1.6k citations · 3.8k across the 68 of their papers we have counts for
17 papers · 1 filter
Deep Level Set for Box-supervised Instance Segmentation in Aerial Images
Wentong Li, Yijie Chen, Wenyu Liu +1
Box-supervised instance segmentation has recently attracted lots of research efforts while little attention is received in aerial image domain. In contrast to the general object co…
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…
Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition
Changxu Cheng, Bohan Li, Qi Zheng +2
Semantic information has been proved effective in scene text recognition. Most existing methods tend to couple both visual and semantic information in an attention-based decoder. A…
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…
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…
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…
Dynamic Class Queue for Large Scale Face Recognition In the Wild
Bi Li, Teng Xi, Gang Zhang +5
Learning discriminative representation using large-scale face datasets in the wild is crucial for real-world applications, yet it remains challenging. The difficulties lie in many…
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…
Scene Text Retrieval via Joint Text Detection and Similarity Learning
Hao Wang, Xiang Bai, Mingkun Yang +3
Scene text retrieval aims to localize and search all text instances from an image gallery, which are the same or similar to a given query text. Such a task is usually realized by m…
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…
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…