no code implementations • ECCV 2020 • Guo-Sen Xie, Li Liu, Fan Zhu, Fang Zhao, Zheng Zhang, Yazhou Yao, Jie Qin, Ling Shao
To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.
no code implementations • ECCV 2020 • Jiaxin Chen, Jie Qin, Yuming Shen, Li Liu, Fan Zhu, Ling Shao
This paper proposes a novel method for 3D shape representation learning, namely Hyperbolic Embedded Attentive Representation (HEAR).
no code implementations • 30 May 2024 • Sizhe Zheng, Pan Gao, Peng Zhou, Jie Qin
In order to achieve better stylization, we design a content feature extractor and a style feature extractor, based on which pure content and style images can be fed to the transformer.
no code implementations • 24 May 2024 • Jiayi Chen, Rong Quan, Jie Qin
Instead of completely relying on support images, we propose Self-Matching Transformation (SMT) to construct query-specific transformation matrices based on query images themselves to transform domain-specific query features into domain-agnostic ones.
no code implementations • 17 May 2024 • Tao Wu, Shuqiu Ge, Jie Qin, Gangshan Wu, LiMin Wang
Open-vocabulary spatio-temporal action detection (OV-STAD) requires training a model on a limited set of base classes with box and label supervision, which is expected to yield good generalization performance on novel action classes.
1 code implementation • 13 May 2024 • Qingguo Liu, Chenyi Zhuang, Pan Gao, Jie Qin
Existing Blind image Super-Resolution (BSR) methods focus on estimating either kernel or degradation information, but have long overlooked the essential content details.
no code implementations • 12 May 2024 • Jing Xu, Wentao Shi, Sheng Ren, Pan Gao, Peng Zhou, Jie Qin
In the field of transportation, it is of paramount importance to address and mitigate illegal actions committed by both motor and non-motor vehicles.
2 code implementations • 23 Apr 2024 • Yao Yuan, Wutao Liu, Pan Gao, Qun Dai, Jie Qin
Firstly, we propose a Progressive Curriculum Learning-based Saliency Distilling (PCL-SD) mechanism to extract saliency cues from a pre-trained deep network.
no code implementations • 18 Jan 2024 • Jie Qin, Jie Wu, Weifeng Chen, Yuxi Ren, Huixia Li, Hefeng Wu, Xuefeng Xiao, Rui Wang, Shilei Wen
Diffusion models have opened up new avenues for the field of image generation, resulting in the proliferation of high-quality models shared on open-source platforms.
1 code implementation • 12 Dec 2023 • Jinsong Shi, Pan Gao, Jie Qin
We first train a model on a large-scale synthetic dataset by SCL (no image subjective score is required) to extract degradation features of images with various distortion types and levels.
no code implementations • 11 Dec 2023 • Xiaoyi Bao, Jie Qin, Siyang Sun, Yun Zheng, Xingang Wang
To improve the semantic consistency of foreground instances, we propose an unlabeled branch as an efficient data utilization method, which teaches the model how to extract intrinsic features robust to intra-class differences.
no code implementations • 16 Oct 2023 • Junjie Li, Guanshuo Wang, Yichao Yan, Fufu Yu, Qiong Jia, Jie Qin, Shouhong Ding, Xiaokang Yang
Person search is a challenging task that involves detecting and retrieving individuals from a large set of un-cropped scene images.
1 code implementation • 13 Oct 2023 • Jiamei Liu, Han Sun, Yizhen Jia, Jie Qin, Huiyu Zhou, Ningzhong Liu
Domain adaptation aims to alleviate the domain shift when transferring the knowledge learned from the source domain to the target domain.
no code implementations • 7 Sep 2023 • Manlin Zhang, Jie Wu, Yuxi Ren, Ming Li, Jie Qin, Xuefeng Xiao, Wei Liu, Rui Wang, Min Zheng, Andy J. Ma
This paper reveals that the recently developed Diffusion Model is a scalable data engine for object detection.
no code implementations • ICCV 2023 • Guodong Wang, Yunhong Wang, Jie Qin, Dongming Zhang, Xiuguo Bao, Di Huang
Anomaly detection (AD), aiming to find samples that deviate from the training distribution, is essential in safety-critical applications.
no code implementations • 30 Jul 2023 • Pan Gao, Haoyue Tian, Jie Qin
Specifically, we design a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making our framework suitable for interpolating frames with large motion while maintaining reasonably low complexity.
