no code implementations • 10 Mar 2024 • Hanxin Zhu, Tianyu He, Xin Li, Bingchen Li, Zhibo Chen
Neural Radiance Field (NeRF) has achieved superior performance for novel view synthesis by modeling the scene with a Multi-Layer Perception (MLP) and a volume rendering procedure, however, when fewer known views are given (i. e., few-shot view synthesis), the model is prone to overfit the given views.
no code implementations • 29 Feb 2024 • Bingchen Li, Xin Li, Hanxin Zhu, Yeying Jin, Ruoyu Feng, Zhizheng Zhang, Zhibo Chen
In particular, one discriminator is utilized to enable the SR network to learn the distribution of real-world high-quality images in an adversarial training manner.
no code implementations • 26 Feb 2024 • Hanxin Zhu, Tianyu He, Zhibo Chen
Furthermore, to regularize the unseen target views, we constrain the rendered colors and depths from different input views to be the same.
no code implementations • 11 Feb 2024 • Yiting Lu, Xin Li, Yajing Pei, Kun Yuan, Qizhi Xie, Yunpeng Qu, Ming Sun, Chao Zhou, Zhibo Chen
Short-form UGC video platforms, like Kwai and TikTok, have been an emerging and irreplaceable mainstream media form, thriving on user-friendly engagement, and kaleidoscope creation, etc.
no code implementations • 25 Jan 2024 • Henan Wang, Xiaohan Pan, Runsen Feng, Zongyu Guo, Zhibo Chen
This document is an expanded version of a one-page abstract originally presented at the 2024 Data Compression Conference.
no code implementations • 16 Jan 2024 • Zihao Yu, Fengbin Guan, Yiting Lu, Xin Li, Zhibo Chen
Furthermore, a temporal transformer is utilized for spatiotemporal feature fusion across the video.
no code implementations • 25 Dec 2023 • Chen Hou, Guoqiang Wei, Zhibo Chen
Diffusion models have attained remarkable success in the domains of image generation and editing.
no code implementations • 20 Oct 2023 • Guangqi Xie, Xin Li, Xiaohan Pan, Zhibo Chen
Remote medical diagnosis has emerged as a critical and indispensable technique in practical medical systems, where medical data are required to be efficiently compressed and transmitted for diagnosis by either professional doctors or intelligent diagnosis devices.
no code implementations • 29 Sep 2023 • Xin Li, Yiting Lu, Zhibo Chen
Based on this, we propose to improve the perception-oriented transferability of BIQA by performing feature frequency decomposition and selecting the frequency components that contained the most transferable perception knowledge for alignment.
Blind Image Quality Assessment Unsupervised Domain Adaptation
no code implementations • 28 Sep 2023 • Ruoyu Feng, Wenming Weng, Yanhui Wang, Yuhui Yuan, Jianmin Bao, Chong Luo, Zhibo Chen, Baining Guo
The versatility of our framework is demonstrated through a diverse range of choices in both structure representations and personalized T2I models, as well as the option to provide the edited key frame.
1 code implementation • NeurIPS 2023 • Xin Li, Dongze Lian, Zhihe Lu, Jiawang Bai, Zhibo Chen, Xinchao Wang
To mitigate that, we propose an effective adapter-style tuning strategy, dubbed GraphAdapter, which performs the textual adapter by explicitly modeling the dual-modality structure knowledge (i. e., the correlation of different semantics/classes in textual and visual modalities) with a dual knowledge graph.
1 code implementation • 18 Aug 2023 • Xin Li, Yulin Ren, Xin Jin, Cuiling Lan, Xingrui Wang, Wenjun Zeng, Xinchao Wang, Zhibo Chen
Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various forms of degradation.
1 code implementation • NeurIPS 2023 • Zongyu Guo, Gergely Flamich, Jiajun He, Zhibo Chen, José Miguel Hernández-Lobato
Many common types of data can be represented as functions that map coordinates to signal values, such as pixel locations to RGB values in the case of an image.
