The prevalence of domain adaptive semantic segmentation has prompted con...
Unsupervised domain adaptation (DA) with the aid of pseudo labeling
tech...
Achieving a reliable LiDAR-based object detector in autonomous driving i...
Zero-shot learning is a learning regime that recognizes unseen classes b...
A typical multi-source domain adaptation (MSDA) approach aims to transfe...
Generalized Zero-Shot Learning (GZSL) aims to recognize images from both...
Open-set domain adaptation (OSDA) has gained considerable attention in m...
With the rapid development of intelligent detection algorithms based on ...
With the advent of media streaming, video action recognition has become
...
Domain generalization (DG) aims to generalize a model trained on multipl...
Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic...
Image captioning model is a cross-modality knowledge discovery task, whi...
Signed link prediction in social networks aims to reveal the underlying
...
Domain adaptation techniques, which focus on adapting models between
dis...
Domain shift is a fundamental problem in visual recognition which typica...
With the rapid advancement of image captioning and visual question answe...
Meta-learning for few-shot learning allows a machine to leverage previou...
Existing deep hashing approaches fail to fully explore semantic correlat...
Existing methods using generative adversarial approaches for Zero-Shot
L...
Visual paragraph generation aims to automatically describe a given image...
With the increasing number of online stores, there is a pressing need fo...
Extremely low bit (e.g., 4-bit) hashing is in high demand for retrieval ...
Rich high-quality annotated data is critical for semantic segmentation
l...
The query-by-image video retrieval (QBIVR) task has been attracting
cons...
Hashing has shown its efficiency and effectiveness in facilitating
large...