1 code implementation • ICCV 2023 • Ming Li, Jie Wu, Xionghui Wang, Chen Chen, Jie Qin, Xuefeng Xiao, Rui Wang, Min Zheng, Xin Pan
To this end, we propose AlignDet, a unified pre-training framework that can be adapted to various existing detectors to alleviate the discrepancies.
no code implementations • CVPR 2023 • Jie Qin, Jie Wu, Pengxiang Yan, Ming Li, Ren Yuxi, Xuefeng Xiao, Yitong Wang, Rui Wang, Shilei Wen, Xin Pan, Xingang Wang
Recently, open-vocabulary learning has emerged to accomplish segmentation for arbitrary categories of text-based descriptions, which popularizes the segmentation system to more general-purpose application scenarios.
Ranked #6 on Open Vocabulary Panoptic Segmentation on ADE20K
1 code implementation • CVPR 2023 • Zhou Huang, Hang Dai, Tian-Zhu Xiang, Shuo Wang, Huai-Xin Chen, Jie Qin, Huan Xiong
Vision transformers have recently shown strong global context modeling capabilities in camouflaged object detection.
no code implementations • 10 Mar 2023 • Xinghong Liu, Yi Zhou, Tao Zhou, Jie Qin, Shengcai Liao
Open-set domain adaptation aims to not only recognize target samples belonging to common classes shared by source and target domains but also perceive unknown class samples.
2 code implementations • 28 Feb 2023 • Peng Zheng, Jie Qin, Shuo Wang, Tian-Zhu Xiang, Huan Xiong
To learn better group consensus, we propose the Group Consensus Aggregation Module (GCAM) to abstract the common features of each image group; meanwhile, to make the consensus representation more discriminative, we introduce the Memory-based Contrastive Module (MCM), which saves and updates the consensus of images from different groups in a queue of memories.
no code implementations • 29 Oct 2022 • Zhiheng Hu, Yongzhen Wang, Peng Li, Jie Qin, Haoran Xie, Mingqiang Wei
First, to maintain small targets in deep layers, we develop a multi-scale nested interaction module to explore a wide range of context information.
1 code implementation • 22 Aug 2022 • Jie Qin, Jie Wu, Ming Li, Xuefeng Xiao, Min Zheng, Xingang Wang
Consequently, we offer the first attempt to provide lightweight SSSS models via a novel multi-granularity distillation (MGD) scheme, where multi-granularity is captured from three aspects: i) complementary teacher structure; ii) labeled-unlabeled data cooperative distillation; iii) hierarchical and multi-levels loss setting.
Knowledge Distillation Semi-Supervised Semantic Segmentation
no code implementations • 12 Aug 2022 • Jingcheng Ni, Nan Zhou, Jie Qin, Qian Wu, Junqi Liu, Boxun Li, Di Huang
Contrastive learning has shown great potential in video representation learning.
1 code implementation • 20 Jul 2022 • Guodong Wang, Yunhong Wang, Jie Qin, Dongming Zhang, Xiuguo Bao, Di Huang
Video Anomaly Detection (VAD) is an important topic in computer vision.
Ranked #5 on Anomaly Detection on ShanghaiTech
no code implementations • 11 Jul 2022 • Jie Qin, Shuaihang Yuan, Jiaxin Chen, Boulbaba Ben Amor, Yi Fang, Nhat Hoang-Xuan, Chi-Bien Chu, Khoi-Nguyen Nguyen-Ngoc, Thien-Tri Cao, Nhat-Khang Ngo, Tuan-Luc Huynh, Hai-Dang Nguyen, Minh-Triet Tran, Haoyang Luo, Jianning Wang, Zheng Zhang, Zihao Xin, Yang Wang, Feng Wang, Ying Tang, Haiqin Chen, Yan Wang, Qunying Zhou, Ji Zhang, Hongyuan Wang
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
no code implementations • 22 Jun 2022 • Ming Li, Jie Wu, Jinhang Cai, Jie Qin, Yuxi Ren, Xuefeng Xiao, Min Zheng, Rui Wang, Xin Pan
Recently, Synthetic data-based Instance Segmentation has become an exceedingly favorable optimization paradigm since it leverages simulation rendering and physics to generate high-quality image-annotation pairs.
3 code implementations • 30 May 2022 • Peng Zheng, Huazhu Fu, Deng-Ping Fan, Qi Fan, Jie Qin, Yu-Wing Tai, Chi-Keung Tang, Luc van Gool
In this paper, we present a novel end-to-end group collaborative learning network, termed GCoNet+, which can effectively and efficiently (250 fps) identify co-salient objects in natural scenes.
Ranked #1 on Co-Salient Object Detection on CoCA
2 code implementations • 19 Apr 2022 • Bing Wang, Zhengdi Yu, Bo Yang, Jie Qin, Toby Breckon, Ling Shao, Niki Trigoni, Andrew Markham
We present RangeUDF, a new implicit representation based framework to recover the geometry and semantics of continuous 3D scene surfaces from point clouds.
