1.6k citations · 6.8k across the 186 of their papers we have counts for
21 papers · 1 filter
NeuSample: Neural Sample Field for Efficient View Synthesis
Jiemin Fang, Lingxi Xie, Xinggang Wang +3
Neural radiance fields (NeRF) have shown great potentials in representing 3D scenes and synthesizing novel views, but the computational overhead of NeRF at the inference stage is s…
Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge
Jiyang Qi, Yan Gao, Yao Hu +7
Although deep learning methods have achieved advanced video object recognition performance in recent years, perceiving heavily occluded objects in a video is still a very challengi…
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Yifu Zhang, Peize Sun, Yi Jiang +6
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are hi…
VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild
Yifu Zhang, Chunyu Wang, Xinggang Wang +2
We present VoxelTrack for multi-person 3D pose estimation and tracking from a few cameras which are separated by wide baselines. It employs a multi-branch network to jointly estima…
Hierarchical Aggregation for 3D Instance Segmentation
Shaoyu Chen, Jiemin Fang, Qian Zhang +2
Instance segmentation on point clouds is a fundamental task in 3D scene perception. In this work, we propose a concise clustering-based framework named HAIS, which makes full use o…
YOLOP: You Only Look Once for Panoptic Driving Perception
Dong Wu, Manwen Liao, Weitian Zhang +4
A panoptic driving perception system is an essential part of autonomous driving. A high-precision and real-time perception system can assist the vehicle in making the reasonable de…
What Makes for Hierarchical Vision Transformer?
Yuxin Fang, Xinggang Wang, Rui Wu +1
Recent studies indicate that hierarchical Vision Transformer with a macro architecture of interleaved non-overlapped window-based self-attention \& shifted-window operation is able…
Bag of Instances Aggregation Boosts Self-supervised Distillation
Haohang Xu, Jiemin Fang, Xiaopeng Zhang +5
Recent advances in self-supervised learning have experienced remarkable progress, especially for contrastive learning based methods, which regard each image as well as its augmenta…
Tracking Instances as Queries
Shusheng Yang, Yuxin Fang, Xinggang Wang +4
Recently, query based deep networks catch lots of attention owing to their end-to-end pipeline and competitive results on several fundamental computer vision tasks, such as object…
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
Yuxin Fang, Bencheng Liao, Xinggang Wang +5
Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure? To answer this q…
Instances as Queries
Yuxin Fang, Shusheng Yang, Xinggang Wang +5
Recently, query based object detection frameworks achieve comparable performance with previous state-of-the-art object detectors. However, how to fully leverage such frameworks to…
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
Jiemin Fang, Lingxi Xie, Xinggang Wang +3
Transformers have offered a new methodology of designing neural networks for visual recognition. Compared to convolutional networks, Transformers enjoy the ability of referring to…
Crossover Learning for Fast Online Video Instance Segmentation
Shusheng Yang, Yuxin Fang, Xinggang Wang +5
Modeling temporal visual context across frames is critical for video instance segmentation (VIS) and other video understanding tasks. In this paper, we propose a fast online VIS mo…
Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images
Xinggang Wang, Jiapei Feng, Bin Hu +4
Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnost…
Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation
Zilong Huang, Wentian Hao, Xinggang Wang +4
Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new class…
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…
Human De-occlusion: Invisible Perception and Recovery for Humans
Qiang Zhou, Shiyin Wang, Yitong Wang +2
In this paper, we tackle the problem of human de-occlusion which reasons about occluded segmentation masks and invisible appearance content of humans. In particular, a two-stage fr…
Noise Modulation: Let Your Model Interpret Itself
Haoyang Li, Xinggang Wang
Given the great success of Deep Neural Networks(DNNs) and the black-box nature of it,the interpretability of these models becomes an important issue.The majority of previous resear…
Deep Online Correction for Monocular Visual Odometry
Jiaxin Zhang, Wei Sui, Xinggang Wang +3
In this work, we propose a novel deep online correction (DOC) framework for monocular visual odometry. The whole pipeline has two stages: First, depth maps and initial poses are ob…
Occluded Video Instance Segmentation: A Benchmark
Jiyang Qi, Yan Gao, Yao Hu +7
Can our video understanding systems perceive objects when a heavy occlusion exists in a scene? To answer this question, we collect a large-scale dataset called OVIS for occluded vi…
Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition
Mengting Chen, Xinggang Wang, Heng Luo +2
Deep networks can learn to accurately recognize objects of a category by training on a large number of annotated images. However, a meta-learning challenge known as a low-shot imag…