SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.02391 · CVPR · 2021

Weakly Supervised Video Salient Object Detection

Jing Zhang, Nick Barnes, Nian Liu, Junwei Han, Wangbo Zhao, Long Li

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are timeconsuming and expensive to obtain. To relieve the burden of data annotation, we present the first weakly supervised video salient object detection model based on relabeled "fixation guided scribble annotations". Specifically, an "Appearance-motion fusion module" and bidirectional ConvLSTM based framework are proposed to achieve effective multi-modal learning and long-term temporal context modeling based on our new weak annotations. Further, we design a novel foreground-background similarity loss to further explore the labeling similarity across frames. A weak annotation boosting strategy is also introduced to boost our model performance with a new pseudo-label generation technique. Extensive experimental results on six benchmark video saliency detection datasets illustrate the effectiveness of our solution 1 .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.02391")
get_code_for_paper("2104.02391")
have("2104.02391")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.02391.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.02391.svg)](https://syntology.ai/paper/2104.02391)

Connect an agent — have() is free.