2.4k citations · 3.4k across the 57 of their papers we have counts for
19 papers · 1 filter
TransTrack: Multiple Object Tracking with Transformer
Peize Sun, Jinkun Cao, Yi Jiang +5
In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an at…
Polygon-free: Unconstrained Scene Text Detection with Box Annotations
Weijia Wu, Enze Xie, Ruimao Zhang +3
Although a polygon is a more accurate representation than an upright bounding box for text detection, the annotations of polygons are extremely expensive and challenging. Unlike ex…
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Xingang Pan, Bo Dai, Ziwei Liu +2
Natural images are projections of 3D objects on a 2D image plane. While state-of-the-art 2D generative models like GANs show unprecedented quality in modeling the natural image man…
UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation
Yuanfeng Ji, Ruimao Zhang, Zhen Li +3
Aggregating multi-level feature representation plays a critical role in achieving robust volumetric medical image segmentation, which is important for the auxiliary diagnosis and t…
RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning
Hao Tan, Ran Cheng, Shihua Huang +4
Despite the remarkable successes of Convolutional Neural Networks (CNNs) in computer vision, it is time-consuming and error-prone to manually design a CNN. Among various Neural Arc…
Webly Supervised Image Classification with Self-Contained Confidence
Jingkang Yang, Litong Feng, Weirong Chen +4
This paper focuses on webly supervised learning (WSL), where datasets are built by crawling samples from the Internet and directly using search queries as web labels. Although WSL…
Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction
Chaofan Tao, Qinhong Jiang, Lixin Duan +1
Multi-agent motion prediction is challenging because it aims to foresee the future trajectories of multiple agents (\textit{e.g.} pedestrians) simultaneously in a complicated scene…
AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text Spotting
Wenhai Wang, Xuebo Liu, Xiaozhong Ji +6
Scene text spotting aims to detect and recognize the entire word or sentence with multiple characters in natural images. It is still challenging because ambiguity often occurs when…
Differentiable Hierarchical Graph Grouping for Multi-Person Pose Estimation
Sheng Jin, Wentao Liu, Enze Xie +4
Multi-person pose estimation is challenging because it localizes body keypoints for multiple persons simultaneously. Previous methods can be divided into two streams, i.e. top-down…
Whole-Body Human Pose Estimation in the Wild
Sheng Jin, Lumin Xu, Jin Xu +5
This paper investigates the task of 2D human whole-body pose estimation, which aims to localize dense landmarks on the entire human body including face, hands, body, and feet. As e…
3D Human Mesh Regression with Dense Correspondence
Wang Zeng, Wanli Ouyang, Ping Luo +2
Estimating 3D mesh of the human body from a single 2D image is an important task with many applications such as augmented reality and Human-Robot interaction. However, prior works…
Learning a Reinforced Agent for Flexible Exposure Bracketing Selection
Zhouxia Wang, Jiawei Zhang, Mude Lin +3
Automatically selecting exposure bracketing (images exposed differently) is important to obtain a high dynamic range image by using multi-exposure fusion. Unlike previous methods t…
AdaX: Adaptive Gradient Descent with Exponential Long Term Memory
Wenjie Li, Zhaoyang Zhang, Xinjiang Wang +1
Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in…
Exemplar Normalization for Learning Deep Representation
Ruimao Zhang, Zhanglin Peng, Lingyun Wu +2
Normalization techniques are important in different advanced neural networks and different tasks. This work investigates a novel dynamic learning-to-normalize (L2N) problem by prop…
Towards Photo-Realistic Virtual Try-On by Adaptively GeneratingPreserving Image Content
Han Yang, Ruimao Zhang, Xiaobao Guo +3
Image visual try-on aims at transferring a target clothing image onto a reference person, and has become a hot topic in recent years. Prior arts usually focus on preserving the cha…
Segmenting Transparent Objects in the Wild
Enze Xie, Wenjia Wang, Wenhai Wang +3
Transparent objects such as windows and bottles made by glass widely exist in the real world. Segmenting transparent objects is challenging because these objects have diverse appea…
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Xingang Pan, Xiaohang Zhan, Bo Dai +3
Learning a good image prior is a long-term goal for image restoration and manipulation. While existing methods like deep image prior (DIP) capture low-level image statistics, there…
Channel Equilibrium Networks for Learning Deep Representation
Wenqi Shao, Shitao Tang, Xingang Pan +3
Convolutional Neural Networks (CNNs) are typically constructed by stacking multiple building blocks, each of which contains a normalization layer such as batch normalization (BN) a…
How Does BN Increase Collapsed Neural Network Filters?
Sheng Zhou, Xinjiang Wang, Ping Luo +3
Improving sparsity of deep neural networks (DNNs) is essential for network compression and has drawn much attention. In this work, we disclose a harmful sparsifying process called…