Mrn: Multiplexed routing network for incremental multilingual text recognition
Multilingual text recognition (MLTR) systems typically focus on a fixed set of languages,
which makes it difficult to handle newly added languages or adapt to ever-changing data …
which makes it difficult to handle newly added languages or adapt to ever-changing data …
Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation
Video-based scene graph generation (VidSGG) is an approach that aims to represent video
content in a dynamic graph by identifying visual entities and their relationships. Due to the …
content in a dynamic graph by identifying visual entities and their relationships. Due to the …
Factorized omnidirectional representation based vision gnn for anisotropic 3d multimodal mr image segmentation
Anisotropy arises due to the influence of scanning equipment and parameters, resulting in a
distance between slices that is often much greater than the actual distance represented by a …
distance between slices that is often much greater than the actual distance represented by a …
Exploring Visual Relationships via Transformer-based Graphs for Enhanced Image Captioning
Image captioning (IC), bringing vision to language, has drawn extensive attention. A crucial
aspect of IC is the accurate depiction of visual relations among image objects. Visual …
aspect of IC is the accurate depiction of visual relations among image objects. Visual …
Multi-view Vision Fusion Network: Can 2D Pre-trained Model Boost 3D Point Cloud Data-scarce Learning?
Point cloud based 3D deep model has wide applications in many applications such as
autonomous driving, house robot, etc. Inspired by the recent prompt learning in natural …
autonomous driving, house robot, etc. Inspired by the recent prompt learning in natural …
Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
Continual learning aims to learn a series of tasks sequentially without forgetting the
knowledge acquired from the previous ones. In this work, we propose the Hessian Aware …
knowledge acquired from the previous ones. In this work, we propose the Hessian Aware …
Hessian Aware Low-Rank Weight Perturbation for Continual Learning
Continual learning aims to learn a series of tasks sequentially without forgetting the
knowledge acquired from the previous ones. In this work, we propose the Hessian Aware …
knowledge acquired from the previous ones. In this work, we propose the Hessian Aware …