• Home
  • Search
  • Joint Graph Learning and Video Segmentation via Multiple Cues and Topology Calibration
  • Cite Icon21
  • https://doi.org/10.1145/2964284.2964295Copy DOI Icon

Joint Graph Learning and Video Segmentation via Multiple Cues and Topology Calibration

  • Oct 1, 2016
  • Jingkuan Song +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Video segmentation has become an important and active research area with a large diversity of proposed approaches. Graph-based methods, enabling top performance on recent benchmarks, usually focus on either obtaining a precise similarity graph or designing efficient graph cutting strategies. However, these two components are often conducted in two separated steps, and thus the obtained similarity graph may not be the optimal one for segmentation and this may lead to suboptimal results. In this paper, we propose a novel framework, joint graph learning and video segmentation (JGLVS)}, which learns the similarity graph and video segmentation simultaneously. JGLVS learns the similarity graph by assigning adaptive neighbors for each vertex based on multiple cues (appearance, motion, boundary and spatial information). Meanwhile, the new rank constraint is imposed to the Laplacian matrix of the similarity graph, such that the connected components in the resulted similarity graph are exactly equal to the number of segmentations. Furthermore, JGLVS can automatically weigh multiple cues and calibrate the pairwise distance of superpixels based on their topology structures. Most noticeably, empirical results on the challenging dataset VSB100 show that JGLVS achieves promising performance on the benchmark dataset which outperforms the state-of-the-art by up to 11% for the BPR metric.

Similar Papers
  • Conference Article
  • Citations148

Object based segmentation of video using color, motion and spatial information

  • Dec 01, 2001
  • S Khan +1
  • Research Article
  • Citations90

Referring Segmentation in Images and Videos With Cross-Modal Self-Attention Network.

  • Jan 01, 2021
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Linwei Ye +4
  • Research Article
  • Citations5

Object proposals for salient object segmentation in videos

  • Jun 24, 2019
  • Multimedia Tools and Applications
  • Rahma Kalboussi +4
  • Research Article
  • Citations46

Multi-view spectral clustering by simultaneous consensus graph learning and discretization

  • Oct 22, 2021
  • Knowledge-Based Systems
  • Guo Zhong +3
  • Research Article
  • Citations9

Self-Weighted Graph-Based Framework for Multi-View Clustering

  • Jan 01, 2023
  • IEEE Access
  • Yanfang He +1
  • Research Article
  • Citations29

A new method to build the adaptive k-nearest neighbors similarity graph matrix for spectral clustering

  • Apr 06, 2022
  • Neurocomputing
  • Yongda Cai +2
  • Research Article
  • Citations27

A semi-supervised heat kernel pagerank MBO algorithm for data classification

  • Jan 01, 2018
  • Communications in Mathematical Sciences
  • Ekaterina Merkurjev +2
  • Research Article
  • Citations31

Foreground Segmentation in Videos Combining General Gaussian Mixture Modeling and Spatial Information

  • Jun 01, 2018
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Aissa Boulmerka +1
  • Research Article

Multi‐View Clustering Based on Intra‐View Heterogeneity and Inter‐View Compatibility

  • Dec 17, 2025
  • Concurrency and Computation: Practice and Experience
  • Zhangshu Xiao +3
  • Research Article
  • Citations5

Label propagation via local geometry preserving for deep semi-supervised image recognition

  • Jun 08, 2021
  • Neural Networks
  • Yuanyuan Qing +2
  • Research Article

Clustering by Mining Density Distributions and Splitting Manifold Structure

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zhichang Xu +2
  • Research Article
  • Citations8

Motion and Appearance Nonparametric Joint Entropy for Video Segmentation

  • Jan 19, 2008
  • International Journal of Computer Vision
  • Sylvain Boltz +4
  • Research Article
  • Citations14

Unsupervised Action Segmentation via Fast Learning of Semantically Consistent Actoms

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Zheng Xing +1
  • Research Article

FC$^{2}$2: Fast Co-Clustering With Small-Scale Similarity Graph and Bipartite Graph Learning.

  • Jan 01, 2026
  • IEEE transactions on pattern analysis and machine intelligence
  • Xiaowei Zhao +4
  • Conference Article

Spatial-Temporal Pyramid Matching for Crowd Scene Analysis

  • Dec 02, 2014
  • Hanhe Lin +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.