Search Results for author:
Found 9 papers, 4 papers with code
Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer
First, a subdivision strategy is introduced to produce a collection of regional prototypes from the foreground of the support prototype.
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion.
Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentation
In this work, we present an approach to extract multiple representative sub-regions from a given support medical image, enabling fine-grained selection over the generated image regions.
Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation
Most generative ZSL methods use category semantic attributes plus a Gaussian noise to generate visual features.
SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting
To obtain the appropriate crowd representation, in this work we proposed SOFA-Net(Second-Order and First-order Attention Network): second-order statistics were extracted to retain selectivity of the channel-wise spatial information for dense heads while first-order statistics, which can enhance the feature discrimination for the heads' areas, were used as complementary information.
Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization
In this article, we propose a novel invariant deep compressible covariance pooling (IDCCP) to solve nuisance variations in aerial scene categorization.
LSTA-Net: Long short-term Spatio-Temporal Aggregation Network for Skeleton-based Action Recognition
We devise our model into a pure factorised architecture which can alternately perform spatial feature aggregation and temporal feature aggregation.
Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition
In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions.
Mutual Balancing in State-Object Components for Compositional Zero-Shot Learning
Compositional Zero-Shot Learning (CZSL) aims to recognize unseen compositions from seen states and objects.
