Deep learning technique for human parsing: A survey and outlook
Human parsing aims to partition humans in image or video into multiple pixel-level semantic
parts. In the last decade, it has gained significantly increased interest in the computer vision …
parts. In the last decade, it has gained significantly increased interest in the computer vision …
Capsule networks with residual pose routing
Capsule networks (CapsNets) have been known difficult to develop a deeper architecture,
which is desirable for high performance in the deep learning era, due to the complex …
which is desirable for high performance in the deep learning era, due to the complex …
A coarse-to-fine pattern parser for mitigating the issue of drastic imbalance in pixel distribution
Z Lin, X Jiang, Z Zheng - Pattern Recognition, 2024 - Elsevier
The significance of minute semantic components such as eyes and eyebrows tends to be
overshadowed by larger components like skin and background, leading to inadequate …
overshadowed by larger components like skin and background, leading to inadequate …
Graphics capsule: learning hierarchical 3D face representations from 2D images
The function of constructing the hierarchy of objects is important to the visual process of the
human brain. Previous studies have successfully adopted capsule networks to decompose …
human brain. Previous studies have successfully adopted capsule networks to decompose …
CtFPPN: A coarse-to-fine pattern parser for dealing with distribution imbalance of pixels
Z Lin, Y Wang, Z Zheng - Knowledge-Based Systems, 2023 - Elsevier
Unbalanced pixel distribution has always plagued pattern parsing tasks. The consequence
of this is that the saliency of tiny semantic components is overshadowed by large …
of this is that the saliency of tiny semantic components is overshadowed by large …
Spatiotemporal Orthogonal Projection Capsule Network for Incremental Few-Shot Action Recognition
In this paper, we propose a new task named incremental few-shot action recognition
(IFSAR), which aims to learn new action classes incrementally with limited samples. Existing …
(IFSAR), which aims to learn new action classes incrementally with limited samples. Existing …
Spatial-temporal exclusive capsule network for open set action recognition
Open set action recognition (OSAR) is a rising research domain that simultaneously
identifies all videos from known classes and rejects videos from unknown classes. Existing …
identifies all videos from known classes and rejects videos from unknown classes. Existing …
Hybrid Gromov–Wasserstein Embedding for Capsule Learning
Capsule networks (CapsNets) aim to parse images into a hierarchy of objects, parts, and
their relationships using a two-step process involving part–whole transformation and …
their relationships using a two-step process involving part–whole transformation and …
Unsupervised Part Discovery via Dual Representation Alignment
Object parts serve as crucial intermediate representations in various downstream tasks, but
part-level representation learning still has not received as much attention as other vision …
part-level representation learning still has not received as much attention as other vision …
Reducing vulnerable internal feature correlations to enhance efficient topological structure parsing
Z Lin, Z Zheng, J Jia, W Gao - Expert Systems with Applications, 2024 - Elsevier
Most cropping-and-segmenting pattern parsers typically establish a single metric/scheme to
reason diverse inner correlations, resulting in over-general and redundant representations …
reason diverse inner correlations, resulting in over-general and redundant representations …