no code implementations • ECCV 2020 • Zerui Chen, Yan Huang, Hongyuan Yu, Bin Xue, Ke Han, Yiru Guo, Liang Wang
With roughly the same computational complexity as previous models, our approach achieves state-of-the-art results on both the single-person and multi-person 3D pose estimation benchmarks.
no code implementations • ECCV 2020 • Ke Han, Yan Huang, Zerui Chen, Liang Wang, Tieniu Tan
In this paper, we propose a novel Prediction, Recovery and Identification (PRI) model for LR re-id, which adaptively recovers missing details by predicting a preferable scale factor based on the image content.
no code implementations • 23 Jun 2022 • Dong An, Zun Wang, Yangguang Li, Yi Wang, Yicong Hong, Yan Huang, Liang Wang, Jing Shao
Our model consists of three modules: the candidate waypoints predictor (CWP), the history enhanced planner and the tryout controller.
no code implementations • 13 Jun 2022 • Yan Huang, Jizheng Xu, Li Zhang, Yan Zhao, Li Song
Inspired by rate control algorithms, we propose a scheme to precisely control the intra encoding complexity of VVC.
no code implementations • 22 Apr 2022 • Changxing Jing, Yan Huang, Yihong Zhuang, Liyan Sun, Yue Huang, Zhenlong Xiao, Xinghao Ding
This paper shows that it is possible to achieve flexible personalization after the convergence of the global model by introducing representation learning.
no code implementations • 21 Apr 2022 • Anni Tang, Yan Huang, Jun Ling, ZhiYu Zhang, Yiwei Zhang, Rong Xie, Li Song
As the latest video coding standard, versatile video coding (VVC) has shown its ability in retaining pixel quality.
no code implementations • CVPR 2022 • Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan
Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones.
no code implementations • 1 Mar 2022 • Ke Han, Chenyang Si, Yan Huang, Liang Wang, Tieniu Tan
In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain.
no code implementations • 9 Jan 2022 • Xiyang Hu, Yan Huang, Beibei Li, Tian Lu
We find two types of biases in gender, preference-based bias and belief-based bias, are present in human evaluators' decisions.
1 code implementation • NeurIPS 2021 • Keji He, Yan Huang, Qi Wu, Jianhua Yang, Dong An, Shuanglin Sima, Liang Wang
In Vision-and-Language Navigation (VLN) task, an agent is asked to navigate inside 3D indoor environments following given instructions.
1 code implementation • 17 Oct 2021 • Qing Yuan, Songfeng Lu, Yan Huang, Wuxin Sha
The former is non-differentiable and the latter needs a non-differentiable post-processing step to enforce connectivity, which constraints the integration of superpixels and downstream tasks.
no code implementations • 25 Aug 2021 • Cong Wang, Yan Huang, Yuexian Zou, Yong Xu
However, it is noted that ASM-based SIDM degrades its performance in dehazing real world hazy images due to the limited modelling ability of ASM where the atmospheric light factor (ALF) and the angular scattering coefficient (ASC) are assumed as constants for one image.
no code implementations • 22 Jul 2021 • Zhengxiong Luo, Zhicheng Wang, Yan Huang, Liang Wang, Tieniu Tan, Erjin Zhou
It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels.
1 code implementation • 15 Jul 2021 • Dong An, Yuankai Qi, Yan Huang, Qi Wu, Liang Wang, Tieniu Tan
Specifically, our NvEM utilizes a subject module and a reference module to collect contexts from neighbor views.
no code implementations • 24 Jun 2021 • Hadi Mansourifar, Dana Alsagheer, Reza Fathi, Weidong Shi, Lan Ni, Yan Huang
This makes the hate speech detection challenging in new social media like Clubhouse.
no code implementations • 22 Jun 2021 • Hadi Mansourifar, Dana Alsagheer, Weidong Shi, Lan Ni, Yan Huang
It has proven that, state-of-the-art hate speech classifiers are efficient only when tested on the data with the same feature distribution as training data.