1 code implementation • CVPR 2023 • Runsen Feng, Zongyu Guo, Weiping Li, Zhibo Chen
In theory, vector quantization (VQ) is always better than scalar quantization (SQ) in terms of rate-distortion (R-D) performance.
no code implementations • 12 May 2023 • Yixin Gao, Runsen Feng, Zongyu Guo, Zhibo Chen
By quantifying the decoding complexity as a factor in the optimization goal, we are now able to precisely control the RDC trade-off and then demonstrate how the rate-distortion performance of neural image codecs could adapt to various complexity demands.
no code implementations • 4 May 2023 • Ruoyu Feng, Jinming Liu, Xin Jin, Xiaohan Pan, Heming Sun, Zhibo Chen
For ICM, developing a unified codec to reduce information redundancy while empowering the compressed features to support various vision tasks is very important, which inevitably faces two core challenges: 1) How should the compression strategy be adjusted based on the downstream tasks?
no code implementations • ICCV 2023 • Ruoyu Feng, Yixin Gao, Xin Jin, Runsen Feng, Zhibo Chen
Nevertheless, they divide the input image into multiple rectangular regions according to semantics and ignore avoiding information interaction among them, causing waste of bitrate and distorted reconstruction of region boundaries.
1 code implementation • 13 Apr 2023 • Tao Yu, Runseng Feng, Ruoyu Feng, Jinming Liu, Xin Jin, Wenjun Zeng, Zhibo Chen
We are also very willing to help everyone share and promote new projects based on our Inpaint Anything (IA).
2 code implementations • CVPR 2023 • Xin Li, Bingchen Li, Xin Jin, Cuiling Lan, Zhibo Chen
In this paper, we are the first to propose a novel training strategy for image restoration from the causality perspective, to improve the generalization ability of DNNs for unknown degradations.
1 code implementation • 21 Jan 2023 • Zongyu Guo, Cuiling Lan, Zhizheng Zhang, Yan Lu, Zhibo Chen
In this paper, we propose an efficient NP framework dubbed Versatile Neural Processes (VNP), which largely increases the capability of approximating functions.
1 code implementation • 6 Dec 2022 • Xin Li, Cuiling Lan, Guoqiang Wei, Zhibo Chen
In this way, our message broadcasting encourages the group tokens to learn more informative and diverse information for effective domain alignment.
Ranked #1 on Unsupervised Domain Adaptation on VisDA2017
1 code implementation • CVPR 2023 • Tao Yu, Zhihe Lu, Xin Jin, Zhibo Chen, Xinchao Wang
Large-scale vision-language models (VLMs) pre-trained on billion-level data have learned general visual representations and broad visual concepts.
no code implementations • 17 Sep 2022 • Hanxin Zhu, Henan Wang, Zhibo Chen
Unlike explicit representation that represents light fields as Sub-Aperture Images (SAIs) based arrays or Micro-Images (MIs) based lenslet images, implicit representation treats light fields as neural networks, which is inherently a continuous representation in contrast to discrete explicit representation.
no code implementations • 24 Aug 2022 • Guangqi Xie, Xin Li, Shiqi Lin, Li Zhang, Kai Zhang, Yue Li, Zhibo Chen
In this paper, we take a step forward to video semantic compression and propose the Hierarchical Reinforcement Learning based task-driven Video Semantic Coding, named as HRLVSC.
Hierarchical Reinforcement Learning reinforcement-learning +3
no code implementations • 24 Aug 2022 • Xiaoshuai Fan, Xin Li, Zhibo Chen
Our proposed transcoding architecture shows significant superiority in the compression of JPEG images thanks to the collaboration of learned lossy transform coding and residual entropy coding.
3 code implementations • 21 Aug 2022 • Bingchen Li, Xin Li, Yiting Lu, Sen Liu, Ruoyu Feng, Zhibo Chen
Compressed Image Super-resolution has achieved great attention in recent years, where images are degraded with compression artifacts and low-resolution artifacts.
Ranked #1 on Compressed Image Super-resolution on DIV2K-q40-x4
no code implementations • 29 Jul 2022 • Yiting Lu, Xin Li, Jianzhao Liu, Zhibo Chen
Specifically, we find a more compact and reliable space i. e., feature style space for perception-oriented UDA based on an interesting/amazing observation, that the feature style (i. e., the mean and variance) of the deep layer in DNNs is exactly associated with the quality score in NR-IQA.
no code implementations • 17 Jul 2022 • Jianzhao Liu, Xin Li, Shukun An, Zhibo Chen
Thanks to the development of unsupervised domain adaptation (UDA), some works attempt to transfer the knowledge from a label-sufficient source domain to a label-free target domain under domain shift with UDA.
