Search Results for author: Changxin Gao

Found 36 papers, 22 papers with code

Hybrid Relation Guided Set Matching for Few-shot Action Recognition

no code implementations28 Apr 2022 Xiang Wang, Shiwei Zhang, Zhiwu Qing, Mingqian Tang, Zhengrong Zuo, Changxin Gao, Rong Jin, Nong Sang

To overcome the two limitations, we propose a novel Hybrid Relation guided Set Matching (HyRSM) approach that incorporates two key components: hybrid relation module and set matching metric.

Few Shot Action Recognition set matching

Style Transformer for Image Inversion and Editing

1 code implementation15 Mar 2022 Xueqi Hu, Qiusheng Huang, Zhengyi Shi, Siyuan Li, Changxin Gao, Li Sun, Qingli Li

Existing GAN inversion methods fail to provide latent codes for reliable reconstruction and flexible editing simultaneously.

Image-to-Image Translation

Multi-Centroid Representation Network for Domain Adaptive Person Re-ID

no code implementations22 Dec 2021 Yuhang Wu, Tengteng Huang, Haotian Yao, Chi Zhang, Yuanjie Shao, Chuchu Han, Changxin Gao, Nong Sang

First, we present a Domain-Specific Contrastive Learning (DSCL) mechanism to fully explore intradomain information by comparing samples only from the same domain.

Contrastive Learning Domain Adaptive Person Re-Identification +1

Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval

1 code implementation15 Dec 2021 Zongheng Huang, Yifan Sun, Chuchu Han, Changxin Gao, Nong Sang

By combining two fundamental learning approaches in DML, e. g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR.

Metric Learning Sketch-Based Image Retrieval

Unsupervised Low-Light Image Enhancement via Histogram Equalization Prior

1 code implementation3 Dec 2021 Feng Zhang, Yuanjie Shao, Yishi Sun, Kai Zhu, Changxin Gao, Nong Sang

We introduce a Noise Disentanglement Module (NDM) to disentangle the noise and content in the reflectance maps with the reliable aid of unpaired clean images.

 Ranked #1 on Low-Light Image Enhancement on DICM (NIQE metric)

Disentanglement Image Restoration +1

Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation

1 code implementation25 Nov 2021 Rui Wang, Jian Chen, Gang Yu, Li Sun, Changqian Yu, Changxin Gao, Nong Sang

Image manipulation with StyleGAN has been an increasing concern in recent years. Recent works have achieved tremendous success in analyzing several semantic latent spaces to edit the attributes of the generated images. However, due to the limited semantic and spatial manipulation precision in these latent spaces, the existing endeavors are defeated in fine-grained StyleGAN image manipulation, i. e., local attribute translation. To address this issue, we discover attribute-specific control units, which consist of multiple channels of feature maps and modulation styles.

Image Manipulation

CondNet: Conditional Classifier for Scene Segmentation

2 code implementations21 Sep 2021 Changqian Yu, Yuanjie Shao, Changxin Gao, Nong Sang

The last layer of FCN is typically a global classifier (1x1 convolution) to recognize each pixel to a semantic label.

Scene Segmentation

ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning

1 code implementation24 Aug 2021 Zhiwu Qing, Ziyuan Huang, Shiwei Zhang, Mingqian Tang, Changxin Gao, Marcelo H. Ang Jr, Rong Jin, Nong Sang

The visualizations show that ParamCrop adaptively controls the center distance and the IoU between two augmented views, and the learned change in the disparity along the training process is beneficial to learning a strong representation.

Contrastive Learning

OadTR: Online Action Detection with Transformers

1 code implementation ICCV 2021 Xiang Wang, Shiwei Zhang, Zhiwu Qing, Yuanjie Shao, Zhengrong Zuo, Changxin Gao, Nong Sang

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure.

Action Detection

A Stronger Baseline for Ego-Centric Action Detection

1 code implementation13 Jun 2021 Zhiwu Qing, Ziyuan Huang, Xiang Wang, Yutong Feng, Shiwei Zhang, Jianwen Jiang, Mingqian Tang, Changxin Gao, Marcelo H. Ang Jr, Nong Sang

This technical report analyzes an egocentric video action detection method we used in the 2021 EPIC-KITCHENS-100 competition hosted in CVPR2021 Workshop.

Action Detection

Temporal Context Aggregation Network for Temporal Action Proposal Refinement

1 code implementation CVPR 2021 Zhiwu Qing, Haisheng Su, Weihao Gan, Dongliang Wang, Wei Wu, Xiang Wang, Yu Qiao, Junjie Yan, Changxin Gao, Nong Sang

In this paper, we propose Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through "local and global" temporal context aggregation and complementary as well as progressive boundary refinement.

Action Detection Temporal Action Proposal Generation +1

Decoupled and Memory-Reinforced Networks: Towards Effective Feature Learning for One-Step Person Search

no code implementations22 Feb 2021 Chuchu Han, Zhedong Zheng, Changxin Gao, Nong Sang, Yi Yang

Specifically, to reconcile the conflicts of multiple objectives, we simplify the standard tightly coupled pipelines and establish a deeply decoupled multi-task learning framework.

Metric Learning Multi-Task Learning +2

Weakly Supervised Text-Based Person Re-Identification

1 code implementation ICCV 2021 Shizhen Zhao, Changxin Gao, Yuanjie Shao, Wei-Shi Zheng, Nong Sang

Specifically, to alleviate the intra-class variations, a clustering method is utilized to generate pseudo labels for both visual and textual instances.

