4 papers
ShapeFormer: Shape Prior Visible-to-Amodal Transformer-based Amodal Instance Segmentation
Minh Tran, Winston Bounsavy, Khoa Vo +3
Amodal Instance Segmentation (AIS) presents a challenging task as it involves predicting both visible and occluded parts of objects within images. Existing AIS methods rely on a bi…
ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
Thinh Phan, Khoa Vo, Duy Le +3
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos. While standard TAD follows fully supervised learning with…
Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
Kashu Yamazaki, Taisei Hanyu, Khoa Vo +5
Precise 3D environmental mapping is pivotal in robotics. Existing methods often rely on predefined concepts during training or are time-intensive when generating semantic maps. Thi…
3DConvCaps: 3DUnet with Convolutional Capsule Encoder for Medical Image Segmentation
Minh Tran, Viet-Khoa Vo-Ho, Ngan T. H. Le
Convolutional Neural Networks (CNNs) have achieved promising results in medical image segmentation. However, CNNs require lots of training data and are incapable of handling pose a…