computer-vision

Video Saliency Detection

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in video-saliency-detection

Trend

Dataset

Best Model

Actions

MSU Video Saliency Prediction

DHF1K

DIEM

Libraries

i

Use these libraries to find video-saliency-detection models and implementations

Datasets

DHF1K

MSU Video Saliency Prediction

Subtasks

No subtasks available.

Most implemented papers

Contextual Encoder-Decoder Network for Visual Saliency Prediction

Alexander Kroner, M. Senden, K. Driessens, R. Goebel•Sun Feb 17 2019

This work proposes an approach based on a convolutional neural network pre-trained on a large-scale image classification task that achieves competitive and consistent results across multiple evaluation metrics on two public saliency benchmarks and demonstrates the effectiveness of the suggested approach on five datasets and selected examples.

210

Content

DIEM

Hollywood2

UCFSports

0

Paper Graph

Simple vs complex temporal recurrences for video saliency prediction

Kevin McGuinness, N. O’Connor, Panagiotis Linardos, Eva Mohedano, J. Nieto, Xavier Giro-i-Nieto•Tue Jul 02 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 using a ConvLSTM and a conceptually simple exponential moving average of an internal convolutional state.

98 0

Paper Graph

Revisiting Video Saliency: A Large-Scale Benchmark and a New Model

Jianbing Shen, Ming-Ming Cheng, A. Borji, Wenguan Wang, Fang Guo•Mon Jan 22 2018

This work introduces a new benchmark for predicting human eye movements during dynamic scene free-viewing, and proposes a novel video saliency model that augments the CNN-LSTM network architecture with an attention mechanism to enable fast, end-to-end saliency learning.

287 0

Paper Graph

Unified Image and Video Saliency Modeling

Richard Droste, Jianbo Jiao, J. Noble•Tue Mar 10 2020

UNISAL achieves state-of-the-art performance on all video saliency datasets and is on par with the state of theart for image Saliency datasets, despite faster runtime and a 5 to 20-fold smaller model size compared to all competing deep methods.

179 0

Paper Graph

Deep Learning Approach for Human Action Recognition Using a Time Saliency Map Based on Motion Features Considering Camera Movement and Shot in Video Image Sequences

José J. M. Machado, A. A. Gharahbagh, Vahid Hajihashemi, J. M. R. S. Tavares•Tue Nov 14 2023

The proposed hierarchical method for action recognition based on temporal and spatial features segments salient objects based on motion, edges, and colour features and can be added as a preprocessing step to most current HAR systems to improve performance.

9 0

Paper Graph

A Dilated Inception Network for Visual Saliency Prediction

Weisi Lin, Sheng Yang, Guosheng Lin, Qiuping Jiang•Sat Apr 06 2019

This work proposes an end-to-end dilated inception network (DINet) for visual saliency prediction that captures multi-scale contextual features effectively with very limited extra parameters and improves the performance of the saliency model by using a set of linear normalization-based probability distribution distance metrics as loss functions.

138 0

Paper Graph

TASED-Net: Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection

Jason J. Corso, Kyle Min•Wed Aug 14 2019

TASED-Net significantly outperforms previous state-of-the-art approaches on all three major large-scale datasets of video saliency detection: DHF1K, Hollywood2, and UCFSports and is especially better at attending to salient moving objects.

177 0

Paper Graph

Video Saliency Prediction Using Enhanced Spatiotemporal Alignment Network

Bo Liu, Kaihua Zhang, Jin Chen, Huihui Song, Qingshan Liu•Wed Jan 01 2020

An effective spatiotemporal feature alignment network tailored to VSP is developed, mainly including two key sub-networks: a multi-scale deformable convolutional alignment network (MDAN) and a bidirectional convolutionsal Long Short-Term Memory (Bi-ConvLSTM) network.

41 0

Paper Graph

A Plug-and-Play Scheme to Adapt Image Saliency Deep Model for Video Data

Shuai Li, Chenglizhao Chen, A. Hao, Hong Qin, Yunxiao Li•Sat Aug 01 2020

This paper proposes a novel plug-and-play scheme to weakly retrain a pretrained image saliency deep model for video data by using the newly sensed and coded temporal information, which will be able to maintain temporal saliency awareness, achieving much improved detection performance.

34 0

Paper Graph

Exploring Rich and Efficient Spatial Temporal Interactions for Real-Time Video Salient Object Detection

Dingwen Zhang, Yuming Fang, Chenglizhao Chen, Hong Qin, Guotao Wang, Chong Peng•Thu Aug 06 2020

A novel spatiotemporal network is advocated, where the key innovation is the design of its temporal unit, which fully enables the computation of temporal saliency cues that interact with their spatial counterparts, ultimately boosting the overall VSOD performance and realizing its full potential towards mutual performance improvement for each.

115 0

Paper Graph

Adding a benchmark result helps the community track progress.