Blind Image Quality Assessment Unsupervised Domain Adaptation
no code implementations • 13 Jul 2022 • Yiting Lu, Jun Fu, Xin Li, Wei Zhou, Sen Liu, Xinxin Zhang, Congfu Jia, Ying Liu, Zhibo Chen
Therefore, we propose a Progressive Reinforcement learning based Instance Discarding module (termed as PRID) to progressively remove quality-irrelevant/negative instances for CCTA VIQA.
no code implementations • 5 Jul 2022 • Ruoyu Feng, Xin Jin, Zongyu Guo, Runsen Feng, Yixin Gao, Tianyu He, Zhizheng Zhang, Simeng Sun, Zhibo Chen
Learning a kind of feature that is both general (for AI tasks) and compact (for compression) is pivotal for its success.
1 code implementation • 9 May 2022 • Jianzhao Liu, Xin Li, Yanding Peng, Tao Yu, Zhibo Chen
In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space.
no code implementations • CVPR 2023 • Shiqi Lin, Zhizheng Zhang, Zhipeng Huang, Yan Lu, Cuiling Lan, Peng Chu, Quanzeng You, Jiang Wang, Zicheng Liu, Amey Parulkar, Viraj Navkal, Zhibo Chen
Improving the generalization ability of Deep Neural Networks (DNNs) is critical for their practical uses, which has been a longstanding challenge.
2 code implementations • 11 Mar 2022 • Guoqiang Wei, Zhizheng Zhang, Cuiling Lan, Yan Lu, Zhibo Chen
In this work, we propose an innovative token-mixer, dubbed Active Token Mixer (ATM), to actively incorporate flexible contextual information distributed across different channels from other tokens into the given query token.
Ranked #64 on Object Detection on COCO minival
1 code implementation • 28 Jan 2022 • Tao Yu, Zhizheng Zhang, Cuiling Lan, Yan Lu, Zhibo Chen
For deep reinforcement learning (RL) from pixels, learning effective state representations is crucial for achieving high performance.
no code implementations • 25 Jan 2022 • Xin Jin, Ruoyu Feng, Simeng Sun, Runsen Feng, Tianyu He, Zhibo Chen
Traditional media coding schemes typically encode image/video into a semantic-unknown binary stream, which fails to directly support downstream intelligent tasks at the bitstream level.
1 code implementation • 26 Dec 2021 • Zongyu Guo, Runsen Feng, Zhizheng Zhang, Xin Jin, Zhibo Chen
Neural video codecs have demonstrated great potential in video transmission and storage applications.
no code implementations • 6 Dec 2021 • Shiqi Lin, Zhizheng Zhang, Xin Li, Wenjun Zeng, Zhibo Chen
Data augmentation (DA) has been widely investigated to facilitate model optimization in many tasks.
no code implementations • 26 Nov 2021 • Xin Li, Zhizheng Zhang, Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Xin Jin, Zhibo Chen
In this paper, we propose a novel Confounder Identification-free Causal Visual Feature Learning (CICF) method, which obviates the need for identifying confounders.
no code implementations • 25 Nov 2021 • Xin Li, Xin Jin, Jun Fu, Xiaoyuan Yu, Bei Tong, Zhibo Chen
Under this brand-new scenario, we propose Distortion Relation guided Transfer Learning (DRTL) for the few-shot RealSR by transferring the rich restoration knowledge from auxiliary distortions (i. e., synthetic distortions) to the target RealSR under the guidance of distortion relation.
no code implementations • 19 Nov 2021 • Xin Jin, Tianyu He, Xu Shen, Tongliang Liu, Xinchao Wang, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua
Unsupervised Person Re-identification (U-ReID) with pseudo labeling recently reaches a competitive performance compared to fully-supervised ReID methods based on modern clustering algorithms.
no code implementations • 7 Nov 2021 • Zexi Hu, Xiaoming Chen, Henry Wing Fung Yeung, Yuk Ying Chung, Zhibo Chen
Despite the recent progress in light field super-resolution (LFSR) achieved by convolutional neural networks, the correlation information of light field (LF) images has not been sufficiently studied and exploited due to the complexity of 4D LF data.
no code implementations • NeurIPS 2021 • Runsen Feng, Zongyu Guo, Zhizheng Zhang, Zhibo Chen
We show that the flow prediction module can largely reduce the transmission cost of voxel flows.
no code implementations • 29 Sep 2021 • Xin Jin, Tianyu He, Xu Shen, Songhua Wu, Tongliang Liu, Xinchao Wang, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua
In this paper, we propose an embarrassing simple yet highly effective adversarial domain adaptation (ADA) method for effectively training models for alignment.
