Saliency Prediction

85 papers with code • 3 benchmarks • 7 datasets

A saliency map is a model that predicts eye fixations on a visual scene. Saliency prediction is informed by the human visual attention mechanism and predicts the possibility of the human eyes to stay in a certain position in the scene.

Libraries

Use these libraries to find Saliency Prediction models and implementations

Most implemented papers

Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model

marcellacornia/sam 29 Nov 2016

Data-driven saliency has recently gained a lot of attention thanks to the use of Convolutional Neural Networks for predicting gaze fixations.

Beyond saliency: understanding convolutional neural networks from saliency prediction on layer-wise relevance propagation

Hey1Li/Salient-Relevance-Propagation 22 Dec 2017

In this paper, we propose a novel two-step understanding method, namely Salient Relevance (SR) map, which aims to shed light on how deep CNNs recognize images and learn features from areas, referred to as attention areas, therein.

Faster gaze prediction with dense networks and Fisher pruning

the-super-toys/glimpse-models Twitter 2018

Predicting human fixations from images has recently seen large improvements by leveraging deep representations which were pretrained for object recognition.

Predicting Gaze in Egocentric Video by Learning Task-dependent Attention Transition

hyf015/egocentric-gaze-prediction ECCV 2018

We present a new computational model for gaze prediction in egocentric videos by exploring patterns in temporal shift of gaze fixations (attention transition) that are dependent on egocentric manipulation tasks.

Understanding Humans in Crowded Scenes: Deep Nested Adversarial Learning and A New Benchmark for Multi-Human Parsing

open-mmlab/mmpose 10 Apr 2018

Despite the noticeable progress in perceptual tasks like detection, instance segmentation and human parsing, computers still perform unsatisfactorily on visually understanding humans in crowded scenes, such as group behavior analysis, person re-identification and autonomous driving, etc.

Temporal Saliency Adaptation in Egocentric Videos

imatge-upc/saliency-2018-videosalgan 28 Aug 2018

This work adapts a deep neural model for image saliency prediction to the temporal domain of egocentric video.

A Neurodynamic model of Saliency prediction in V1

dberga/NSWAM 15 Nov 2018

Lateral connections in the primary visual cortex (V1) have long been hypothesized to be responsible of several visual processing mechanisms such as brightness induction, chromatic induction, visual discomfort and bottom-up visual attention (also named saliency).

PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection

nian-liu/PiCANet 15 Dec 2018

We propose three specific formulations of the PiCANet via embedding the pixel-wise contextual attention mechanism into the pooling and convolution operations with attending to global or local contexts.

DAVE: A Deep Audio-Visual Embedding for Dynamic Saliency Prediction

hrtavakoli/DAVE 25 May 2019

Our results suggest that (1) audio is a strong contributing cue for saliency prediction, (2) salient visible sound-source is the natural cause of the superiority of our Audio-Visual model, (3) richer feature representations for the input space leads to more powerful predictions even in absence of more sophisticated saliency decoders, and (4) Audio-Visual model improves over 53. 54\% of the frames predicted by the best Visual model (our baseline).

Simple vs complex temporal recurrences for video saliency prediction

imatge-upc/SalEMA 3 Jul 2019

This paper investigates modifying an existing neural network architecture for static saliency prediction using two types of recurrences that integrate information from the temporal domain.