no code implementations • 26 Jul 2022 • Chuhui Xue, Jiaxing Huang, Shijian Lu, Changhu Wang, Song Bai
We formulate the new setup by a dual detection task which first detects integral text units and then groups them into a CTB.
1 code implementation • 23 May 2022 • Junjie Tang, Changhu Wang, Feiyi Xiao, Ruibin Xi
In this paper, we consider inferring GRNs in single cells based on single cell RNA sequencing (scRNA-seq) data.
no code implementations • 5 Apr 2022 • Bo Yuan, Danpei Zhao, Shuai Shao, Zehuan Yuan, Changhu Wang
In two typical cross-domain semantic segmentation tasks, i. e., GTA5 to Cityscapes and SYNTHIA to Cityscapes, our method achieves the state-of-the-art segmentation accuracy.
1 code implementation • 26 Feb 2022 • Guanghao Yin, Wei Wang, Zehuan Yuan, Chuchu Han, Wei Ji, Shouqian Sun, Changhu Wang
The comparisons of distribution differences between HQ and LQ images can help our model better assess the image quality.
no code implementations • 18 Dec 2021 • Yiwei Wang, Yujun Cai, Yuxuan Liang, Henghui Ding, Changhu Wang, Bryan Hooi
In this work, we propose the TNS (Time-aware Neighbor Sampling) method: TNS learns from temporal information to provide an adaptive receptive neighborhood for every node at any time.
no code implementations • NeurIPS 2021 • Yiwei Wang, Yujun Cai, Yuxuan Liang, Henghui Ding, Changhu Wang, Siddharth Bhatia, Bryan Hooi
To address this issue, our idea is to transform the temporal graphs using data augmentation (DA) with adaptive magnitudes, so as to effectively augment the input features and preserve the essential semantic information.
1 code implementation • NeurIPS 2021 • Zekun Tong, Yuxuan Liang, Henghui Ding, Yongxing Dai, Xinke Li, Changhu Wang
However, it is still in its infancy with two concerns: 1) changing the graph structure through data augmentation to generate contrastive views may mislead the message passing scheme, as such graph changing action deprives the intrinsic graph structural information, especially the directional structure in directed graphs; 2) since GCL usually uses predefined contrastive views with hand-picking parameters, it does not take full advantage of the contrastive information provided by data augmentation, resulting in incomplete structure information for models learning.
no code implementations • ICLR 2022 • Shuo Yang, Peize Sun, Yi Jiang, Xiaobo Xia, Ruiheng Zhang, Zehuan Yuan, Changhu Wang, Ping Luo, Min Xu
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently.
no code implementations • 29 Sep 2021 • Chuhui Xue, Jiaxing Huang, Wenqing Zhang, Shijian Lu, Song Bai, Changhu Wang
This paper presents Contextual Text Detection, a new setup that detects contextual text blocks for better understanding of texts in scenes.
no code implementations • ICCV 2021 • Chi Zhang, Henghui Ding, Guosheng Lin, Ruibo Li, Changhu Wang, Chunhua Shen
Inspired by the recent success in Automated Machine Learning literature (AutoML), in this paper, we present Meta Navigator, a framework that attempts to solve the aforementioned limitation in few-shot learning by seeking a higher-level strategy and proffer to automate the selection from various few-shot learning designs.
no code implementations • ICCV 2021 • Chuchu Han, Kai Su, Dongdong Yu, Zehuan Yuan, Changxin Gao, Nong Sang, Yi Yang, Changhu Wang
Large-scale labeled training data is often difficult to collect, especially for person identities.
no code implementations • 1 Sep 2021 • Zhenchao Jin, Dongdong Yu, Kai Su, Zehuan Yuan, Changhu Wang
Video scene parsing is a long-standing challenging task in computer vision, aiming to assign pre-defined semantic labels to pixels of all frames in a given video.
1 code implementation • ICCV 2021 • Minghao Xu, Hang Wang, Bingbing Ni, Riheng Zhu, Zhenbang Sun, Changhu Wang
For tackling such practical problem, we propose a Dual-Learner-based Video Highlight Detection (DL-VHD) framework.
