84 citations · 188 across the 29 of their papers we have counts for
16 papers · 1 filter
Explicit Attention-Enhanced Fusion for RGB-Thermal Perception Tasks
Mingjian Liang, Junjie Hu, Chenyu Bao +3
Recently, RGB-Thermal based perception has shown significant advances. Thermal information provides useful clues when visual cameras suffer from poor lighting conditions, such as l…
Peer Learning for Unbiased Scene Graph Generation
Liguang Zhou, Junjie Hu, Yuhongze Zhou +2
Unbiased scene graph generation (USGG) is a challenging task that requires predicting diverse and heavily imbalanced predicates between objects in an image. To address this, we pro…
Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation
Junjie Hu, Chenyou Fan, Liguang Zhou +3
With the rapid advancements in autonomous driving and robot navigation, there is a growing demand for lifelong learning models capable of estimating metric (absolute) depth. Lifelo…
Attentional Graph Convolutional Network for Structure-aware Audio-Visual Scene Classification
Liguang Zhou, Yuhongze Zhou, Xiaonan Qi +3
Audio-Visual scene understanding is a challenging problem due to the unstructured spatial-temporal relations that exist in the audio signals and spatial layouts of different object…
Dense Depth Distillation with Out-of-Distribution Simulated Images
Junjie Hu, Chenyou Fan, Mete Ozay +2
We study data-free knowledge distillation (KD) for monocular depth estimation (MDE), which learns a lightweight model for real-world depth perception tasks by compressing it from a…
Context-aware Mixture-of-Experts for Unbiased Scene Graph Generation
Liguang Zhou, Yuhongze Zhou, Tin Lun Lam +1
Scene graph generation (SGG) has gained tremendous progress in recent years. However, its underlying long-tailed distribution of predicate classes is a challenging problem. For ext…
Deep Depth Completion from Extremely Sparse Data: A Survey
Junjie Hu, Chenyu Bao, Mete Ozay +4
Depth completion aims at predicting dense pixel-wise depth from an extremely sparse map captured from a depth sensor, e.g., LiDARs. It plays an essential role in various applicatio…
Abnormal Occupancy Grid Map Recognition using Attention Network
Fuqin Deng, Hua Feng, Mingjian Liang +6
The occupancy grid map is a critical component of autonomous positioning and navigation in the mobile robotic system, as many other systems' performance depends heavily on it. To g…
FEANet: Feature-Enhanced Attention Network for RGB-Thermal Real-time Semantic Segmentation
Fuqin Deng, Hua Feng, Mingjian Liang +7
The RGB-Thermal (RGB-T) information for semantic segmentation has been extensively explored in recent years. However, most existing RGB-T semantic segmentation usually compromises…
PoseFusion2: Simultaneous Background Reconstruction and Human Shape Recovery in Real-time
Huayan Zhang, Tianwei Zhang, Tin Lun Lam +1
Dynamic environments that include unstructured moving objects pose a hard problem for Simultaneous Localization and Mapping (SLAM) performance. The motion of rigid objects can be t…
Object-to-Scene: Learning to Transfer Object Knowledge to Indoor Scene Recognition
Bo Miao, Liguang Zhou, Ajmal Mian +2
Accurate perception of the surrounding scene is helpful for robots to make reasonable judgments and behaviours. Therefore, developing effective scene representation and recognition…
BORM: Bayesian Object Relation Model for Indoor Scene Recognition
Liguang Zhou, Jun Cen, Xingchao Wang +3
Scene recognition is a fundamental task in robotic perception. For human beings, scene recognition is reasonable because they have abundant object knowledge of the real world. The…
Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention
Yuhongze Zhou, Liguang Zhou, Tin Lun Lam +1
Natural image matting aims to precisely separate foreground objects from background using alpha matte. Fully automatic natural image matting without external annotation is challeng…
Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
Shuai Zhao, Liguang Zhou, Wenxiao Wang +3
The width of a neural network matters since increasing the width will necessarily increase the model capacity. However, the performance of a network does not improve linearly with…
A Two-stage Unsupervised Approach for Low light Image Enhancement
Junjie Hu, Xiyue Guo, Junfeng Chen +3
As vision based perception methods are usually built on the normal light assumption, there will be a serious safety issue when deploying them into low light environments. Recently,…
IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report
Qi She, Fan Feng, Qi Liu +33
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top finalists (out of over~…