1 code implementation • NeurIPS 2021 • Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhizheng Zhang, Zhibo Chen
Unsupervised domain adaptive classifcation intends to improve the classifcation performance on unlabeled target domain.
no code implementations • CVPR 2021 • Tianyu He, Xu Shen, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua
Driven by the success of deep learning, the last decade has seen rapid advances in person re-identification (re-ID).
2 code implementations • NeurIPS 2021 • Tao Yu, Cuiling Lan, Wenjun Zeng, Mingxiao Feng, Zhizheng Zhang, Zhibo Chen
In this work, we propose a novel method, dubbed PlayVirtual, which augments cycle-consistent virtual trajectories to enhance the data efficiency for RL feature representation learning.
Continuous Control (100k environment steps) Continuous Control (500k environment steps) +3
1 code implementation • 7 Jun 2021 • Xin Li, Jun Shi, Zhibo Chen
However, the traditional hybrid coding framework cannot be optimized in an end-to-end manner, which makes task-driven semantic fidelity metric unable to be automatically integrated into the rate-distortion optimization process.
no code implementations • 19 May 2021 • Jun Fu, Chen Hou, Wei Zhou, Jiahua Xu, Zhibo Chen
In the hypergraph construction, we build a location-based hyperedge and a content-based hyperedge for each viewport.
1 code implementation • 15 May 2021 • Wei Zhou, Zhou Wang, Zhibo Chen
In this paper, we assess the quality of SISR generated images in a two-dimensional (2D) space of structural fidelity versus statistical naturalness.
no code implementations • 12 Apr 2021 • Zongyu Guo, Zhizheng Zhang, Runsen Feng, Zhibo Chen
Quantization is one of the core components in lossy image compression.
no code implementations • 1 Apr 2021 • Jun Fu, Wei Zhou, Zhibo Chen
Under this framework, the graph structure is viewed as a random realization from a parametric generative model, and its posterior is inferred using the observed topology of the road network and traffic data.
1 code implementation • CVPR 2022 • Xin Jin, Tianyu He, Kecheng Zheng, Zhiheng Yin, Xu Shen, Zhen Huang, Ruoyu Feng, Jianqiang Huang, Xian-Sheng Hua, Zhibo Chen
Specifically, we introduce Gait recognition as an auxiliary task to drive the Image ReID model to learn cloth-agnostic representations by leveraging personal unique and cloth-independent gait information, we name this framework as GI-ReID.
Ranked #5 on Person Re-Identification on PRCC
Cloth-Changing Person Re-Identification Computational Efficiency +1
no code implementations • 25 Mar 2021 • Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Quanzeng You, Zicheng Liu, Kecheng Zheng, Zhibo Chen
Each recomposed feature, obtained based on the domain-invariant feature (which enables a reliable inheritance of identity) and an enhancement from a domain specific feature (which enables the approximation of real distributions), is thus an "ideal" augmentation.
1 code implementation • CVPR 2021 • Guoqiang Wei, Cuiling Lan, Wenjun Zeng, Zhibo Chen
For unsupervised domain adaptation (UDA), to alleviate the effect of domain shift, many approaches align the source and target domains in the feature space by adversarial learning or by explicitly aligning their statistics.
no code implementations • ICCV 2021 • Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
Many unsupervised domain adaptation (UDA) methods exploit domain adversarial training to align the features to reduce domain gap, where a feature extractor is trained to fool a domain discriminator in order to have aligned feature distributions.