1 code implementation • ICCV 2021 • Zhenchao Jin, Tao Gong, Dongdong Yu, Qi Chu, Jian Wang, Changhu Wang, Jie Shao
To address this, this paper proposes to mine the contextual information beyond individual images to further augment the pixel representations.
1 code implementation • ICCV 2021 • Panhe Feng, Qi She, Lei Zhu, Jiaxin Li, Lin Zhang, Zijian Feng, Changhu Wang, Chunpeng Li, Xuejing Kang, Anlong Ming
Retrieving occlusion relation among objects in a single image is challenging due to sparsity of boundaries in image.
1 code implementation • ICCV 2021 • Lei Zhu, Qi She, Duo Li, Yanye Lu, Xuejing Kang, Jie Hu, Changhu Wang
The nonlocal-based blocks are designed for capturing long-range spatial-temporal dependencies in computer vision tasks.
1 code implementation • 5 Jul 2021 • Meng-Jiun Chiou, Henghui Ding, Hanshu Yan, Changhu Wang, Roger Zimmermann, Jiashi Feng
Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.
Ranked #2 on Unbiased Scene Graph Generation on Visual Genome
1 code implementation • 2 Jul 2021 • Lin Zhang, Qi She, Zhengyang Shen, Changhu Wang
Contrastive learning applied to self-supervised representation learning has seen a resurgence in deep models.
1 code implementation • 1 Jun 2021 • Ju He, Adam Kortylewski, Shaokang Yang, Shuai Liu, Cheng Yang, Changhu Wang, Alan Yuille
In particular, we decouple the training of the representation and the classifier, and systematically investigate the effects of different data re-sampling techniques when training the whole network including a classifier as well as fine-tuning the feature extractor only.
no code implementations • 18 May 2021 • Chuhui Xue, Jiaxing Huang, Wenqing Zhang, Shijian Lu, Changhu Wang, Song Bai
The first task focuses on image-to-character (I2C) mapping which detects a set of character candidates from images based on different alignments of visual features in an non-sequential way.
no code implementations • 30 Apr 2021 • Lu Yang, Yunlong Wang, Lingqiao Liu, Peng Wang, Lu Chi, Zehuan Yuan, Changhu Wang, Yanning Zhang
In this paper, we propose a new loss based on center predictivity, that is, a sample must be positioned in a location of the feature space such that from it we can roughly predict the location of the center of same-class samples.
2 code implementations • 27 Apr 2021 • Haotian Yan, Zhe Li, Weijian Li, Changhu Wang, Ming Wu, Chuang Zhang
It is also worth pointing that, given identical strong data augmentations, the performance improvement of ConTNet is more remarkable than that of ResNet.
1 code implementation • 8 Apr 2021 • Guanghao Yin, Wei Wang, Zehuan Yuan, Wei Ji, Dongdong Yu, Shouqian Sun, Tat-Seng Chua, Changhu Wang
We extract degradation prior at task-level with the proposed ConditionNet, which will be used to adapt the parameters of the basic SR network (BaseNet).
1 code implementation • ICCV 2021 • Jiaxin Li, Zijian Feng, Qi She, Henghui Ding, Changhu Wang, Gim Hee Lee
In this paper, we propose MINE to perform novel view synthesis and depth estimation via dense 3D reconstruction from a single image.
2 code implementations • 14 Mar 2021 • Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang
Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences.
Ranked #4 on Fine-Grained Image Classification on CUB-200-2011
13 code implementations • CVPR 2021 • Duo Li, Jie Hu, Changhu Wang, Xiangtai Li, Qi She, Lei Zhu, Tong Zhang, Qifeng Chen
Convolution has been the core ingredient of modern neural networks, triggering the surge of deep learning in vision.
Ranked #706 on Image Classification on ImageNet
no code implementations • 19 Feb 2021 • Shaokang Yang, Shuai Liu, Cheng Yang, Changhu Wang
In this paper, a retrieval-based coarse-to-fine framework is proposed, where we re-rank the TopN classification results by using the local region enhanced embedding features to improve the Top1 accuracy (based on the observation that the correct category usually resides in TopN results).
