1 code implementation • ECCV 2020 • Mingfei Han, Yali Wang, Xiaojun Chang, Yu Qiao
Recent studies have shown that, context aggregating information from proposals in different frames can clearly enhance the performance of video object detection.
Ranked #1 on
Video Object Detection
on ImageNet VID
no code implementations • 22 May 2022 • Sihao Lin, Hongwei Xie, Bing Wang, Kaicheng Yu, Xiaojun Chang, Xiaodan Liang, Gang Wang
To this end, we propose a novel one-to-all spatial matching knowledge distillation approach.
no code implementations • 20 May 2022 • Qinghua Zheng, Jihong Wang, Minnan Luo, YaoLiang Yu, Jundong Li, Lina Yao, Xiaojun Chang
Due to the superior performance of Graph Neural Networks (GNNs) in various domains, there is an increasing interest in the GNN explanation problem "\emph{which fraction of the input graph is the most crucial to decide the model's decision?}"
no code implementations • 27 Apr 2022 • Yameng Peng, Andy Song, Vic Ciesielski, Haytham M. Fayek, Xiaojun Chang
This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space during the search.
no code implementations • 5 Apr 2022 • Mingfei Han, David Junhao Zhang, Yali Wang, Rui Yan, Lina Yao, Xiaojun Chang, Yu Qiao
Learning spatial-temporal relation among multiple actors is crucial for group activity recognition.
1 code implementation • 28 Mar 2022 • Changlin Li, Bohan Zhuang, Guangrun Wang, Xiaodan Liang, Xiaojun Chang, Yi Yang
First, we develop a strong manual baseline for progressive learning of ViTs, by introducing momentum growth (MoGrow) to bridge the gap brought by model growth.
no code implementations • 27 Mar 2022 • Chengyou Jia, Minnan Luo, Caixia Yan, Xiaojun Chang, Qinghua Zheng
On the other hand, there are numerous unpaired persons in real-world scene images.
1 code implementation • 24 Mar 2022 • Pengzhen Ren, Changlin Li, Guangrun Wang, Yun Xiao, Qing Du, Xiaodan Liang, Xiaojun Chang
Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window.
1 code implementation • 8 Feb 2022 • Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang
Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation.
no code implementations • 6 Jan 2022 • Yun Li, Zhe Liu, Lina Yao, Xiaojun Chang
In this paper, we propose an end-to-end network with balanced generalization and specialization abilities, termed as BGSNet, to take advantage of both abilities, and balance them at instance- and dataset-level.
no code implementations • 25 Nov 2021 • Miao Zhang, Jilin Hu, Steven Su, Shirui Pan, Xiaojun Chang, Bin Yang, Gholamreza Haffari
Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation.
no code implementations • 3 Nov 2021 • Yun Li, Zhe Liu, Lina Yao, Xianzhi Wang, Julian McAuley, Xiaojun Chang
Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations.
no code implementations • 22 Oct 2021 • Ali Hamdi, Flora Salim, Du Yong Kim, Xiaojun Chang
SGN constructs unique undirected graphs for each image based on the CNN feature maps.
no code implementations • 17 Oct 2021 • Zutao Jiang, Changlin Li, Xiaojun Chang, Jihua Zhu, Yi Yang
Here, we present dynamic slimmable denoising network (DDS-Net), a general method to achieve good denoising quality with less computational complexity, via dynamically adjusting the channel configurations of networks at test time with respect to different noisy images.
no code implementations • 17 Oct 2021 • Di Yuan, Xiaojun Chang, Yi Yang, Qiao Liu, Dehua Wang, Zhenyu He
In this paper, we propose an active learning method for deep visual tracking, which selects and annotates the unlabeled samples to train the deep CNNs model.
no code implementations • 12 Oct 2021 • Minnan Luo, Xiaojun Chang, Chen Gong
In this paper, we decompose the video into several segments and intuitively model the task of complex event detection as a multiple instance learning problem by representing each video as a "bag" of segments in which each segment is referred to as an instance.
no code implementations • 29 Sep 2021 • Siyi Hu, Chuanlong Xie, Xiaodan Liang, Xiaojun Chang
In addition, role diversity can help to find a better training strategy and increase performance in cooperative MARL.