2 code implementations • 20 Mar 2021 • Shiqi Lin, Tao Yu, Ruoyu Feng, Xin Li, Xin Jin, Zhibo Chen
We formulate it as a multi-agent reinforcement learning (MARL) problem, where each agent learns an augmentation policy for each patch based on its content together with the semantics of the whole image.
no code implementations • ICCV 2021 • Tianyu He, Xin Jin, Xu Shen, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua
The CNN encoder is responsible for efficiently extracting discriminative spatial features while the DI decoder is designed to densely model spatial-temporal inherent interaction across frames.
Ranked #1 on Person Re-Identification on DukeMTMC-reID
no code implementations • 22 Feb 2021 • Wei Zhou, Jiahua Xu, Qiuping Jiang, Zhibo Chen
To our knowledge, the proposed model is the first no-reference quality assessment method for 360-degreee images that combines multi-frequency information and image naturalness.
no code implementations • 21 Jan 2021 • Yingxue Pang, Jianxin Lin, Tao Qin, Zhibo Chen
Image-to-image translation (I2I) aims to transfer images from a source domain to a target domain while preserving the content representations.
1 code implementation • 3 Jan 2021 • Xin Jin, Cuiling Lan, Wenjun Zeng, Zhibo Chen
In this paper, we design a novel Style Normalization and Restitution module (SNR) to simultaneously ensure both high generalization and discrimination capability of the networks.
no code implementations • 17 Dec 2020 • Yaojun Wu, Xin Li, Zhizheng Zhang, Xin Jin, Zhibo Chen
Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications.
no code implementations • 11 Dec 2020 • Xin Li, Xin Jin, Tao Yu, Yingxue Pang, Simeng Sun, Zhizheng Zhang, Zhibo Chen
Traditional single image super-resolution (SISR) methods that focus on solving single and uniform degradation (i. e., bicubic down-sampling), typically suffer from poor performance when applied into real-world low-resolution (LR) images due to the complicated realistic degradations.
no code implementations • 1 Dec 2020 • Wei Zhou, Zhibo Chen
In this paper, motivated by the human visual system (HVS) combining multi-scale features for perception, we propose to use pyramid features learning to build a DNN with hierarchical multi-scale features for distorted image quality prediction.
no code implementations • 19 Nov 2020 • Zongyu Guo, Zhizheng Zhang, Runsen Feng, Zhibo Chen
In this paper, we propose the concept of separate entropy coding to leverage a serial decoding process for causal contextual entropy prediction in the latent space.
no code implementations • 6 Nov 2020 • Yufan Jiang, Shuangzhi Wu, Jing Gong, Yahui Cheng, Peng Meng, Weiliang Lin, Zhibo Chen, Mu Li
In addition, by transferring knowledge from other kinds of MRC tasks, our model achieves a new state-of-the-art results in both single and ensemble settings.
Ranked #1 on Reading Comprehension on RACE
no code implementations • 20 Oct 2020 • Shaohuai Shi, Xianhao Zhou, Shutao Song, Xingyao Wang, Zilin Zhu, Xue Huang, Xinan Jiang, Feihu Zhou, Zhenyu Guo, Liqiang Xie, Rui Lan, Xianbin Ouyang, Yan Zhang, Jieqian Wei, Jing Gong, Weiliang Lin, Ping Gao, Peng Meng, Xiaomin Xu, Chenyang Guo, Bo Yang, Zhibo Chen, Yongjian Wu, Xiaowen Chu
Distributed training techniques have been widely deployed in large-scale deep neural networks (DNNs) training on dense-GPU clusters.
no code implementations • 15 Oct 2020 • Jun Fu, Wei Zhou, Zhibo Chen
The graph structure in our network is learned from the physical topology of the road network and traffic data in an end-to-end manner, which discovers a more accurate description of the relationship among traffic flows.
Ranked #2 on Traffic Prediction on SZ-Taxi
no code implementations • 9 Oct 2020 • Zhizheng Zhang, Cuiling Lan, Wenjun Zeng, Zhibo Chen, Shih-Fu Chang
In this work, we propose Uncertainty-Aware Few-Shot framework for image classification by modeling uncertainty of the similarities of query-support pairs and performing uncertainty-aware optimization.
no code implementations • 30 Sep 2020 • Yingxue Pang, Xin Li, Xin Jin, Yaojun Wu, Jianzhao Liu, Sen Liu, Zhibo Chen
Specifically, we extract different frequencies of the LR image and pass them to a channel attention-grouped residual dense network (CA-GRDB) individually to output corresponding feature maps.
