b'Song Bai'

research

∙ 06/01/2023

Intriguing Properties of Text-guided Diffusion Models

Text-guided diffusion models (TDMs) are widely applied but can fail unex...

0 Qihao Liu, et al. ∙

research

∙ 03/17/2023

SRFormer: Permuted Self-Attention for Single Image Super-Resolution

Previous works have shown that increasing the window size for Transforme...

0 Yupeng Zhou, et al. ∙

research

∙ 03/14/2023

InstMove: Instance Motion for Object-centric Video Segmentation

Despite significant efforts, cutting-edge video segmentation methods sti...

0 Qihao Liu, et al. ∙

research

∙ 12/13/2022

PV3D: A 3D Generative Model for Portrait Video Generation

Recent advances in generative adversarial networks (GANs) have demonstra...

4 Eric Zhongcong Xu, et al. ∙

research

∙ 11/29/2022

Language-driven Open-Vocabulary 3D Scene Understanding

Open-vocabulary scene understanding aims to localize and recognize unsee...

0 Runyu Ding, et al. ∙

research

∙ 11/29/2022

LUMix: Improving Mixup by Better Modelling Label Uncertainty

Modern deep networks can be better generalized when trained with noisy s...

0 Shuyang Sun, et al. ∙

research

∙ 11/18/2022

The Runner-up Solution for YouTube-VIS Long Video Challenge 2022

This technical report describes our 2nd-place solution for the ECCV 2022...

0 Junfeng Wu, et al. ∙

research

∙ 10/24/2022

Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning

This paper presents Holistically-Attracted Wireframe Parsing (HAWP) for ...

0 Nan Xue, et al. ∙

research

∙ 10/01/2022

Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning

Federated learning aims to train models collaboratively across different...

7 Yujun Shi, et al. ∙

research

∙ 09/01/2022

1st Place Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: End-to-End Recognition of Out of Vocabulary Words

Scene text recognition has attracted increasing interest in recent years...

1 Zhangzi Zhu, et al. ∙

research

∙ 08/04/2022

1st Place Solution to ECCV 2022 Challenge on Out of Vocabulary Scene Text Understanding: Cropped Word Recognition

This report presents our winner solution to ECCV 2022 challenge on Out-o...

3 Zhangzi Zhu, et al. ∙

research

∙ 07/29/2022

Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation

Occlusion poses a great threat to monocular multi-person 3D human pose e...

0 Qihao Liu, et al. ∙

research

∙ 07/26/2022

Contextual Text Block Detection towards Scene Text Understanding

Most existing scene text detectors focus on detecting characters or word...

0 Chuhui Xue, et al. ∙

research

∙ 07/21/2022

In Defense of Online Models for Video Instance Segmentation

In recent years, video instance segmentation (VIS) has been largely adva...

1 Junfeng Wu, et al. ∙

research

∙ 04/18/2022

CenterNet++ for Object Detection

There are two mainstreams for object detection: top-down and bottom-up. ...

0 Kaiwen Duan, et al. ∙

research

∙ 04/06/2022

An Empirical Study of End-to-End Temporal Action Detection

Temporal action detection (TAD) is an important yet challenging task in ...

0 Xiaolong Liu, et al. ∙

research

∙ 03/18/2022

Fourier Document Restoration for Robust Document Dewarping and Recognition

State-of-the-art document dewarping techniques learn to predict 3-dimens...

0 Chuhui Xue, et al. ∙

research

∙ 03/10/2022

Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability

Large-scale pre-training has been proven to be crucial for various compu...

0 Ruifei He, et al. ∙

research

∙ 03/08/2022

Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting

Recently, Vision-Language Pre-training (VLP) techniques have greatly ben...

0 Chuhui Xue, et al. ∙

research

∙ 12/15/2021

SeqFormer: a Frustratingly Simple Model for Video Instance Segmentation

In this work, we present SeqFormer, a frustratingly simple model for vid...

16 Junfeng Wu, et al. ∙

research

∙ 12/09/2021

Mimicking the Oracle: An Initial Phase Decorrelation Approach for Class Incremental Learning

Class Incremental Learning (CIL) aims at learning a multi-class classifi...

0 Yujun Shi, et al. ∙

research

∙ 11/29/2021

DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion

A typical pipeline for multi-object tracking (MOT) is to use a detector ...

11 Peize Sun, et al. ∙

research

∙ 11/18/2021

TransMix: Attend to Mix for Vision Transformers

Mixup-based augmentation has been found to be effective for generalizing...

0 Jie-Neng Chen, et al. ∙

research

∙ 11/18/2021

Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence

Artificial intelligence (AI) provides a promising substitution for strea...

14 Xiang Bai, et al. ∙

research

∙ 11/15/2021

Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

Although deep learning methods have achieved advanced video object recog...

