b'Song Bai'

Anchor-Free Person Search

Person search aims to simultaneously localize and identify a query perso...
03/22/2021 ∙ by Yichao Yan, et al. ∙ 0 ∙ share

read it
SwiftNet: Real-time Video Object Segmentation

In this work we present SwiftNet for real-time semi-supervised video obj...
02/09/2021 ∙ by Haochen Wang, et al. ∙ 0 ∙ share

read it
Occluded Video Instance Segmentation

Can our video understanding systems perceive objects when a heavy occlus...
02/02/2021 ∙ by Jiyang Qi, et al. ∙ 12 ∙ share

read it
Multi-shot Temporal Event Localization: a Benchmark

Current developments in temporal event or action localization usually ta...
12/17/2020 ∙ by Xiaolong Liu, et al. ∙ 1 ∙ share

read it
Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training

Semantic segmentation (SS) is an important perception manner for self-dr...
10/21/2020 ∙ by Xiaofeng Liu, et al. ∙ 0 ∙ share

read it
Dual Attention GANs for Semantic Image Synthesis

In this paper, we focus on the semantic image synthesis task that aims a...
08/29/2020 ∙ by Hao Tang, et al. ∙ 22 ∙ share

read it
Reinforced Wasserstein Training for Severity-Aware Semantic Segmentation in Autonomous Driving

Semantic segmentation is important for many real-world systems, e.g., au...
08/11/2020 ∙ by Xiaofeng Liu, et al. ∙ 0 ∙ share

read it
Bipartite Graph Reasoning GANs for Person Image Generation

We present a novel Bipartite Graph Reasoning GAN (BiGraphGAN) for the ch...
08/10/2020 ∙ by Hao Tang, et al. ∙ 3 ∙ share

read it
Corner Proposal Network for Anchor-free, Two-stage Object Detection

The goal of object detection is to determine the class and location of o...
07/27/2020 ∙ by Kaiwen Duan, et al. ∙ 0 ∙ share

read it
FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition

While scene text recognition techniques have been widely used in commerc...
07/22/2020 ∙ by Wenqing Zhang, et al. ∙ 0 ∙ share

read it
XingGAN for Person Image Generation

We propose a novel Generative Adversarial Network (XingGAN or CrossingGA...
07/17/2020 ∙ by Hao Tang, et al. ∙ 11 ∙ share

read it
Neural Architecture Search for Lightweight Non-Local Networks

Non-Local (NL) blocks have been widely studied in various vision tasks. ...
04/04/2020 ∙ by Yingwei Li, et al. ∙ 5 ∙ share

read it
Holistically-Attracted Wireframe Parsing

This paper presents a fast and parsimonious parsing method to accurately...
03/03/2020 ∙ by Nan Xue, et al. ∙ 4 ∙ share

read it
AutoScale: Learning to Scale for Crowd Counting

Crowd counting in images is a widely explored but challenging task. Thou...
12/20/2019 ∙ by Chenfeng Xu, et al. ∙ 13 ∙ share

read it
Learning Regional Attraction for Line Segment Detection

This paper presents regional attraction of line segment maps, and hereby...
12/18/2019 ∙ by Nan Xue, et al. ∙ 9 ∙ share

read it
Anchor Diffusion for Unsupervised Video Object Segmentation

Unsupervised video object segmentation has often been tackled by methods...
10/24/2019 ∙ by Zhao Yang, et al. ∙ 13 ∙ share

read it
Asymmetric Non-local Neural Networks for Semantic Segmentation

The non-local module works as a particularly useful technique for semant...
08/21/2019 ∙ by Zhen Zhu, et al. ∙ 8 ∙ share

read it
View N-gram Network for 3D Object Retrieval

How to aggregate multi-view representations of a 3D shape object into an...
08/06/2019 ∙ by Xinwei He, et al. ∙ 6 ∙ share

read it
Symmetry-constrained Rectification Network for Scene Text Recognition

Reading text in the wild is a very challenging task due to the diversity...
08/06/2019 ∙ by Mingkun Yang, et al. ∙ 8 ∙ share

read it
Learn to Scale: Generating Multipolar Normalized Density Map for Crowd Counting