no code implementations • ECCV 2020 • Jianzhao Liu, Jianxin Lin, Xin Li, Wei Zhou, Sen Liu, Zhibo Chen
Most existing image restoration networks are designed in a disposable way and catastrophically forget previously learned distortions when trained on a new distortion removal task.
no code implementations • ECCV 2020 • Xin Li, Xin Jin, Jianxin Lin, Tao Yu, Sen Liu, Yaojun Wu, Wei Zhou, Zhibo Chen
Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions.
no code implementations • 22 Jun 2020 • Xin Jin, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen
To ensure high discrimination, we propose a Feature Restoration (FR) operation to distill task-relevant features from the residual information and use them to compensate for the aligned features.
Ranked #72 on Domain Generalization on PACS
no code implementations • 8 Jun 2020 • Zhizheng Zhang, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen, Shih-Fu Chang
There is a lack of loss design which enables the joint optimization of multiple instances (of multiple classes) within per-query optimization for person ReID.
1 code implementation • 1 Jun 2020 • Jun Fu, Jianfeng Xu, Kazuyuki Tasaka, Zhibo Chen
Image deraining is an important image processing task as rain streaks not only severely degrade the visual quality of images but also significantly affect the performance of high-level vision tasks.
no code implementations • ECCV 2020 • Xin Jin, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen
To address this problem, we introduce a global distance-distributions separation (GDS) constraint over the two distributions to encourage the clear separation of positive and negative samples from a global view.
1 code implementation • CVPR 2020 • Xin Jin, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen, Li Zhang
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps.
Ranked #7 on Unsupervised Domain Adaptation on Market to Duke
no code implementations • 16 May 2020 • Xin Li, Simeng Sun, Zhizheng Zhang, Zhibo Chen
Versatile Video Coding (H. 266/VVC) standard achieves better image quality when keeping the same bits than any other conventional image codec, such as BPG, JPEG, and etc.
no code implementations • 13 Apr 2020 • Wei Zhou, Qiuping Jiang, Yuwang Wang, Zhibo Chen, Weiping Li
Numerous image superresolution (SR) algorithms have been proposed for reconstructing high-resolution (HR) images from input images with lower spatial resolutions.
1 code implementation • ECCV 2020 • Jianxin Lin, Yingxue Pang, Yingce Xia, Zhibo Chen, Jiebo Luo
With TuiGAN, an image is translated in a coarse-to-fine manner where the generated image is gradually refined from global structures to local details.
no code implementations • CVPR 2020 • Zhizheng Zhang, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen
In this paper, we propose an attentive feature aggregation module, namely Multi-Granularity Reference-aided Attentive Feature Aggregation (MG-RAFA), to delicately aggregate spatio-temporal features into a discriminative video-level feature representation.
no code implementations • 25 Mar 2020 • Ya Zhou, Jianfeng Xu, Kazuyuki Tasaka, Zhibo Chen, Weiping Li
Various blur distortions in video will cause negative impact on both human viewing and video-based applications, which makes motion-robust deblurring methods urgently needed.
no code implementations • 12 Mar 2020 • Jun Shi, Jianfeng Xu, Kazuyuki Tasaka, Zhibo Chen
Accelerating the inference speed of CNNs is critical to their deployment in real-world applications.
no code implementations • 4 Mar 2020 • Jiale Chen, Xu Tan, Chaowei Shan, Sen Liu, Zhibo Chen
This paper introduces VESR-Net, a method for video enhancement and super-resolution (VESR).
no code implementations • 15 Jan 2020 • Xin Jin, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen
To the best of our knowledge, we are the first to make use of multi-shots of an object in a teacher-student learning manner for effectively boosting the single image based re-id.
no code implementations • 30 Dec 2019 • Yaojun Wu, Tianyu He, Zhibo Chen
In this paper, we figure out this issue by disentangling surveillance video into the structure of a global spatio-temporal feature (memory) for Group of Picture (GoP) and skeleton for each frame (clue).
