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 • 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 • 20 Feb 2024 • Jianhong Bai, Tianyu He, Yuchi Wang, Junliang Guo, Haoji Hu, Zuozhu Liu, Jiang Bian
Recent advances in text-guided video editing have showcased promising results in appearance editing (e. g., stylization).
no code implementations • 1 Dec 2023 • Tianyu He, Guanghui Fu, Yijing Yu, Fan Wang, Jianqiang Li, Qing Zhao, Changwei Song, Hongzhi Qi, Dan Luo, Huijing Zou, Bing Xiang Yang
The complexity of psychological principles underscore a significant societal challenge, given the vast social implications of psychological problems.
no code implementations • 26 Nov 2023 • Tianyu He, Junliang Guo, Runyi Yu, Yuchi Wang, Jialiang Zhu, Kaikai An, Leyi Li, Xu Tan, Chunyu Wang, Han Hu, HsiangTao Wu, Sheng Zhao, Jiang Bian
Zero-shot talking avatar generation aims at synthesizing natural talking videos from speech and a single portrait image.
no code implementations • 3 Nov 2023 • Dayal Singh Kalra, Tianyu He, Maissam Barkeshli
In gradient descent dynamics of neural networks, the top eigenvalue of the Hessian of the loss (sharpness) displays a variety of robust phenomena throughout training.
no code implementations • 31 Oct 2023 • Wei Zhao, Yijun Wang, Tianyu He, Lianying Yin, Jianxin Lin, Xin Jin
To augment the richness of 3D facial animation, we construct a new 3D dataset with detailed shapes and learn to synthesize facial details in line with speech content.
1 code implementation • 19 Oct 2023 • Darshil Doshi, Aritra Das, Tianyu He, Andrey Gromov
Robust generalization is a major challenge in deep learning, particularly when the number of trainable parameters is very large.
1 code implementation • 18 Oct 2023 • Dingyao Yu, Kaitao Song, Peiling Lu, Tianyu He, Xu Tan, Wei Ye, Shikun Zhang, Jiang Bian
For developers and amateurs, it is very difficult to grasp all of these task to satisfy their requirements in music processing, especially considering the huge differences in the representations of music data and the model applicability across platforms among various tasks.
no code implementations • 20 Jun 2023 • Lianying Yin, Yijun Wang, Tianyu He, Jinming Liu, Wei Zhao, Bohan Li, Xin Jin, Jianxin Lin
In this paper, we present a novel framework (EMoG) to tackle the above challenges with denoising diffusion models: 1) To alleviate the one-to-many problem, we incorporate emotion clues to guide the generation process, making the generation much easier; 2) To model joint correlation, we propose to decompose the difficult gesture generation into two sub-problems: joint correlation modeling and temporal dynamics modeling.
no code implementations • ICCV 2023 • Zenghao Chai, Tianke Zhang, Tianyu He, Xu Tan, Tadas Baltrušaitis, HsiangTao Wu, Runnan Li, Sheng Zhao, Chun Yuan, Jiang Bian
3D Morphable Models (3DMMs) demonstrate great potential for reconstructing faithful and animatable 3D facial surfaces from a single image.
Ranked #1 on 3D Face Reconstruction on REALY (side-view)
no code implementations • 9 Dec 2022 • Anni Tang, Tianyu He, Xu Tan, Jun Ling, Li Song
More specifically, the implicit memory is employed in the audio-to-expression model to capture high-level semantics in the audio-expression shared space, while the explicit memory is employed in the neural-rendering model to help synthesize pixel-level details.
1 code implementation • 22 Nov 2022 • Shaoming Duan, Chuanyi Liu, Peiyi Han, Tianyu He, Yifeng Xu, Qiyuan Deng
Non-independent and identically distributed (non-IID) data is a key challenge in federated learning (FL), which usually hampers the optimization convergence and the performance of FL.
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.
no code implementations • 27 Jun 2022 • Tianyu He, Darshil Doshi, Andrey Gromov
Good initialization is essential for training Deep Neural Networks (DNNs).
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.
no code implementations • 23 Nov 2021 • Darshil Doshi, Tianyu He, Andrey Gromov
We derive recurrence relations for the norms of partial Jacobians and utilize these relations to analyze criticality of deep fully connected neural networks with LayerNorm and/or residual connections.
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.
1 code implementation • 4 Oct 2021 • Xiaopeng Sun, Muxingzi Li, Tianyu He, Lubin Fan
Low-light image enhancement exhibits an ill-posed nature, as a given image may have many enhanced versions, yet recent studies focus on building a deterministic mapping from input to an enhanced version.
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.
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).
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 • 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 • 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).
no code implementations • 17 Aug 2019 • Tianyu He, Xu Tan, Tao Qin
Neural machine translation (NMT) typically adopts the encoder-decoder framework.
no code implementations • 17 Aug 2019 • Tianyu He, Jiale Chen, Xu Tan, Tao Qin
Neural machine translation on low-resource language is challenging due to the lack of bilingual sentence pairs.
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.
no code implementations • ICLR 2019 • Yiren Wang, Yingce Xia, Tianyu He, Fei Tian, Tao Qin, ChengXiang Zhai, Tie-Yan Liu
Dual learning has attracted much attention in machine learning, computer vision and natural language processing communities.
Ranked #1 on Machine Translation on WMT2016 English-German
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 • 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 • 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