12 Jiyang Qi, et al. ∙

research

∙ 11/15/2021

Object Propagation via Inter-Frame Attentions for Temporally Stable Video Instance Segmentation

Video instance segmentation aims to detect, segment, and track objects i...

11 Anirudh S Chakravarthy, et al. ∙

research

∙ 09/03/2021

CAP-Net: Correspondence-Aware Point-view Fusion Network for 3D Shape Analysis

Learning 3D representations by fusing point cloud and multi-view data ha...

0 Xinwei He, et al. ∙

research

∙ 07/27/2021

PlaneTR: Structure-Guided Transformers for 3D Plane Recovery

This paper presents a neural network built upon Transformers, namely Pla...

2 Bin Tan, et al. ∙

research

∙ 07/13/2021

Visual Parser: Representing Part-whole Hierarchies with Transformers

Human vision is able to capture the part-whole hierarchical information ...

0 Shuyang Sun, et al. ∙

research

∙ 06/18/2021

End-to-end Temporal Action Detection with Transformer

Temporal action detection (TAD) aims to determine the semantic label and...

0 Xiaolong Liu, et al. ∙

research

∙ 05/18/2021

I2C2W: Image-to-Character-to-Word Transformers for Accurate Scene Text Recognition

Leveraging the advances of natural language processing, most recent scen...

7 Chuhui Xue, et al. ∙

research

∙ 04/11/2021

Location-Sensitive Visual Recognition with Cross-IOU Loss

Object detection, instance segmentation, and pose estimation are popular...

0 Kaiwen Duan, et al. ∙

research

∙ 03/22/2021

Anchor-Free Person Search

Person search aims to simultaneously localize and identify a query perso...

0 Yichao Yan, et al. ∙

research

∙ 02/09/2021

SwiftNet: Real-time Video Object Segmentation

In this work we present SwiftNet for real-time semi-supervised video obj...

0 Haochen Wang, et al. ∙

research

∙ 02/02/2021

Occluded Video Instance Segmentation

Can our video understanding systems perceive objects when a heavy occlus...

12 Jiyang Qi, et al. ∙

research

∙ 12/17/2020

Multi-shot Temporal Event Localization: a Benchmark

Current developments in temporal event or action localization usually ta...

1 Xiaolong Liu, et al. ∙

research

∙ 10/21/2020

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

Semantic segmentation (SS) is an important perception manner for self-dr...

0 Xiaofeng Liu, et al. ∙

research

∙ 08/29/2020

Dual Attention GANs for Semantic Image Synthesis

In this paper, we focus on the semantic image synthesis task that aims a...

22 Hao Tang, et al. ∙

research

∙ 08/11/2020

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

Semantic segmentation is important for many real-world systems, e.g., au...

0 Xiaofeng Liu, et al. ∙

research

∙ 08/10/2020

Bipartite Graph Reasoning GANs for Person Image Generation

We present a novel Bipartite Graph Reasoning GAN (BiGraphGAN) for the ch...

3 Hao Tang, et al. ∙

research

∙ 07/27/2020

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

The goal of object detection is to determine the class and location of o...

0 Kaiwen Duan, et al. ∙

research

∙ 07/22/2020

FedOCR: Communication-Efficient Federated Learning for Scene Text Recognition

While scene text recognition techniques have been widely used in commerc...

0 Wenqing Zhang, et al. ∙

research

∙ 07/17/2020

XingGAN for Person Image Generation

We propose a novel Generative Adversarial Network (XingGAN or CrossingGA...

11 Hao Tang, et al. ∙

research

∙ 04/04/2020

Neural Architecture Search for Lightweight Non-Local Networks

Non-Local (NL) blocks have been widely studied in various vision tasks. ...

5 Yingwei Li, et al. ∙

research

∙ 03/03/2020

Holistically-Attracted Wireframe Parsing

This paper presents a fast and parsimonious parsing method to accurately...

4 Nan Xue, et al. ∙

research

∙ 12/20/2019

AutoScale: Learning to Scale for Crowd Counting

Crowd counting in images is a widely explored but challenging task. Thou...

13 Chenfeng Xu, et al. ∙

research

∙ 12/18/2019

Learning Regional Attraction for Line Segment Detection

This paper presents regional attraction of line segment maps, and hereby...

9 Nan Xue, et al. ∙

research

∙ 10/24/2019

Anchor Diffusion for Unsupervised Video Object Segmentation

Unsupervised video object segmentation has often been tackled by methods...

13 Zhao Yang, et al. ∙

research

∙ 08/21/2019

Asymmetric Non-local Neural Networks for Semantic Segmentation

The non-local module works as a particularly useful technique for semant...

8 Zhen Zhu, et al. ∙

research

∙ 08/06/2019

View N-gram Network for 3D Object Retrieval

How to aggregate multi-view representations of a 3D shape object into an...

6 Xinwei He, et al. ∙

Song Bai

Featured Co-authors