1 code implementation • 23 Nov 2019 • Tao Yu, Zongyu Guo, Xin Jin, Shilin Wu, Zhibo Chen, Weiping Li, Zhizheng Zhang, Sen Liu
In this work, we show that the mean and variance shifts caused by full-spatial FN limit the image inpainting network training and we propose a spatial region-wise normalization named Region Normalization (RN) to overcome the limitation.
no code implementations • 16 Oct 2019 • Jun Shi, Zhibo Chen
Rapid growing intelligent applications require optimized bit allocation in image/video coding to support specific task-driven scenarios such as detection, classification, segmentation, etc.
no code implementations • 5 Sep 2019 • Wei Zhou, Likun Shi, Zhibo Chen, Jinglin Zhang
Light field image (LFI) quality assessment is becoming more and more important, which helps to better guide the acquisition, processing and application of immersive media.
1 code implementation • 4 Sep 2019 • Jiahua Xu, Wei Zhou, Zhibo Chen, Suiyi Ling, Patrick Le Callet
Stereoscopic image quality measurement (SIQM) has become increasingly important for guiding stereo image processing and commutation systems due to the widespread usage of 3D contents.
Multimedia Image and Video Processing
no code implementations • 17 Aug 2019 • Likun Shi, Wei Zhou, Zhibo Chen, Jinglin Zhang
In this paper, we propose a No-Reference Light Field image Quality Assessment (NR-LFQA) scheme, where the main idea is to quantify the LFI quality degradation through evaluating the spatial quality and angular consistency.
2 code implementations • 24 Jul 2019 • Zongyu Guo, Zhibo Chen, Tao Yu, Jiale Chen, Sen Liu
Recently, learning-based algorithms for image inpainting achieve remarkable progress dealing with squared or irregular holes.
no code implementations • 12 Jun 2019 • Zhibo Chen, Jiahua Xu, Chaoyi Lin, Wei Zhou
In this paper, based on the predictive coding theory of the human vision system (HVS), we propose a stereoscopic omnidirectional image quality evaluator (SOIQE) to cope with the characteristics of 3D 360-degree images.
no code implementations • 8 Jun 2019 • Chaowei Shan, Zhizheng Zhang, Zhibo Chen
For current learned methods in this field, global harmonious perception and local details are hard to be well-considered in a single model simultaneously.
1 code implementation • 1 Jun 2019 • Jianxin Lin, Yingce Xia, Sen Liu, Shuqin Zhao, Zhibo Chen
Image-to-image translation models have shown remarkable ability on transferring images among different domains.
1 code implementation • 1 Jun 2019 • Jianxin Lin, Yijun Wang, Tianyu He, Zhibo Chen
Unsupervised domain translation has recently achieved impressive performance with Generative Adversarial Network (GAN) and sufficient (unpaired) training data.
1 code implementation • 30 May 2019 • Xin Jin, Cuiling Lan, Wen-Jun Zeng, Guoqiang Wei, Zhibo Chen
Specifically, we build a Semantics Aligning Network (SAN) which consists of a base network as encoder (SA-Enc) for re-ID, and a decoder (SA-Dec) for reconstructing/regressing the densely semantics aligned full texture image.
no code implementations • 29 May 2019 • Jianxin Lin, Yingce Xia, Yijun Wang, Tao Qin, Zhibo Chen
In this work, we introduce a new kind of loss, multi-path consistency loss, which evaluates the differences between direct translation $\mathcal{D}_s\to\mathcal{D}_t$ and indirect translation $\mathcal{D}_s\to\mathcal{D}_a\to\mathcal{D}_t$ with $\mathcal{D}_a$ as an auxiliary domain, to regularize training.
no code implementations • 17 Apr 2019 • Xin Jin, Cuiling Lan, Wen-Jun Zeng, Zhizheng Zhang, Zhibo Chen
We achieve this by the context interaction among the features of different scales.
1 code implementation • CVPR 2019 • Kean Chen, Jianguo Li, Weiyao Lin, John See, Ji Wang, Ling-Yu Duan, Zhibo Chen, Changwei He, Junni Zou
For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks.
1 code implementation • CVPR 2020 • Zhizheng Zhang, Cuiling Lan, Wen-Jun Zeng, Xin Jin, Zhibo Chen
For person re-identification (re-id), attention mechanisms have become attractive as they aim at strengthening discriminative features and suppressing irrelevant ones, which matches well the key of re-id, i. e., discriminative feature learning.
