No abstract

A large body of previous models to predict where people look in natural scenes focused on pixel-level image attributes. To bridge the semantic gap between the predictive power of computational saliency models and human behavior, we propose a new saliency architecture that incorporates information at three layers: pixel-level image attributes, object-level attributes, and semantic-level attributes. Object- and semantic-level information is frequently ignored, or only a few sample object categories are discussed where scaling to a large number of object categories is not feasible nor neurally plausible. To address this problem, this work constructs a principled vocabulary of basic attributes to describe object- and semantic-level information thus not restricting to a limited number of object categories. We build a new dataset of 700 images with eye-tracking data of 15 viewers and annotation data of 5,551 segmented objects with fine contours and 12 semantic attributes (publicly available with the paper). Experimental results demonstrate the importance of the object- and semantic-level information in the prediction of visual attention.

Summary The social difficulties that are a hallmark of autism spectrum disorder (ASD) are thought to arise, at least in part, from atypical attention towards stimuli and their features. To investigate this hypothesis comprehensively, we characterized 700 complex natural scene images with a novel 3-layered saliency model that incorporated pixel-level (e.g., contrast), object-level (e.g., shape), and semantic-level attributes (e.g., faces) on 5551 annotated objects. Compared to matched controls, people with ASD had a stronger image center bias regardless of object distribution, reduced saliency for faces and for locations indicated by social gaze, yet a general increase in pixel-level saliency at the expense of semantic-level saliency. These results were further corroborated by direct analysis of fixation characteristics and investigation of feature interactions. Our results for the first time quantify atypical visual attention in ASD across multiple levels and categories of objects.

Instance-level human analysis is common in real-life scenarios and has multiple manifestations, such as human part segmentation, dense pose estimation, human-object interactions, etc. Models need to distinguish different human instances in the image panel and learn rich features to represent the details of each instance. In this paper, we present an end-to-end pipeline for solving the instance-level human analysis, named Parsing R-CNN. It processes a set of human instances simultaneously through comprehensive considering the characteristics of region-based approach and the appearance of a human, thus allowing representing the details of instances.Parsing R-CNN is very flexible and efficient, which is applicable to many issues in human instance analysis. Our approach outperforms all state-of-the-art methods on CIHP (Crowd Instance-level Human Parsing), MHP v2.0 (Multi-Human Parsing) and DensePose-COCO datasets. Based on the proposed Parsing R-CNN, we reach the 1st place in the COCO 2018 Challenge DensePose Estimation task. Code and models are public available 1 .

No abstract