17 citations · 29 across the 4 of their papers we have counts for
6 papers · 1 filter
Prior-Free Continual Learning with Unlabeled Data in the Wild
Tao Zhuo, Zhiyong Cheng, Hehe Fan +1
Continual Learning (CL) aims to incrementally update a trained model on new tasks without forgetting the acquired knowledge of old ones. Existing CL methods usually reduce forgetti…
Continual Learning with Strong Experience Replay
Tao Zhuo, Zhiyong Cheng, Zan Gao +2
Continual Learning (CL) aims at incrementally learning new tasks without forgetting the knowledge acquired from old ones. Experience Replay (ER) is a simple and effective rehearsal…
Effective Abstract Reasoning with Dual-Contrast Network
Tao Zhuo, Mohan Kankanhalli
As a step towards improving the abstract reasoning capability of machines, we aim to solve Raven's Progressive Matrices (RPM) with neural networks, since solving RPM puzzles is hig…
Solving Raven's Progressive Matrices with Neural Networks
Tao Zhuo, Mohan Kankanhalli
Raven's Progressive Matrices (RPM) have been widely used for Intelligence Quotient (IQ) test of humans. In this paper, we aim to solve RPM with neural networks in both supervised a…
Fast Video Object Segmentation via Mask Transfer Network
Tao Zhuo, Zhiyong Cheng, Mohan Kankanhalli
Accuracy and processing speed are two important factors that affect the use of video object segmentation (VOS) in real applications. With the advanced techniques of deep neural net…
Explainable Video Action Reasoning via Prior Knowledge and State Transitions
Tao Zhuo, Zhiyong Cheng, Peng Zhang +2
Human action analysis and understanding in videos is an important and challenging task. Although substantial progress has been made in past years, the explainability of existing me…