most accurate one which is the fully convolutional network (FCN) [24] in this letter. …

… sensorimotor data while a robot interacts with objects, and allow the robot to … deep
neural networks (DNN) model that learns to recognize object characteristics, acquires tool–object…

… • We propose a click-based deep interactive image matting (DIIM) approach that are versatile
and user-friendly. • We propose a spatial recurrent alpha feature propagation and a full-…

… Deep interactive segmentation addresses this trade-off between high-quality segmentation
and laborious manual annotation. The idea is to boost annotation efficiency by incorporating …