Semantically coherent co-segmentation and reconstruction of dynamic scenes

A Mustafa, A Hilton - … of the IEEE Conference on Computer …, 2017‏ - openaccess.thecvf.com
In this paper we propose a framework for spatially and temporally coherent semantic co-
segmentation and reconstruction of complex dynamic scenes from multiple static or moving …

Hierarchical parsing net: Semantic scene parsing from global scene to objects

H Shi, H Li, F Meng, Q Wu, L Xu… - IEEE Transactions on …, 2018‏ - ieeexplore.ieee.org
This paper proposes a novel Hierarchical Parsing Net (HPN) for semantic scene parsing.
Unlike previous methods, which separately classify each object, HPN leverages global …

Jointly learning the attributes and composition of shots for boundary detection in videos

X Jiang, L **, A Rao, L Xu, D Lin - IEEE Transactions on …, 2021‏ - ieeexplore.ieee.org
In film making, shot has a profound influence on how the movie content is delivered and how
the audiences are echoed, where different emotions and contents can be delivered through …

Video object segmentation via global consistency aware query strategy

B Luo, H Li, F Meng, Q Wu… - IEEE Transactions on …, 2017‏ - ieeexplore.ieee.org
In this paper, we propose a video object segmentation method via global consistency aware
query strategy. The aim is to obtain higher segmentation accuracy with less user annotation …

Seeds-based part segmentation by seeds propagation and region convexity decomposition

F Meng, H Li, Q Wu, KN Ngan… - IEEE Transactions on …, 2017‏ - ieeexplore.ieee.org
Object part segmentation is an important and challenging task in computer vision. The
existing supervised part segmentation methods need pixel level training data which leads to …

Joint graph learning and video segmentation via multiple cues and topology calibration

J Song, L Gao, MM Puscas, F Nie, F Shen… - Proceedings of the 24th …, 2016‏ - dl.acm.org
Video segmentation has become an important and active research area with a large
diversity of proposed approaches. Graph-based methods, enabling top performance on …

Real-time hierarchical supervoxel segmentation via a minimum spanning tree

B Wang, Y Chen, W Liu, J Qin, Y Du… - IEEE Transactions on …, 2020‏ - ieeexplore.ieee.org
Supervoxel segmentation algorithm has been applied as a preprocessing step for many
vision tasks. However, existing supervoxel segmentation algorithms cannot generate …

4D Temporally Coherent Multi-Person Semantic Reconstruction and Segmentation

A Mustafa, C Russell, A Hilton - International journal of computer vision, 2022‏ - Springer
We introduce the first approach to solve the challenging problem of automatic 4D visual
scene understanding for complex dynamic scenes with multiple interacting people from multi …

Boosting scene parsing performance via reliable scale prediction

H Shi, H Li, Q Wu, F Meng, KN Ngan - Proceedings of the 26th ACM …, 2018‏ - dl.acm.org
Segmenting objects on suitable scales is a key factor to improve the scene parsing
performance. Existing methods either simply average multi-scale results or predict scales by …

Transductive video segmentation on tree-structured model

B Wang, Z Fu, H **ong, YF Zheng - IEEE Transactions on …, 2016‏ - ieeexplore.ieee.org
This paper presents a transductive multicomponent video segmentation algorithm, which is
capable of segmenting the predefined object of interest in the frames of a video sequence …