Ranked #10 on Fine-Grained Image Classification on Stanford Cars
Fine-Grained Image Classification Fine-Grained Image Recognition +2
no code implementations • 7 Jan 2021 • Ningxin Xu, Cheng Yang, Yixin Zhu, Xiaowei Hu, Changhu Wang
Most typical click models assume that the probability of a document to be examined by users only depends on position, such as PBM and UBM.
no code implementations • 1 Jan 2021 • Lei Zhu, Qi She, Changhu Wang
When choosing Chebyshev graph filter, a generalized formulation can be derived for explaining the existing nonlocal-based blocks (e. g. nonlocal block, nonlocal stage, double attention block) and uses to analyze their irrationality.
no code implementations • ICCV 2021 • Wei Wang, Haochen Zhang, Zehuan Yuan, Changhu Wang
A popular attempts towards the challenge is unpaired generative adversarial networks, which generate "real" LR counterparts from real HR images using image-to-image translation and then perform super-resolution from "real" LR->SR.
no code implementations • ICCV 2021 • Chuang Lin, Zehuan Yuan, Sicheng Zhao, Peize Sun, Changhu Wang, Jianfei Cai
By disentangling representations on both image and instance levels, DIDN is able to learn domain-invariant representations that are suitable for generalized object detection.
2 code implementations • 31 Dec 2020 • Peize Sun, Jinkun Cao, Yi Jiang, Rufeng Zhang, Enze Xie, Zehuan Yuan, Changhu Wang, Ping Luo
In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems.
Ranked #7 on Multi-Object Tracking on SportsMOT (using extra training data)
Multi-Object Tracking Multiple Object Tracking with Transformer +3
1 code implementation • 10 Dec 2020 • Liang Hou, Zehuan Yuan, Lei Huang, HuaWei Shen, Xueqi Cheng, Changhu Wang
In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power.
1 code implementation • 10 Dec 2020 • Peize Sun, Yi Jiang, Enze Xie, Wenqi Shao, Zehuan Yuan, Changhu Wang, Ping Luo
We identify that classification cost in matching cost is the main ingredient: (1) previous detectors only consider location cost, (2) by additionally introducing classification cost, previous detectors immediately produce one-to-one prediction during inference.
no code implementations • 4 Dec 2020 • Daizong Liu, Dongdong Yu, Changhu Wang, Pan Zhou
Specifically, our proposed network consists of three main parts: Siamese Encoder Module, Center Guiding Appearance Diffusion Module, and Dynamic Information Fusion Module.
Ranked #6 on Unsupervised Video Object Segmentation on FBMS test
Semantic Segmentation Unsupervised Video Object Segmentation +1
1 code implementation • NeurIPS 2020 • Jie Shao, Kai Hu, Changhu Wang, xiangyang xue, Bhiksha Raj
In this paper, we study what would happen when normalization layers are removed from the network, and show how to train deep neural networks without normalization layers and without performance degradation.
6 code implementations • CVPR 2021 • Peize Sun, Rufeng Zhang, Yi Jiang, Tao Kong, Chenfeng Xu, Wei Zhan, Masayoshi Tomizuka, Lei LI, Zehuan Yuan, Changhu Wang, Ping Luo
In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location.
Ranked #5 on 2D Object Detection on CeyMo
1 code implementation • CVPR 2021 • Jiacheng Chen, Hexiang Hu, Hao Wu, Yuning Jiang, Changhu Wang
Visual Semantic Embedding (VSE) is a dominant approach for vision-language retrieval, which aims at learning a deep embedding space such that visual data are embedded close to their semantic text labels or descriptions.
no code implementations • 28 Oct 2019 • Dongdong Yu, Kai Su, Changhu Wang
Multi-Person Pose Estimation is an interesting yet challenging task in computer vision.
