Browse SoTA > Computer Vision > Saliency Prediction

# Saliency Prediction Edit

37 papers with code · Computer Vision

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

# Saliency Prediction with External Knowledge

27 Jul 2020

At the core of the method is a new Graph Semantic Saliency Network (GraSSNet) that constructs a graph that encodes semantic relationships learned from external knowledge.

# Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains

24 Jul 2020

Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification.

# $n$-Reference Transfer Learning for Saliency Prediction

9 Jul 2020

The proposed framework is gradient-based and model-agnostic.

# ITSELF: Iterative Saliency Estimation fLexible Framework

30 Jun 2020

We compare ITSELF to two state-of-the-art saliency estimators on five metrics and six datasets, four of which are composed of natural-images, and two of biomedical-images.

# Revisiting Saliency Metrics: Farthest-Neighbor Area Under Curve

In this paper, we propose a new metric to address the long-standing problem of center bias in saliency evaluation.

# Select, Supplement and Focus for RGB-D Saliency Detection

Depth data containing a preponderance of discriminative power in location have been proven beneficial for accurate saliency prediction.

# STAViS: Spatio-Temporal AudioVisual Saliency Network

We introduce STAViS, a spatio-temporal audiovisual saliency network that combines spatio-temporal visual and auditory information in order to efficiently address the problem of saliency estimation in videos.

# "Looking at the Right Stuff" - Guided Semantic-Gaze for Autonomous Driving

In recent years, predicting driver's focus of attention has been a very active area of research in the autonomous driving community.

# Distilling Localization for Self-Supervised Representation Learning

14 Apr 2020

For high-level visual recognition, self-supervised learning defines and makes use of proxy tasks such as colorization and visual tracking to learn a semantic representation useful for distinguishing objects.

# Self-supervised Representation Learning for Ultrasound Video

28 Feb 2020

Therefore, there is significant interest in learning representations from unlabelled raw data.