About

Video salient object detection (VSOD) is significantly essential for understanding the underlying mechanism behind HVS during free-viewing in general and instrumental to a wide range of real-world applications, e.g., video segmentation, video captioning, video compression, autonomous driving, robotic interaction, weakly supervised attention. Besides its academic value and practical significance, VSOD presents great difficulties due to the challenges carried by video data (diverse motion patterns, occlusions, blur, large object deformations, etc.) and the inherent complexity of human visual attention behavior (i.e., selective attention allocation, attention shift) during dynamic scenes. Online benchmark: http://dpfan.net/davsod.

( Image credit: Shifting More Attention to Video Salient Object Detection, CVPR2019-Best Paper Finalist )

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Datasets

Greatest papers with code

Shifting More Attention to Video Salient Object Detection

CVPR 2019 DengPingFan/DAVSOD

This is the first work that explicitly emphasizes the challenge of saliency shift, i. e., the video salient object(s) may dynamically change.

 Ranked #1 on Video Salient Object Detection on FBMS-59 (using extra training data)

SALIENT OBJECT DETECTION VIDEO SALIENT OBJECT DETECTION

Motion Guided Attention for Video Salient Object Detection

ICCV 2019 lhaof/Motion-Guided-Attention

In this paper, we develop a multi-task motion guided video salient object detection network, which learns to accomplish two sub-tasks using two sub-networks, one sub-network for salient object detection in still images and the other for motion saliency detection in optical flow images.

OPTICAL FLOW ESTIMATION SALIENCY DETECTION SALIENT OBJECT DETECTION VIDEO SALIENT OBJECT DETECTION

Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection

ECCV 2018 shenjianbing/PDB-ConvLSTM

This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM).

 Ranked #1 on Video Salient Object Detection on UVSD (using extra training data)

SALIENT OBJECT DETECTION SEMANTIC SEGMENTATION UNSUPERVISED VIDEO OBJECT SEGMENTATION VIDEO SALIENT OBJECT DETECTION VIDEO SEMANTIC SEGMENTATION

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

ICCV 2019 Kinpzz/RCRNet-Pytorch

Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module.

 Ranked #1 on Video Salient Object Detection on VOS-T (using extra training data)

SALIENT OBJECT DETECTION UNSUPERVISED VIDEO OBJECT SEGMENTATION VIDEO SALIENT OBJECT DETECTION

Saliency-Aware Geodesic Video Object Segmentation

CVPR 2015 shenjianbing/videoseg15

Building on the observation that foreground areas are surrounded by the regions with high spatiotemporal edge values, geodesic distance provides an initial estimation for foreground and background.

Ranked #4 on Video Salient Object Detection on DAVSOD-Difficult20 (using extra training data)

SEMANTIC SEGMENTATION VIDEO SALIENT OBJECT DETECTION VIDEO SEMANTIC SEGMENTATION

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

7 Aug 2020guotaowang/STVS

In this way, even though the overall video saliency quality is heavily dependent on its spatial branch, however, the performance of the temporal branch still matter.

SALIENT OBJECT DETECTION VIDEO SALIENCY DETECTION VIDEO SALIENT OBJECT DETECTION

DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detection

9 Dec 2020TJUMMG/DS-Net

In this paper, we investigate the complimentary roles of spatial and temporal information and propose a novel dynamic spatiotemporal network (DS-Net) for more effective fusion of spatiotemporal information.

OPTICAL FLOW ESTIMATION SALIENCY DETECTION SALIENT OBJECT DETECTION VIDEO SALIENT OBJECT DETECTION

Weakly Supervised Video Salient Object Detection

6 Apr 2021wangbo-zhao/WSVSOD

Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain.

SALIENT OBJECT DETECTION VIDEO SALIENCY DETECTION VIDEO SALIENT OBJECT DETECTION

A Novel Video Salient Object Detection Method via Semi-supervised Motion Quality Perception

7 Aug 2020qduOliver/MQP

Consequently, we can achieve a significant performance improvement by using this new training set to start a new round of network training.

SALIENT OBJECT DETECTION VIDEO SALIENT OBJECT DETECTION