Person Re-Identification

Representative Graph Neural Network

no code implementations ECCV 2020 Changqian Yu, Yifan Liu, Changxin Gao, Chunhua Shen, Nong Sang

In this paper, we present a Representative Graph (RepGraph) layer to dynamically sample a few representative features, which dramatically reduces redundancy.

Object Detection Semantic Segmentation

Multi-Level Temporal Pyramid Network for Action Detection

no code implementations7 Aug 2020 Xiang Wang, Changxin Gao, Shiwei Zhang, Nong Sang

By this means, the proposed MLTPN can learn rich and discriminative features for different action instances with different durations.

Action Detection

Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)

no code implementations13 Jun 2020 Zhiwu Qing, Xiang Wang, Yongpeng Sang, Changxin Gao, Shiwei Zhang, Nong Sang

This technical report analyzes a temporal action localization method we used in the HACS competition which is hosted in Activitynet Challenge 2020. The goal of our task is to locate the start time and end time of the action in the untrimmed video, and predict action category. Firstly, we utilize the video-level feature information to train multiple video-level action classification models.

Action Classification Temporal Action Localization

Relevant Region Prediction for Crowd Counting

no code implementations20 May 2020 Xinya Chen, Yanrui Bin, Changxin Gao, Nong Sang, Hao Tang

The module builds a fully connected directed graph between the regions of different density where each node (region) is represented by weighted global pooled feature, and GCN is learned to map this region graph to a set of relation-aware regions representations.

Crowd Counting

Domain Adaptation for Image Dehazing

1 code implementation CVPR 2020 Yuanjie Shao, Lerenhan Li, Wenqi Ren, Changxin Gao, Nong Sang

By training image translation and dehazing network in an end-to-end manner, we can obtain better effects of both image translation and dehazing.

Domain Adaptation Image Dehazing +1

BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation

4 code implementations5 Apr 2020 Changqian Yu, Changxin Gao, Jingbo Wang, Gang Yu, Chunhua Shen, Nong Sang

We propose to treat these spatial details and categorical semantics separately to achieve high accuracy and high efficiency for realtime semantic segmentation.

Real-Time Semantic Segmentation

Context Prior for Scene Segmentation

2 code implementations CVPR 2020 Changqian Yu, Jingbo Wang, Changxin Gao, Gang Yu, Chunhua Shen, Nong Sang

Given an input image and corresponding ground truth, Affinity Loss constructs an ideal affinity map to supervise the learning of Context Prior.

Scene Segmentation Scene Understanding

FGN: Fully Guided Network for Few-Shot Instance Segmentation

no code implementations CVPR 2020 Zhibo Fan, Jin-Gang Yu, Zhihao Liang, Jiarong Ou, Changxin Gao, Gui-Song Xia, Yuanqing Li

Few-shot instance segmentation (FSIS) conjoins the few-shot learning paradigm with general instance segmentation, which provides a possible way of tackling instance segmentation in the lack of abundant labeled data for training.

Few-Shot Learning Instance Segmentation +1

GTNet: Generative Transfer Network for Zero-Shot Object Detection

1 code implementation19 Jan 2020 Shizhen Zhao, Changxin Gao, Yuanjie Shao, Lerenhan Li, Changqian Yu, Zhong Ji, Nong Sang

FFU and BFU add the IoU variance to the results of CFU, yielding class-specific foreground and background features, respectively.

Transfer Learning Zero-Shot Object Detection

Re-ID Driven Localization Refinement for Person Search

no code implementations ICCV 2019 Chuchu Han, Jiacheng Ye, Yunshan Zhong, Xin Tan, Chi Zhang, Changxin Gao, Nong Sang

The state-of-the-art methods train the detector individually, and the detected bounding boxes may be sub-optimal for the following re-ID task.

Person Re-Identification Person Search

Learning a Discriminative Feature Network for Semantic Segmentation

3 code implementations CVPR 2018 Changqian Yu, Jingbo Wang, Chao Peng, Changxin Gao, Gang Yu, Nong Sang

Most existing methods of semantic segmentation still suffer from two aspects of challenges: intra-class inconsistency and inter-class indistinction.

Semantic Segmentation Thermal Image Segmentation

Learning a Discriminative Prior for Blind Image Deblurring

no code implementations CVPR 2018 Lerenhan Li, Jinshan Pan, Wei-Sheng Lai, Changxin Gao, Nong Sang, Ming-Hsuan Yang

We present an effective blind image deblurring method based on a data-driven discriminative prior. Our work is motivated by the fact that a good image prior should favor clear images over blurred images. In this work, we formulate the image prior as a binary classifier which can be achieved by a deep convolutional neural network (CNN). The learned prior is able to distinguish whether an input image is clear or not. Embedded into the maximum a posterior (MAP) framework, it helps blind deblurring in various scenarios, including natural, face, text, and low-illumination images. However, it is difficult to optimize the deblurring method with the learned image prior as it involves a non-linear CNN. Therefore, we develop an efficient numerical approach based on the half-quadratic splitting method and gradient decent algorithm to solve the proposed model. Furthermore, the proposed model can be easily extended to non-uniform deblurring. Both qualitative and quantitative experimental results show that our method performs favorably against state-of-the-art algorithms as well as domain-specific image deblurring approaches.

Blind Image Deblurring Image Deblurring

Exemplar-based Linear Discriminant Analysis for Robust Object Tracking

no code implementations24 Feb 2014 Changxin Gao, Feifei Chen, Jin-Gang Yu, Rui Huang, Nong Sang

However, the task in tracking is to search for a specific object, rather than an object category as in detection.

Object Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.