1 code implementation • 21 Sep 2021 • Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference.
no code implementations • 4 Sep 2021 • Caixia Yan, Xiaojun Chang, Minnan Luo, Huan Liu, Xiaoqin Zhang, Qinghua Zheng
To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection.
no code implementations • 1 Sep 2021 • Xiangtan Lin, Pengzhen Ren, Chung-Hsing Yeh, Lina Yao, Andy Song, Xiaojun Chang
Therefore, comprehensive surveys on this topic are essential to summarise challenges and solutions to foster future research.
1 code implementation • Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2) 2021 • Mingjie Li, Wenjia Cai, Rui Liu, Yuetian Weng, Xiaoyun Zhao, Cong Wang, Xin Chen, Zhong Liu, Caineng Pan, Mengke Li, Yizhi Liu, Flora D Salim, Karin Verspoor, Xiaodan Liang, Xiaojun Chang
Researchers have explored advanced methods from computer vision and natural language processing to incorporate medical domain knowledge for the generation of readable medical reports.
1 code implementation • 9 Aug 2021 • Shangbin Feng, Zilong Chen, Wenqian Zhang, Qingyao Li, Qinghua Zheng, Xiaojun Chang, Minnan Luo
Specifically, we construct a political knowledge graph to serve as domain-specific external knowledge.
no code implementations • 9 Aug 2021 • Shangbin Feng, Zhaoxuan Tan, Zilong Chen, Peisheng Yu, Qinghua Zheng, Xiaojun Chang, Minnan Luo
Modeling the ideological perspectives of political actors is an essential task in computational political science with applications in many downstream tasks.
no code implementations • 7 Jul 2021 • Fengda Zhu, Yi Zhu, Vincent CS Lee, Xiaodan Liang, Xiaojun Chang
A navigation agent is supposed to have various intelligent skills, such as visual perceiving, mapping, planning, exploring and reasoning, etc.
no code implementations • 22 Jun 2021 • Miao Zhang, Steven Su, Shirui Pan, Xiaojun Chang, Wei Huang, Bin Yang, Gholamreza Haffari
Although Differentiable ARchiTecture Search (DARTS) has become the mainstream paradigm in Neural Architecture Search (NAS) due to its simplicity and efficiency, more recent works found that the performance of the searched architecture barely increases with the optimization proceeding in DARTS, and the final magnitudes obtained by DARTS could hardly indicate the importance of operations.
1 code implementation • 21 Jun 2021 • Miao Zhang, Steven Su, Shirui Pan, Xiaojun Chang, Ehsan Abbasnejad, Reza Haffari
A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation.
1 code implementation • ICCV 2021 • Chong Liu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang, ZongYuan Ge, Yi-Dong Shen
Then, we cross-connect the key views of different scenes to construct augmented scenes.
Ranked #26 on
Vision and Language Navigation
on VLN Challenge
no code implementations • 1 May 2021 • Xiangtan Lin, Pengzhen Ren, Yun Xiao, Xiaojun Chang, Alex Hauptmann
This paper surveyed the recent works on image-based and text-based person search from the perspective of challenges and solutions.
no code implementations • 22 Apr 2021 • Yun Li, Zhe Liu, Lina Yao, Xiaojun Chang
The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned on semantic side information and to incorporate meta-learning to eliminate the model's inherent bias towards seen classes.
no code implementations • CVPR 2021 • Fengda Zhu, Xiwen Liang, Yi Zhu, Xiaojun Chang, Xiaodan Liang
In this task, an agent is required to navigate from an arbitrary position in a 3D embodied environment to localize a target following a scene description.
1 code implementation • CVPR 2021 • Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang
Here, we explore a dynamic network slimming regime, named Dynamic Slimmable Network (DS-Net), which aims to achieve good hardware-efficiency via dynamically adjusting filter numbers of networks at test time with respect to different inputs, while keeping filters stored statically and contiguously in hardware to prevent the extra burden.
