66 citations · 187 across the 16 of their papers we have counts for
25 papers
Sim2Real Object-Centric Keypoint Detection and Description
Chengliang Zhong, Chao Yang, Jinshan Qi +4
Keypoint detection and description play a central role in computer vision. Most existing methods are in the form of scene-level prediction, without returning the object classes of…
Continual Learning with Recursive Gradient Optimization
Hao Liu, Huaping Liu
Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing meth…
Self-supervised 3D Semantic Representation Learning for Vision-and-Language Navigation
Sinan Tan, Mengmeng Ge, Di Guo +2
In the Vision-and-Language Navigation task, the embodied agent follows linguistic instructions and navigates to a specific goal. It is important in many practical scenarios and has…
Audio-Visual Grounding Referring Expression for Robotic Manipulation
Yefei Wang, Kaili Wang, Yi Wang +3
Referring expressions are commonly used when referring to a specific target in people's daily dialogue. In this paper, we develop a novel task of audio-visual grounding referring e…
Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge
Xinzhu Liu, Di Guo, Huaping Liu +1
In visual semantic navigation, the robot navigates to a target object with egocentric visual observations and the class label of the target is given. It is a meaningful task inspir…
Knowledge-based Embodied Question Answering
Sinan Tan, Mengmeng Ge, Di Guo +2
In this paper, we propose a novel Knowledge-based Embodied Question Answering (K-EQA) task, in which the agent intelligently explores the environment to answer various questions wi…