1 code implementation • 3 Mar 2019 • Zhizheng Zhang, Jiale Chen, Zhibo Chen, Weiping Li
Not limited to the control tasks in computationally complex environments, AE-DDPG also achieves higher rewards and 2- to 4-fold improvement in sample efficiency on average compared to other variants of DDPG in MuJoCo environments.
1 code implementation • 11 Feb 2019 • Jianxin Lin, Zhibo Chen, Yingce Xia, Sen Liu, Tao Qin, Jiebo Luo
After pre-training, this network is used to extract the domain-specific features of each image.
no code implementations • 30 Jan 2019 • Guoqiang Wei, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen
The diversity of capturing viewpoints and the flexibility of the human poses, however, remain some significant challenges.
no code implementations • 25 Dec 2018 • Zhibo Chen, Tianyu He
The experimental results verify the framework's efficiency by demonstrating performance improvement of 71. 41%, 48. 28% and 52. 67% bitrate saving separately over JPEG2000, WebP and neural network-based codecs under the same face verification accuracy distortion metric.
no code implementations • CVPR 2019 • Zhizheng Zhang, Cuiling Lan, Wen-Jun Zeng, Zhibo Chen
We propose a densely semantically aligned person re-identification framework.
1 code implementation • 19 Dec 2018 • Zhibo Chen, Jianxin Lin, Tiankuang Zhou, Feng Wu
The SGU sequentially takes information from two different levels as inputs and decides the output based on one active input.
no code implementations • NeurIPS 2018 • Tianyu He, Xu Tan, Yingce Xia, Di He, Tao Qin, Zhibo Chen, Tie-Yan Liu
Neural Machine Translation (NMT) has achieved remarkable progress with the quick evolvement of model structures.
no code implementations • 21 Nov 2018 • Xin Jin, Zhibo Chen, Jianxin Lin, Zhikai Chen, Wei Zhou
Most existing single image deraining methods require learning supervised models from a large set of paired synthetic training data, which limits their generality, scalability and practicality in real-world multimedia applications.
no code implementations • 19 Nov 2018 • Jianxin Lin, Tiankuang Zhou, Zhibo Chen
We present \emph{Deep Image Retargeting} (\emph{DeepIR}), a coarse-to-fine framework for content-aware image retargeting.
no code implementations • 18 Nov 2018 • Sen Liu, Jianxin Lin, Zhibo Chen
Accordingly, we introduce a collaborative training scheme: a discriminator $D$ is trained to discriminate the reconstructed image from the encrypted image, and an encryption model $G_e$ is required to generate these two kinds of images to maximize the recognition rate of $D$, leading to the same training objective for both $D$ and $G_e$.
no code implementations • 6 May 2018 • Jianxin Lin, Tiankuang Zhou, Zhibo Chen
Experiment results demonstrate that our SGEN is more effective at multi-scale human face restoration with more image details and less noise than state-of-the-art image restoration models.
no code implementations • CVPR 2018 • Jianxin Lin, Yingce Xia, Tao Qin, Zhibo Chen, Tie-Yan Liu
In this paper, we study a new problem, conditional image-to-image translation, which is to translate an image from the source domain to the target domain conditioned on a given image in the target domain.
no code implementations • 26 Apr 2018 • Zhibo Chen, Tianyu He, Xin Jin, Feng Wu
One key challenge to learning-based video compression is that motion predictive coding, a very effective tool for video compression, can hardly be trained into a neural network.
Multimedia Image and Video Processing
2 code implementations • 2 Apr 2018 • Łukasz Kidziński, Sharada Prasanna Mohanty, Carmichael Ong, Zhewei Huang, Shuchang Zhou, Anton Pechenko, Adam Stelmaszczyk, Piotr Jarosik, Mikhail Pavlov, Sergey Kolesnikov, Sergey Plis, Zhibo Chen, Zhizheng Zhang, Jiale Chen, Jun Shi, Zhuobin Zheng, Chun Yuan, Zhihui Lin, Henryk Michalewski, Piotr Miłoś, Błażej Osiński, Andrew Melnik, Malte Schilling, Helge Ritter, Sean Carroll, Jennifer Hicks, Sergey Levine, Marcel Salathé, Scott Delp
In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course.