Few-shot object detection (FSOD) identifies objects from extremely few
a...
The challenge in fine-grained visual categorization lies in how to explo...
In recent years, graph neural networks (GNN) have achieved significant
d...
Zero-shot learning (ZSL) aims to recognize the novel classes which canno...
Fine-grained visual categorization (FGVC) is a challenging task due to
s...
Data is the foundation for the development of computer vision, and the
e...
With the fast development of AI-related techniques, the applications of
...
Graph neural networks (GNNs) with missing node features have recently
re...
Hashing that projects data into binary codes has shown extraordinary tal...
Zero-shot cross-modal retrieval (ZS-CMR) deals with the retrieval proble...
Clustering attempts to partition data instances into several distinctive...
Fine-grained visual categorization (FGVC) aims to discriminate similar
s...
The key challenge of zero-shot learning (ZSL) is how to infer the latent...
Trajectory prediction aims to predict the movement trend of the agents l...
Zero-shot learning (ZSL) tackles the novel class recognition problem by
...
Learning to understand and predict future motions or behaviors for agent...
Generalized zero-shot learning (GZSL) has achieved significant progress,...
It is essential but challenging to predict future trajectories of variou...
As a promising step, the performance of data analysis and feature learni...
Visual images usually contain the informative context of the environment...
Generative adversarial networks (GANs) have been a popular deep generati...
Low-rank Multi-view Subspace Learning (LMvSL) has shown great potential ...
It remains challenging to automatically predict the multi-agent trajecto...
Dynamic texture (DT) exhibits statistical stationarity in the spatial do...
Weakly-supervised semantic segmentation aims to assign each pixel a sema...
High angular resolution diffusion imaging (HARDI) demands a lager amount...
It remains challenging to automatically segment kidneys in clinical
ultr...
It remains a huge challenge to design effective and efficient trackers u...
It remains challenging to automatically segment kidneys in clinical
ultr...
Fine-grained visual recognition is challenging because it highly relies ...
Despite the great potential of using the low-rank matrix recovery (LRMR)...
Cross-view classification that means to classify samples from heterogene...
We present a novel cross-view classification algorithm where the gallery...