no code implementations • 28 Oct 2019 • Dongdong Yu, Zehuan Yuan, Jinlai Liu, Kun Yuan, Changhu Wang
Instance Segmentation is an interesting yet challenging task in computer vision.
no code implementations • 30 Sep 2019 • Dongdong Yu, Kai Su, Hengkai Guo, Jian Wang, Kaihui Zhou, Yuanyuan Huang, Minghui Dong, Jie Shao, Changhu Wang
Semi-supervised video object segmentation is an interesting yet challenging task in machine learning.
no code implementations • 3 Jul 2019 • Wei Li, Zehuan Yuan, Dashan Guo, Lei Huang, Xiangzhong Fang, Changhu Wang
To perform action detection, we design a 3D convolution network with skip connections for tube classification and regression.
no code implementations • 14 May 2019 • Dongdong Yu, Kai Su, Xin Geng, Changhu Wang
In this paper, a novel Context-and-Spatial Aware Network (CSANet), which integrates both a Context Aware Path and Spatial Aware Path, is proposed to obtain effective features involving both context information and spatial information.
no code implementations • CVPR 2019 • Kai Su, Dongdong Yu, Zhenqi Xu, Xin Geng, Changhu Wang
Multi-person pose estimation is an important but challenging problem in computer vision.
1 code implementation • CVPR 2019 • He Huang, Changhu Wang, Philip S. Yu, Chang-Dong Wang
Most previous models try to learn a fixed one-directional mapping between visual and semantic space, while some recently proposed generative methods try to generate image features for unseen classes so that the zero-shot learning problem becomes a traditional fully-supervised classification problem.
no code implementations • 24 Oct 2018 • Jia Sun, Dongdong Yu, Yinghong Li, Changhu Wang
In this work, we propose a mask propagation network to treat the video segmentation problem as a concept of the guided instance segmentation.
no code implementations • 9 Oct 2018 • Wei Li, Zehuan Yuan, Xiangzhong Fang, Changhu Wang
Attention mechanisms have been widely used in Visual Question Answering (VQA) solutions due to their capacity to model deep cross-domain interactions.
no code implementations • 16 Sep 2018 • Jinlai Liu, Zehuan Yuan, Changhu Wang
Leveraging both visual frames and audio has been experimentally proven effective to improve large-scale video classification.
no code implementations • 12 Mar 2018 • He Huang, Philip S. Yu, Changhu Wang
There has been a drastic growth of research in Generative Adversarial Nets (GANs) in the past few years.
no code implementations • ICLR 2018 • Tao Wei, Changhu Wang, Chang Wen Chen
In this research, we present a novel learning scheme called network iterative learning for deep neural networks.
no code implementations • 18 Feb 2017 • Chang Liu, Fuchun Sun, Changhu Wang, Feng Wang, Alan Yuille
In this way, the sequential representation of an image can be naturally translated to a sequence of words, as the target sequence of the RNN model.
no code implementations • 12 Jan 2017 • Tao Wei, Changhu Wang, Chang Wen Chen
Different from existing work where basic morphing types on the layer level were addressed, we target at the central problem of network morphism at a higher level, i. e., how a convolutional layer can be morphed into an arbitrary module of a neural network.
no code implementations • CVPR 2017 • Si Liu, Changhu Wang, Ruihe Qian, Han Yu, Renda Bao
In this paper, we develop a Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage.
no code implementations • 5 Mar 2016 • Tao Wei, Changhu Wang, Yong Rui, Chang Wen Chen
The second requirement for this network morphism is its ability to deal with non-linearity in a network.
1 code implementation • ICCV 2015 • Xiang Fu, Chien-Yi Wang, Chen Chen, Changhu Wang, C. -C. Jay Kuo
The contour-guided color palette (CCP) is proposed for robust image segmentation.
no code implementations • CVPR 2015 • Xian-Ming Liu, Rongrong Ji, Changhu Wang, Wei Liu, Bineng Zhong, Thomas S. Huang
A hierarchical shape parsing strategy is proposed to partition and organize image components into a hierarchical structure in the scale space.