How best to evaluate a saliency model's ability to predict where humans look in images is an
open research question. The choice of evaluation metric depends on how saliency is …

In this paper, we tackle the challenging task of unsupervised salient object detection (SOD)
by leveraging spectral clustering on self-supervised features. We make the following …

This paper addresses the problem of pixel-level segmentation and classification of scene
images with an entirely learning-based approach using Long Short Term Memory (LSTM) …

Existing saliency detection approaches use images as inputs and are sensitive to
foreground/background similarities, complex background textures, and occlusions. We …

We present a novel spatiotemporal saliency detection method to estimate salient regions in
videos based on the gradient flow field and energy optimization. The proposed gradient flow …

Abstract Content-Aware Image Retargeting (CAIR) techniques are important in multimedia
applications for displaying images on various display devices. This paper first provides a …

We propose a new type of saliency—context-aware saliency—which aims at detecting the
image regions that represent the scene. This definition differs from previous definitions …

This paper presents interactive image editing tools using a new randomized algorithm for
quickly finding approximate nearestneighbor matches between image patches. Previous …

For many applications in graphics, design, and human computer interaction, it is essential to
understand where humans look in a scene. Where eye tracking devices are not a viable …

We describe a technique that transforms a video from a hand-held video camera so that it
appears as if it were taken with a directed camera motion. Our method adjusts the video to …