1 code implementation • 16 Jun 2021 • Jianhua Yang, Yan Huang, Zhanyu Ma, Liang Wang
To solve this problem, we propose a simple yet effective Cascaded Multi-modal Fusion (CMF) module, which stacks multiple atrous convolutional layers in parallel and further introduces a cascaded branch to fuse visual and linguistic features.
1 code implementation • 14 May 2021 • Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan
More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of the ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}.
no code implementations • 12 May 2021 • Jiayi Lin, Yan Huang, Liang Wang
Recently, deformable alignment has drawn extensive attention in VSR community for its remarkable performance, which can adaptively align neighboring frames with the reference one.
no code implementations • 21 Jan 2021 • Cong Wang, Yan Huang, Yuexian Zou, Yong Xu
However, for images taken in real-world, the illumination is not uniformly distributed over whole image which brings model mismatch and possibly results in color shift of the deep models using ASM.
no code implementations • ICCV 2021 • Yan Huang, Qiang Wu, Jingsong Xu, Yi Zhong, Zhaoxiang Zhang
This work argues that these approaches in fact are not aware of clothing status (i. e., change or no-change) of a pedestrian.
1 code implementation • CVPR 2021 • Zhengxiong Luo, Zhicheng Wang, Yan Huang, Tieniu Tan, Erjin Zhou
However, for bottom-up methods, which need to handle a large variance of human scales and labeling ambiguities, the current practice seems unreasonable.
no code implementations • 13 Dec 2020 • Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai, GuanAn Wang, Yan Huang, Liang Wang, Erjin Zhou, Tieniu Tan, Jian Sun
Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method.
no code implementations • 10 Dec 2020 • Kewen Shi, Wenlong Cai, Sheng Jiang, Daoqian Zhu, Kaihua Cao, Zongxia Guo, Jiaqi Wei, Ao Du, Zhi Li, Yan Huang, Jialiang Yin, Johan Akerman, Weisheng Zhao
Magnetic droplets, a class of highly non-linear magnetodynamical solitons, can be nucleated and stabilized in nanocontact spin-torque nano-oscillators where they greatly increase the microwave output power.
Applied Physics
no code implementations • COLING 2020 • Jinhua Du, Yan Huang, Karo Moilanen
Recurrent neural networks (RNNs) suffer from well-known limitations and complications which include slow inference and vanishing gradients when processing long sequences in text classification.
no code implementations • 5 Nov 2020 • Junjie Pang, Jianbo Li, Zhenzhen Xie, Yan Huang, Zhipeng Cai
In this work, we propose a collaborative city digital twin based on FL, a novel paradigm that allowing multiple city DT to share the local strategy and status in a timely manner.
no code implementations • 2 Nov 2020 • Jianhua Yang, Yan Huang, Kai Niu, Zhanyu Ma, Liang Wang
We first learn the actor-/action-related content for the video and textual query, and then match them in a symmetrical manner to localize the target region.
Ranked #6 on
Referring Expression Segmentation
on J-HMDB
1 code implementation • NeurIPS 2020 • Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan
More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}.
Ranked #2 on
Blind Super-Resolution
on Set5 - 2x upscaling
no code implementations • 21 Aug 2020 • Qiaochu Wang, Yan Huang, Stefanus Jasin, Param Vir Singh
We show that, in some cases, even the predictive power of machine learning algorithms may increase if the firm makes them transparent.
no code implementations • 13 Aug 2020 • Hongyuan Yu, Yan Huang, Lihong Pi, Liang Wang
The RDN is a deconvolutional version of conventional recurrent neural network, which can well model the long-range temporal dependency of generated video frames and make good use of conditional information.
no code implementations • 20 Jul 2020 • Runshan Fu, Yan Huang, Param Vir Singh
We then use the machine to make investment decisions, and find that the machine benefits not only the lenders but also the borrowers.