1 code implementation • ICCV 2021 • Changlin Li, Tao Tang, Guangrun Wang, Jiefeng Peng, Bing Wang, Xiaodan Liang, Xiaojun Chang
In this work, we present Block-wisely Self-supervised Neural Architecture Search (BossNAS), an unsupervised NAS method that addresses the problem of inaccurate architecture rating caused by large weight-sharing space and biased supervision in previous methods.
no code implementations • 17 Mar 2021 • Xiaojun Chang, Pengzhen Ren, Pengfei Xu, Zhihui Li, Xiaojiang Chen, Alex Hauptmann
For example, given an image, we want to not only detect and recognize objects in the image, but also know the relationship between objects (visual relationship detection), and generate a text description (image captioning) based on the image content.
no code implementations • 17 Mar 2021 • Pengzhen Ren, Gang Xiao, Xiaojun Chang, Yun Xiao, Zhihui Li, Xiaojiang Chen
Accordingly, because of the automated design of its network structure, Neural architecture search (NAS) has achieved great success in the image processing field and attracted substantial research attention in recent years.
1 code implementation • 20 Jan 2021 • Siyi Hu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang
Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task.
no code implementations • 1 Jan 2021 • Xuanli He, Lingjuan Lyu, Lichao Sun, Xiaojun Chang, Jun Zhao
We then demonstrate how the extracted model can be exploited to develop effective attribute inference attack to expose sensitive information of the training data.
no code implementations • ICLR 2021 • Siyi Hu, Fengda Zhu, Xiaojun Chang, Xiaodan Liang
Recent advances in multi-agent reinforcement learning have been largely limited in training one model from scratch for every new task.
1 code implementation • ICCV 2021 • Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang
Extensive experiments on two vision tasks, including ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consistently outperforms many existing methods, advancing the state-of-the-art in the fields of Knowledge Distillation.
Ranked #6 on
Knowledge Distillation
on ImageNet
1 code implementation • NeurIPS 2020 • Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, ZongYuan Ge, Steven Su
A probabilistic exploration enhancement method is accordingly devised to encourage intelligent exploration during the architecture search in the latent space, to avoid local optimal in architecture search.
1 code implementation • NeurIPS 2020 • Xuelian Cheng, Yiran Zhong, Mehrtash Harandi, Yuchao Dai, Xiaojun Chang, Tom Drummond, Hongdong Li, ZongYuan Ge
To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classification and semantic segmentation.
Ranked #2 on
Stereo Disparity Estimation
on Scene Flow
no code implementations • 24 Sep 2020 • Caixia Yan, Xiaojun Chang, Minnan Luo, Qinghua Zheng, Xiaoqin Zhang, Zhihui Li, Feiping Nie
In this regard, a novel self-weighted robust LDA with l21-norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes.
1 code implementation • 30 Aug 2020 • Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Brij B. Gupta, Xiaojiang Chen, Xin Wang
Therefore, deep active learning (DAL) has emerged.
no code implementations • 3 Jul 2020 • Di Yuan, Xiu Shu, Nana Fan, Xiaojun Chang, Qiao Liu, Zhenyu He
Moreover, we introduce a classification part that is trained online and optimized with a Conjugate-Gradient-based strategy to guarantee real-time tracking speed.
no code implementations • 23 Jun 2020 • Siyi Hu, Xiaojun Chang
In this paper, we focus on the task of multi-view multi-source geo-localization, which serves as an important auxiliary method of GPS positioning by matching drone-view image and satellite-view image with pre-annotated GPS tag.
no code implementations • 19 Jun 2020 • Zhen Yu, Jennifer Nguyen, Xiaojun Chang, John Kelly, Catriona Mclean, Lei Zhang, Victoria Mar, ZongYuan Ge
Existing studies for automated melanoma diagnosis are based on single-time point images of lesions.
no code implementations • 6 Jun 2020 • Mingjie Li, Fuyu Wang, Xiaojun Chang, Xiaodan Liang
Firstly, the regions of primary interest to radiologists are usually located in a small area of the global image, meaning that the remainder parts of the image could be considered as irrelevant noise in the training procedure.
no code implementations • 1 Jun 2020 • Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-Yao Huang, Zhihui Li, Xiaojiang Chen, Xin Wang
Neural Architecture Search (NAS) is just such a revolutionary algorithm, and the related research work is complicated and rich.