1 code implementation • Information Sciences 2022 • Yuanyuan Liu, Chuanxu Feng, Xiaohui Yuan, Lin Zhou, Wenbin Wang, Jie Qin, and Zhongwen Luo
In this paper, we divide a video into several short clips for processing and propose a clip-aware emotion-rich feature learning network (CEFLNet) for robust video-based FER.
Ranked #16 on Dynamic Facial Expression Recognition on DFEW
Dynamic Facial Expression Recognition Facial Expression Recognition +1
1 code implementation • 21 Dec 2021 • Zichen Yang, Jie Qin, Di Huang
Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available.
Weakly-supervised Temporal Action Localization Weakly Supervised Temporal Action Localization
1 code implementation • 16 Dec 2021 • Jie Qin, Jie Wu, Xuefeng Xiao, Lujun Li, Xingang Wang
Extensive experiments show that AMR establishes a new state-of-the-art performance on the PASCAL VOC 2012 dataset, surpassing not only current methods trained with the image-level of supervision but also some methods relying on stronger supervision, such as saliency label.
1 code implementation • 5 Dec 2021 • Jie Qin, Peng Zheng, Yichao Yan, Rong Quan, Xiaogang Cheng, Bingbing Ni
Person search aims to jointly localize and identify a query person from natural, uncropped images, which has been actively studied over the past few years.
Ranked #3 on Person Search on CUHK-SYSU
no code implementations • 29 Nov 2021 • Yichao Yan, Junjie Li, Shengcai Liao, Jie Qin, Bingbing Ni, Xiaokang Yang
In the meantime, we design an adaptive BN layer in the domain-invariant stream, to approximate the statistics of various unseen domains.
Domain Generalization Generalizable Person Re-identification +1
4 code implementations • 1 Sep 2021 • Yichao Yan, Jinpeng Li, Jie Qin, Shengcai Liao, Xiaokang Yang
Third, by investigating the advantages of both anchor-based and anchor-free models, we further augment AlignPS with an ROI-Align head, which significantly improves the robustness of re-id features while still keeping our model highly efficient.
Ranked #4 on Person Search on PRW
no code implementations • 26 Aug 2021 • Jingcheng Ni, Jie Qin, Di Huang
Action detection plays an important role in high-level video understanding and media interpretation.
3 code implementations • 19 Jun 2021 • Yichao Yan, Jinpeng Li, Shengcai Liao, Jie Qin, Bingbing Ni, Xiaokang Yang, Ling Shao
This paper inventively considers weakly supervised person search with only bounding box annotations.
no code implementations • NeurIPS 2021 • Yuming Shen, Ziyi Shen, Menghan Wang, Jie Qin, Philip H. S. Torr, Ling Shao
On one hand, with the corresponding assignment variables being the weight, a weighted aggregation along the data points implements the set representation of a cluster.
1 code implementation • 29 Apr 2021 • Yichao Yan, Jie Qin, Bingbing Ni, Jiaxin Chen, Li Liu, Fan Zhu, Wei-Shi Zheng, Xiaokang Yang, Ling Shao
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
1 code implementation • CVPR 2021 • Yichao Yan, Jinpeng Li, Jie Qin, Song Bai, Shengcai Liao, Li Liu, Fan Zhu, Ling Shao
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id).
Ranked #10 on Person Search on CUHK-SYSU
1 code implementation • ICCV 2021 • Bing Wang, Changhao Chen, Zhaopeng Cui, Jie Qin, Chris Xiaoxuan Lu, Zhengdi Yu, Peijun Zhao, Zhen Dong, Fan Zhu, Niki Trigoni, Andrew Markham
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds.
1 code implementation • CVPR 2021 • Zhiqiang Shen, Zechun Liu, Jie Qin, Lei Huang, Kwang-Ting Cheng, Marios Savvides
In this paper, we focus on this more difficult scenario: learning networks where both weights and activations are binary, meanwhile, without any human annotated labels.
no code implementations • 8 Feb 2021 • Zhiqiang Shen, Zechun Liu, Jie Qin, Marios Savvides, Kwang-Ting Cheng
A common practice for this task is to train a model on the base set first and then transfer to novel classes through fine-tuning (Here fine-tuning procedure is defined as transferring knowledge from base to novel data, i. e. learning to transfer in few-shot scenario.)