3 code implementations • 18 Jun 2020 • Hongyuan Yu, Houwen Peng, Yan Huang, Jianlong Fu, Hao Du, Liang Wang, Haibin Ling
First, the search network generates an initial architecture for evaluation, and the weights of the evaluation network are optimized.
no code implementations • 25 Apr 2020 • Zhong Meng, Hu Hu, Jinyu Li, Changliang Liu, Yan Huang, Yifan Gong, Chin-Hui Lee
We propose a novel neural label embedding (NLE) scheme for the domain adaptation of a deep neural network (DNN) acoustic model with unpaired data samples from source and target domains.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Zheng Zhang, Lizi Liao, Xiaoyan Zhu, Tat-Seng Chua, Zitao Liu, Yan Huang, Minlie Huang
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment.
no code implementations • 12 Apr 2020 • Zhi Liu, Yan Huang, Jing Gao, Li Chen, Dong Li
Similar product recommendation is one of the most common scenes in e-commerce.
no code implementations • 10 Dec 2019 • Takuya Yoshioka, Igor Abramovski, Cem Aksoylar, Zhuo Chen, Moshe David, Dimitrios Dimitriadis, Yifan Gong, Ilya Gurvich, Xuedong Huang, Yan Huang, Aviv Hurvitz, Li Jiang, Sharon Koubi, Eyal Krupka, Ido Leichter, Changliang Liu, Partha Parthasarathy, Alon Vinnikov, Lingfeng Wu, Xiong Xiao, Wayne Xiong, Huaming Wang, Zhenghao Wang, Jun Zhang, Yong Zhao, Tianyan Zhou
This increases marginally to 1. 6% when 50% of the attendees are unknown to the system.
no code implementations • ICCV 2019 • Yan Huang, Liang Wang
Image and sentence matching has drawn much attention recently, but due to the lack of sufficient pairwise data for training, most previous methods still cannot well associate those challenging pairs of images and sentences containing rarely appeared regions and words, i. e., few-shot content.
no code implementations • ICCV 2019 • Yan Huang, Qiang Wu, JingSong Xu, Yi Zhong
We observe that if backgrounds in the training and testing datasets are very different, it dramatically introduces difficulties to extract robust pedestrian features, and thus compromises the cross-domain person re-ID performance.
no code implementations • 5 Aug 2019 • Chenglong Li, Yan Huang, Liang Wang, Jin Tang, Liang Lin
Many state-of-the-art trackers usually resort to the pretrained convolutional neural network (CNN) model for correlation filtering, in which deep features could usually be redundant, noisy and less discriminative for some certain instances, and the tracking performance might thus be affected.
no code implementations • 23 Jun 2019 • Kai Niu, Yan Huang, Wanli Ouyang, Liang Wang
Firstly, the global-global alignment in the Global Contrast (GC) module is for matching the global contexts of images and descriptions.
Ranked #10 on
Text based Person Retrieval
on CUHK-PEDES
1 code implementation • CVPR 2019 • Chunfeng Song, Yan Huang, Wanli Ouyang, Liang Wang
To address this problem, it is a good choice to learn to segment with weak supervision from bounding boxes.
no code implementations • NeurIPS 2018 • Zhen Zhang, Mianzhi Wang, Yijian Xiang, Yan Huang, Arye Nehorai
Graph-structured data arise in wide applications, such as computer vision, bioinformatics, and social networks.
1 code implementation • ECCV 2018 • Chenglong Li, Chengli Zhu, Yan Huang, Jin Tang, Liang Wang
To address this problem, this paper presents a novel approach to suppress background effects for RGB-T tracking.
no code implementations • 11 Jul 2018 • Yang Zhou, Yan Huang
DeepMove is spatial and temporal context aware.
no code implementations • CVPR 2018 • Zhen Zhang, Mianzhi Wang, Yan Huang, Arye Nehorai
Domain shift, which occurs when there is a mismatch between the distributions of training (source) and testing (target) datasets, usually results in poor performance of the trained model on the target domain.
1 code implementation • CVPR 2018 • Chunfeng Song, Yan Huang, Wanli Ouyang, Liang Wang
We may be the first one to successfully introduce the binary mask into person ReID task and the first one to propose region-level contrastive learning.
no code implementations • CVPR 2018 • Junbo Wang, Wei Wang, Yan Huang, Liang Wang, Tieniu Tan
Inspired by the facts that memory modelling poses potential advantages to long-term sequential problems [35] and working memory is the key factor of visual attention [33], we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide visual attention on described visual targets to solve visual-textual alignments.
no code implementations • 7 May 2018 • Wu Zheng, Lin Li, Zhao-Xiang Zhang, Yan Huang, Liang Wang
We introduce the Recurrent Relational Network to learn the spatial features in a single skeleton, followed by a multi-layer LSTM to learn the temporal features in the skeleton sequences.