3 code implementations • 24 May 2020 • Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, Chengqi Zhang
Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic.
Ranked #2 on
Univariate Time Series Forecasting
on Electricity
no code implementations • ACL 2020 • Po-Yao Huang, Junjie Hu, Xiaojun Chang, Alexander Hauptmann
In this paper, we investigate how to utilize visual content for disambiguation and promoting latent space alignment in unsupervised MMT.
1 code implementation • CVPR 2020 • Yi Zhu, Fengda Zhu, Zhaohuan Zhan, Bingqian Lin, Jianbin Jiao, Xiaojun Chang, Xiaodan Liang
Benefiting from the collaborative learning of the L-mem and the V-mem, our CMN is able to explore the memory about the decision making of historical navigation actions which is for the current step.
no code implementations • CVPR 2020 • Lingling Zhang, Xiaojun Chang, Jun Liu, Minnan Luo, Sen Wang, ZongYuan Ge, Alexander Hauptmann
An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos.
no code implementations • CVPR 2020 • Chong Liu, Xiaojun Chang, Yi-Dong Shen
To solve this problem, we propose a UnityStyle adaption method, which can smooth the style disparities within the same camera and across different cameras.
1 code implementation • Proceedings of the IEEE Winter Conference on Applications of Computer Vision Workshops 2020 • Wenhe Liu, Guoliang Kang, Po-Yao Huang, Xiaojun Chang, Yijun Qian, Junwei Liang, Liangke Gui, Jing Wen, Peng Chen
We propose an Efficient Activity Detection System, Argus, for Extended Video Analysis in the surveillance scenario.
1 code implementation • 29 Nov 2019 • Changlin Li, Jiefeng Peng, Liuchun Yuan, Guangrun Wang, Xiaodan Liang, Liang Lin, Xiaojun Chang
Moreover, we find that the knowledge of a network model lies not only in the network parameters but also in the network architecture.
Ranked #1 on
Neural Architecture Search
on CIFAR-100
(Top-1 Error Rate metric)
no code implementations • CVPR 2020 • Fengda Zhu, Yi Zhu, Xiaojun Chang, Xiaodan Liang
In this paper, we introduce Auxiliary Reasoning Navigation (AuxRN), a framework with four self-supervised auxiliary reasoning tasks to take advantage of the additional training signals derived from the semantic information.
Ranked #7 on
Vision and Language Navigation
on VLN Challenge
no code implementations • IJCNLP 2019 • Po-Yao Huang, Xiaojun Chang, Alexander Hauptmann
With the aim of promoting and understanding the multilingual version of image search, we leverage visual object detection and propose a model with diverse multi-head attention to learn grounded multilingual multimodal representations.
no code implementations • 21 Jun 2019 • Fengda Zhu, Xiaojun Chang, Runhao Zeng, Mingkui Tan
We first develop an unsupervised diversity exploration method to learn task-specific skills using an unsupervised objective.
no code implementations • 8 Apr 2019 • Chen Gong, DaCheng Tao, Xiaojun Chang, Jian Yang
More importantly, HyDEnT conducts propagation under the guidance of an ensemble of teachers.
no code implementations • 12 Nov 2018 • Zhiyong Cheng, Xiaojun Chang, Lei Zhu, Rose C. Kanjirathinkal, Mohan Kankanhalli
Then the aspect importance is integrated into a novel aspect-aware latent factor model (ALFM), which learns user's and item's latent factors based on ratings.
no code implementations • 12 Nov 2018 • Kaixuan Chen, Lina Yao, Dalin Zhang, Xiaojun Chang, Guodong Long, Sen Wang
Semi-supervised learning is crucial for alleviating labelling burdens in people-centric sensing.
no code implementations • ECCV 2018 • Xiaojun Chang, Po-Yao Huang, Yi-Dong Shen, Xiaodan Liang, Yi Yang, Alexander G. Hauptmann
In this paper, we address this problem by training relational context-aware agents which learn the actions to localize the target person from the gallery of whole scene images.