1 code implementation • 21 Dec 2020 • Jie Qin, Jiemin Fang, Qian Zhang, Wenyu Liu, Xingang Wang, Xinggang Wang
Especially, CutMix uses a simple but effective method to improve the classifiers by randomly cropping a patch from one image and pasting it on another image.
no code implementations • 7 Oct 2020 • Fangbo Qin, Jie Qin, Siyu Huang, De Xu
For the novel CPI extraction task, we built the Object Contour Primitives dataset using online public images, and the Robotic Object Contour Measurement dataset using a camera mounted on a robot.
no code implementations • 27 Sep 2020 • Lei Huang, Jie Qin, Yi Zhou, Fan Zhu, Li Liu, Ling Shao
Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications.
1 code implementation • ECCV 2020 • Yuming Shen, Jie Qin, Lei Huang
Deep generative models have been successfully applied to Zero-Shot Learning (ZSL) recently.
2 code implementations • CVPR 2020 • Yuming Shen, Jie Qin, Jiaxin Chen, Mengyang Yu, Li Liu, Fan Zhu, Fumin Shen, Ling Shao
One bottleneck (i. e., binary codes) conveys the high-level intrinsic data structure captured by the code-driven graph to the other (i. e., continuous variables for low-level detail information), which in turn propagates the updated network feedback for the encoder to learn more discriminative binary codes.
no code implementations • ECCV 2020 • Lei Huang, Jie Qin, Li Liu, Fan Zhu, Ling Shao
To this end, we propose layer-wise conditioning analysis, which explores the optimization landscape with respect to each layer independently.
no code implementations • 13 Dec 2019 • Zhao Zhang, Zemin Tang, Zheng Zhang, Yang Wang, Jie Qin, Meng Wang
But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling operation may lose important feature information and is unlearnable; 2) the tradi-tional convolution operation optimizes slowly and the hierar-chical features from different layers are not fully utilized.
1 code implementation • 26 Aug 2019 • Yuming Shen, Jie Qin, Jiaxin Chen, Li Liu, Fan Zhu
Recent binary representation learning models usually require sophisticated binary optimization, similarity measure or even generative models as auxiliaries.
no code implementations • 27 May 2019 • Zhao Zhang, Weiming Jiang, Jie Qin, Li Zhang, Fanzhang Li, Min Zhang, Shuicheng Yan
Then we compute a linear classifier based on the approximated sparse codes by an analysis mechanism to simultaneously consider the classification and representation powers.
no code implementations • 25 May 2019 • Zhao Zhang, Weiming Jiang, Zheng Zhang, Sheng Li, Guangcan Liu, Jie Qin
More importantly, LC-PDL avoids using the complementary data matrix to learn the sub-dictionary over each class.
no code implementations • ECCV 2018 • Zheng Zhang, Li Liu, Jie Qin, Fan Zhu, Fumin Shen, Yong Xu, Ling Shao, Heng Tao Shen
How to economically cluster large-scale multi-view images is a long-standing problem in computer vision.
no code implementations • ECCV 2018 • Mengshi Qi, Jie Qin, Annan Li, Yunhong Wang, Jiebo Luo, Luc van Gool
Group activity recognition plays a fundamental role in a variety of applications, e. g. sports video analysis and intelligent surveillance.
1 code implementation • ECCV 2018 • Diwen Wan, Fumin Shen, Li Liu, Fan Zhu, Jie Qin, Ling Shao, Heng Tao Shen
Despite the remarkable success of Convolutional Neural Networks (CNNs) on generalized visual tasks, high computational and memory costs restrict their comprehensive applications on consumer electronics (e. g., portable or smart wearable devices).
no code implementations • 29 Mar 2018 • Zheng Liu, Jie Qin, Annan Li, Yunhong Wang, Luc van Gool
Specifically, instead of learning explicit projections or adding fully-connected mapping layers, the proposed Adversarial Binary Coding (ABC) framework guides the extraction of binary codes implicitly and effectively.
no code implementations • CVPR 2017 • Jiaxin Chen, Yunhong Wang, Jie Qin, Li Liu, Ling Shao
Numerous methods have been proposed for person re-identification, most of which however neglect the matching efficiency.
no code implementations • CVPR 2017 • Jie Qin, Li Liu, Ling Shao, Fumin Shen, Bingbing Ni, Jiaxin Chen, Yunhong Wang
Our ZSECOC equips the conventional ECOC with the additional capability of ZSAR, by addressing the domain shift problem.
Ranked #4 on Zero-Shot Action Recognition on Olympics
no code implementations • CVPR 2017 • Jie Qin, Li Liu, Ling Shao, Bingbing Ni, Chen Chen, Fumin Shen, Yunhong Wang
Extensive experiments on four realistic action datasets in terms of three tasks (i. e., partial action retrieval, recognition and prediction) clearly show the superiority of PRBC over the state-of-the-art methods, along with significantly reduced memory load and computational costs during the online test.