Dense crowd counting aims to predict thousands of human instances from a...
07/29/2019 ∙ by Chenfeng Xu, et al. ∙ 3 ∙ share

read it
Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting

Dense crowd counting aims to predict thousands of human instances from a...
07/29/2019 ∙ by Chenfeng Xu, et al. ∙ 0 ∙ share

read it
CenterNet: Keypoint Triplets for Object Detection

In object detection, keypoint-based approaches often suffer a large numb...
04/17/2019 ∙ by Kaiwen Duan, et al. ∙ 0 ∙ share

read it
CenterNet: Object Detection with Keypoint Triplets

In object detection, keypoint-based approaches often suffer a large numb...
04/17/2019 ∙ by Kaiwen Duan, et al. ∙ 0 ∙ share

read it
Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation

Accurate multi-organ abdominal CT segmentation is essential to many clin...
04/12/2019 ∙ by Yuyin Zhou, et al. ∙ 0 ∙ share

read it
Regional Homogeneity: Towards Learning Transferable Universal Adversarial Perturbations Against Defenses

This paper focuses on learning transferable adversarial examples specifi...
04/01/2019 ∙ by Yingwei Li, et al. ∙ 4 ∙ share

read it
Adversarial Metric Attack for Person Re-identification

Person re-identification (re-ID) has attracted much attention recently d...
01/30/2019 ∙ by Song Bai, et al. ∙ 0 ∙ share

read it
Hypergraph Convolution and Hypergraph Attention

Recently, graph neural networks have attracted great attention and achie...
01/23/2019 ∙ by Song Bai, et al. ∙ 0 ∙ share

read it
Learn to Interpret Atari Agents

Deep Reinforcement Learning (DeepRL) models surpass human-level performa...
12/29/2018 ∙ by Zhao Yang, et al. ∙ 8 ∙ share

read it
Learning Transferable Adversarial Examples via Ghost Networks

The recent development of adversarial attack has proven that ensemble-ba...
12/09/2018 ∙ by Yingwei Li, et al. ∙ 0 ∙ share

read it
Learning Attraction Field Representation for Robust Line Segment Detection

This paper presents a region-partition based attraction field dual repre...
12/05/2018 ∙ by Nan Xue, et al. ∙ 12 ∙ share

read it
Hard-Aware Point-to-Set Deep Metric for Person Re-identification

Person re-identification (re-ID) is a highly challenging task due to lar...
07/30/2018 ∙ by Rui Yu, et al. ∙ 0 ∙ share

read it
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection

Weakly Supervised Object Detection (WSOD), using only image-level annota...
07/09/2018 ∙ by Peng Tang, et al. ∙ 0 ∙ share

read it
Triplet-Center Loss for Multi-View 3D Object Retrieval

Most existing 3D object recognition algorithms focus on leveraging the s...
03/16/2018 ∙ by Xinwei He, et al. ∙ 0 ∙ share

read it
Divide and Fuse: A Re-ranking Approach for Person Re-identification

As re-ranking is a necessary procedure to boost person re-identification...
08/11/2017 ∙ by Rui Yu, et al. ∙ 0 ∙ share

read it
Scalable Person Re-identification on Supervised Smoothed Manifold

Most existing person re-identification algorithms either extract robust ...
03/24/2017 ∙ by Song Bai, et al. ∙ 0 ∙ share

read it
GIFT: A Real-time and Scalable 3D Shape Search Engine

Projective analysis is an important solution for 3D shape retrieval, sin...
04/07/2016 ∙ by Song Bai, et al. ∙ 0 ∙ share

read it
Deep Learning Representation using Autoencoder for 3D Shape Retrieval

We study the problem of how to build a deep learning representation for ...
09/25/2014 ∙ by Zhuotun Zhu, et al. ∙ 0 ∙ share

read it

Song Bai

Featured Co-authors