2.4k citations · 3.3k across the 23 of their papers we have counts for
24 papers
MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
Bencheng Liao, Shaoyu Chen, Yunchi Zhang +5
High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in a…
VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene
Shaoyu Chen, Yunchi Zhang, Bencheng Liao +7
High-definition (HD) map serves as the essential infrastructure of autonomous driving. In this work, we build up a systematic vectorized map annotation framework (termed VMA) for e…
VAD: Vectorized Scene Representation for Efficient Autonomous Driving
Bo Jiang, Shaoyu Chen, Qing Xu +7
Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene representat…
Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction
Bencheng Liao, Shaoyu Chen, Bo Jiang +5
Online lane graph construction is a promising but challenging task in autonomous driving. Previous methods usually model the lane graph at the pixel or piece level, and recover the…
Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction
Bo Jiang, Shaoyu Chen, Xinggang Wang +7
Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving. In this work, we propose PIP, the first en…
MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
Bencheng Liao, Shaoyu Chen, Xinggang Wang +4
High-definition (HD) map provides abundant and precise environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomo…
Polar Parametrization for Vision-based Surround-View 3D Detection
Shaoyu Chen, Xinggang Wang, Tianheng Cheng +3
3D detection based on surround-view camera system is a critical technique in autopilot. In this work, we present Polar Parametrization for 3D detection, which reformulates position…
AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception
Shaoyu Chen, Xinggang Wang, Tianheng Cheng +4
Studying the inherent symmetry of data is of great importance in machine learning. Point cloud, the most important data format for 3D environmental perception, is naturally endowed…
Sparse Instance Activation for Real-Time Instance Segmentation
Tianheng Cheng, Xinggang Wang, Shaoyu Chen +5
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods hea…
Real-Time and Accurate Object Detection in Compressed Video by Long Short-term Feature Aggregation
Xinggang Wang, Zhaojin Huang, Bencheng Liao +3
Video object detection is a fundamental problem in computer vision and has a wide spectrum of applications. Based on deep networks, video object detection is actively studied for p…
Diversity Transfer Network for Few-Shot Learning
Mengting Chen, Yuxin Fang, Xinggang Wang +6
Few-shot learning is a challenging task that aims at training a classifier for unseen classes with only a few training examples. The main difficulty of few-shot learning lies in th…
RDSNet: A New Deep Architecture for Reciprocal Object Detection and Instance Segmentation
Shaoru Wang, Yongchao Gong, Junliang Xing +3
Object detection and instance segmentation are two fundamental computer vision tasks. They are closely correlated but their relations have not yet been fully explored in most previ…
High Performance Visual Object Tracking with Unified Convolutional Networks
Zheng Zhu, Wei Zou, Guan Huang +2
Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks. Nonetheless, the chosen CNN features are always pre-trained in…
Object Detection in Video with Spatial-temporal Context Aggregation
Hao Luo, Lichao Huang, Han Shen +3
Recent cutting-edge feature aggregation paradigms for video object detection rely on inferring feature correspondence. The feature correspondence estimation problem is fundamentall…
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
Qiang Zhou, Zilong Huang, Lichao Huang +5
Video object segmentation (VOS) aims at pixel-level object tracking given only the annotations in the first frame. Due to the large visual variations of objects in video and the la…
Mask Scoring R-CNN
Zhaojin Huang, Lichao Huang, Yongchao Gong +2
Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. In the task of instance segmentation, the confidence of instance clas…
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
Jiemin Fang, Yukang Chen, Xinbang Zhang +5
Neural architecture search (NAS) methods have been proposed to release human experts from tedious architecture engineering. However, most current methods are constrained in small-s…
CCNet: Criss-Cross Attention for Semantic Segmentation
Zilong Huang, Xinggang Wang, Yunchao Wei +4
Contextual information is vital in visual understanding problems, such as semantic segmentation and object detection. We propose a Criss-Cross Network (CCNet) for obtaining full-im…
Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking
Han Shen, Lichao Huang, Chang Huang +1
Traditional multiple object tracking methods divide the task into two parts: affinity learning and data association. The separation of the task requires to define a hand-crafted tr…
Unsupervised Domain Adaptive Re-Identification: Theory and Practice
Liangchen Song, Cheng Wang, Lefei Zhang +4
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation. We first extend exist…
UCT: Learning Unified Convolutional Networks for Real-time Visual Tracking
Zheng Zhu, Guan Huang, Wei Zou +2
Convolutional neural networks (CNN) based tracking approaches have shown favorable performance in recent benchmarks. Nonetheless, the chosen CNN features are always pre-trained in…
Text Flow: A Unified Text Detection System in Natural Scene Images
Shangxuan Tian, Yifeng Pan, Chang Huang +3
The prevalent scene text detection approach follows four sequential steps comprising character candidate detection, false character candidate removal, text line extraction, and tex…
CNN-RNN: A Unified Framework for Multi-label Image Classification
Jiang Wang, Yi Yang, Junhua Mao +3
While deep convolutional neural networks (CNNs) have shown a great success in single-label image classification, it is important to note that real world images generally contain mu…
Conditional Random Fields as Recurrent Neural Networks
Shuai Zheng, Sadeep Jayasumana, Bernardino Romera-Paredes +5
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learnin…