Ranked #68 on
Skeleton Based Action Recognition
on NTU RGB+D
no code implementations • 21 Jan 2018 • Yan Huang, Jinsong Xu, Qiang Wu, Zhedong Zheng, Zhao-Xiang Zhang, Jian Zhang
Unlike the traditional label which usually is a single integral number, the virtual label proposed in this work is a set of weight-based values each individual of which is a number in (0, 1] called multi-pseudo label and reflects the degree of relation between each generated data to every pre-defined class of real data.
no code implementations • CVPR 2018 • Yan Huang, Qi Wu, Liang Wang
This mainly arises from that the representation of pixel-level image usually lacks of high-level semantic information as in its matched sentence.
Ranked #10 on
Image Retrieval
on Flickr30K 1K test
1 code implementation • 14 Nov 2017 • Qiang Cui, Shu Wu, Yan Huang, Liang Wang
We fuse the current hidden state and a contextual hidden state built by the attention mechanism, which leads to a more suitable user's overall interest.
no code implementations • CVPR 2017 • Zhen Zhou, Yan Huang, Wei Wang, Liang Wang, Tieniu Tan
Accordingly, a demanding need is to recognize a person under different cameras, which is called person re-identification.
no code implementations • CVPR 2017 • Yan Huang, Wei Wang, Liang Wang
Based on the observation that such a global similarity arises from a complex aggregation of multiple local similarities between pairwise instances of image (objects) and sentence (words), we propose a selective multimodal Long Short-Term Memory network (sm-LSTM) for instance-aware image and sentence matching.
Ranked #13 on
Image Retrieval
on Flickr30K 1K test
no code implementations • 17 Nov 2016 • Junbo Wang, Wei Wang, Yan Huang, Liang Wang, Tieniu Tan
In this paper, we propose a Multimodal Memory Model (M3) to describe videos, which builds a visual and textual shared memory to model the long-term visual-textual dependency and further guide global visual attention on described targets.
no code implementations • CVPR 2016 • Yuhui Quan, Yong Xu, Yuping Sun, Yan Huang, Hui Ji
Discriminative sparse coding has emerged as a promising technique in image analysis and recognition, which couples the process of classifier training and the process of dictionary learning for improving the discriminability of sparse codes.
no code implementations • EMNLP 2016 • Yevgeni Berzak, Yan Huang, Andrei Barbu, Anna Korhonen, Boris Katz
Our agreement results control for parser bias, and are consequential in that they are on par with state of the art parsing performance for English newswire.
no code implementations • ICCV 2015 • Yan Huang, Wei Wang, Liang Wang
Relation learning is a fundamental operation in many computer vision tasks.
no code implementations • ICCV 2015 • Yuhui Quan, Yan Huang, Hui Ji
In addition, based on the proposed dictionary learning method, a DT descriptor is developed, which has better adaptivity, discriminability and scalability than the existing approaches.
no code implementations • NeurIPS 2015 • Yan Huang, Wei Wang, Liang Wang
Super resolving a low-resolution video is usually handled by either single-image super-resolution (SR) or multi-frame SR. Single-Image SR deals with each video frame independently, and ignores intrinsic temporal dependency of video frames which actually plays a very important role in video super-resolution.
Ranked #15 on
Video Super-Resolution
on Vid4 - 4x upscaling
no code implementations • ACM SIGSPATIAL GIS 2010 2010 • Jing Yuan, Yu Zheng, Chengyang Zhang, Wenlei Xie, Xing Xie, Guangzhong Sun, Yan Huang
GPS-equipped taxis can be regarded as mobile sensors probing traffic flows on road surfaces, and taxi drivers are usually experienced in finding the fastest (quickest) route to a destination based on their knowledge.