no code implementations • 3 Aug 2018 • Ting-yao Hu, Xiaojun Chang, Alexander G. Hauptmann
In this work, we propose the idea of visual distributional representation, which interprets an image set as samples drawn from an unknown distribution in appearance feature space.
no code implementations • CVPR 2018 • Junwei Han, Le Yang, Dingwen Zhang, Xiaojun Chang, Xiaodan Liang
In this paper, we formulate this problem as a Markov Decision Process, where agents are learned to segment object regions under a deep reinforcement learning framework.
no code implementations • ICCV 2017 • Hehe Fan, Xiaojun Chang, De Cheng, Yi Yang, Dong Xu, Alexander G. Hauptmann
relevant) to the given event class, we formulate this task as a multi-instance learning (MIL) problem by taking each video as a bag and the video shots in each video as instances.
no code implementations • 4 Feb 2017 • Minnan Luo, Xiaojun Chang, Zhihui Li, Liqiang Nie, Alexander G. Hauptmann, Qinghua Zheng
The heterogeneity-gap between different modalities brings a significant challenge to multimedia information retrieval.
no code implementations • 9 Jul 2016 • Sen Wang, Feiping Nie, Xiaojun Chang, Xue Li, Quan Z. Sheng, Lina Yao
We propose a method that utilizes both the manifold structure of data and local discriminant information.
no code implementations • 17 Jun 2016 • Shoou-I Yu, Yi Yang, Zhongwen Xu, Shicheng Xu, Deyu Meng, Zexi Mao, Zhigang Ma, Ming Lin, Xuanchong Li, Huan Li, Zhenzhong Lan, Lu Jiang, Alexander G. Hauptmann, Chuang Gan, Xingzhong Du, Xiaojun Chang
The large number of user-generated videos uploaded on to the Internet everyday has led to many commercial video search engines, which mainly rely on text metadata for search.
no code implementations • CVPR 2016 • Xiaojun Chang, Yao-Liang Yu, Yi Yang, Eric P. Xing
Complex event detection on unconstrained Internet videos has seen much progress in recent years.
no code implementations • 14 Jan 2016 • Xiaojun Chang, Yi Yang, Guodong Long, Chengqi Zhang, Alexander G. Hauptmann
In this paper, we focus on automatically detecting events in unconstrained videos without the use of any visual training exemplars.
no code implementations • 3 Jun 2015 • Sen Wang, Feiping Nie, Xiaojun Chang, Lina Yao, Xue Li, Quan Z. Sheng
In this paper, we propose an unsupervised feature selection method seeking a feature coefficient matrix to select the most distinctive features.
no code implementations • 23 Nov 2014 • Xiaojun Chang, Feiping Nie, Sen Wang, Yi Yang, Xiaofang Zhou, Chengqi Zhang
In many real-world applications, data are represented by matrices or high-order tensors.
no code implementations • 23 Nov 2014 • Xiaojun Chang, Feiping Nie, Yi Yang, Heng Huang
Our algorithm is built upon two advancements of the state of the art:1) label propagation, which propagates a node\'s labels to neighboring nodes according to their proximity; and 2) manifold learning, which has been widely used in its capacity to leverage the manifold structure of data points.
no code implementations • 23 Nov 2014 • Xiaojun Chang, Feiping Nie, Zhigang Ma, Yi Yang, Xiaofang Zhou
Thus, applying manifold information obtained from the original space to the clustering process in a low-dimensional subspace is prone to inferior performance.
no code implementations • 23 Nov 2014 • Xiaojun Chang, Feiping Nie, Zhigang Ma, Yi Yang
Clustering is an effective technique in data mining to generate groups that are the matter of interest.
no code implementations • 23 Nov 2014 • Xiaojun Chang, Feiping Nie, Yi Yang, Heng Huang
In addition, based on the sparse model used in CSPCA, an optimal weight is assigned to each of the original feature, which in turn provides the output with good interpretability.
no code implementations • 23 Nov 2014 • Xiaojun Chang, Yi Yang
In this paper, we propose a novel semi-supervised feature selection framework by mining correlations among multiple tasks and apply it to different multimedia applications.