no code implementations • ECCV 2020 • Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, Chenliang Xu
Monocular 3D object detection is a challenging task due to unreliable depth, resulting in a distinct performance gap between monocular and LiDAR-based approaches.
no code implementations • ECCV 2020 • Zhong Li, Yu Ji, Jingyi Yu, Jinwei Ye
In this paper, we present a PIV solution that uses a compact lenslet-based light field camera to track dense particles floating in the fluid and reconstruct the 3D fluid flow.
no code implementations • 3 Mar 2024 • Tianyu Luan, Zhong Li, Lele Chen, Xuan Gong, Lichang Chen, Yi Xu, Junsong Yuan
Then, we calculate the Area Under the Curve (AUC) difference between the two spectrums, so that each frequency band that captures either the overall or detailed shape is equitably considered.
1 code implementation • 9 Jan 2024 • Jiaqi Wang, Yuying Chang, Zhong Li, Ning An, Qi Ma, Lei Hei, Haibo Luo, Yifei Lu, Feiliang Ren
Large language models have exhibited robust performance across diverse natural language processing tasks.
1 code implementation • 28 Dec 2023 • Zhan Li, Zhang Chen, Zhong Li, Yi Xu
Novel view synthesis of dynamic scenes has been an intriguing yet challenging problem.
1 code implementation • NeurIPS 2023 • Puheng Li, Zhong Li, Huishuai Zhang, Jiang Bian
This precisely elucidates the adverse effect of "modes shift" in ground truths on the model generalization.
1 code implementation • 23 Oct 2023 • Zhong Li, Liangchen Song, Zhang Chen, Xiangyu Du, Lele Chen, Junsong Yuan, Yi Xu
A DecomposeNet learns to map each ray to its SVBRDF components: albedo, normal, and roughness.
1 code implementation • ICCV 2023 • Zhang Chen, Zhong Li, Liangchen Song, Lele Chen, Jingyi Yu, Junsong Yuan, Yi Xu
The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals.
no code implementations • NeurIPS 2023 • Isabella Liu, Linghao Chen, Ziyang Fu, Liwen Wu, Haian Jin, Zhong Li, Chin Ming Ryan Wong, Yi Xu, Ravi Ramamoorthi, Zexiang Xu, Hao Su
We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations.
1 code implementation • ICCV 2023 • Wentao Bao, Lele Chen, Libing Zeng, Zhong Li, Yi Xu, Junsong Yuan, Yu Kong
In this paper, we set up an egocentric 3D hand trajectory forecasting task that aims to predict hand trajectories in a 3D space from early observed RGB videos in a first-person view.
1 code implementation • CVPR 2023 • Tianyu Luan, Yuanhao Zhai, Jingjing Meng, Zhong Li, Zhang Chen, Yi Xu, Junsong Yuan
To capture high-frequency personalized details, we transform the 3D mesh into the frequency domain, and propose a novel frequency decomposition loss to supervise each frequency component.
1 code implementation • 2 Jul 2023 • Zhong Li, Jiayang Shi, Matthijs van Leeuwen
Event logs are widely used to record the status of high-tech systems, making log anomaly detection important for monitoring those systems.
1 code implementation • 30 May 2023 • Shida Wang, Zhong Li, Qianxiao Li
We prove an inverse approximation theorem for the approximation of nonlinear sequence-to-sequence relationships using recurrent neural networks (RNNs).
1 code implementation • 15 Mar 2023 • Liangchen Song, Zhong Li, Xuan Gong, Lele Chen, Zhang Chen, Yi Xu, Junsong Yuan
We further propose a simple-yet-effective strategy for tuning the frequency to avoid overfitting few-shot inputs: enforcing consistency among the frequency domain of rendered 2D images.
no code implementations • 27 Feb 2023 • Haotian Jiang, Qianxiao Li, Zhong Li, Shida Wang
We survey current developments in the approximation theory of sequence modelling in machine learning.
1 code implementation • 22 Feb 2023 • Zhong Li, Matthijs van Leeuwen
Traditional anomaly detection methods aim to identify objects that deviate from most other objects by treating all features equally.
no code implementations • 5 Feb 2023 • Zeping Min, Qian Ge, Zhong Li, Weinan E
Furthermore, in the ASR task, MAC beats wav2vec2 (with fine-tuning) on common voice datasets of Cantonese and gets really competitive results on common voice datasets of Taiwanese and Japanese.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • CVPR 2023 • Libing Zeng, Lele Chen, Wentao Bao, Zhong Li, Yi Xu, Junsong Yuan, Nima Khademi Kalantari
Accurate facial landmark detection on wild images plays an essential role in human-computer interaction, entertainment, and medical applications.
no code implementations • CVPR 2023 • Shengwei Qin, Zhong Li, Ligang Liu
Especially, in the case of sparse point clouds (64 points) with noise under arbitrary SO(3) rotation, the classification result (85. 4%) of NLGAT is improved by 39. 4% compared with the best development of other methods.
no code implementations • 28 Oct 2022 • Liangchen Song, Anpei Chen, Zhong Li, Zhang Chen, Lele Chen, Junsong Yuan, Yi Xu, Andreas Geiger
Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest.
no code implementations • 13 Oct 2022 • Zhong Li, Yuxuan Zhu, Matthijs van Leeuwen
In the past two decades, most research on anomaly detection has focused on improving the accuracy of the detection, while largely ignoring the explainability of the corresponding methods and thus leaving the explanation of outcomes to practitioners.
no code implementations • 19 Aug 2022 • Zhong Li, Matthijs van Leeuwen
Event logs are widely used for anomaly detection and prediction in complex systems.
no code implementations • 5 Apr 2022 • Yanyong Huang, Kejun Guo, Xiuwen Yi, Zhong Li, Tianrui Li
To address these issues, we propose an Incremental Incomplete Multi-view Unsupervised Feature Selection method (I$^2$MUFS) on incomplete multi-view streaming data.
no code implementations • ICLR 2022 • Zhong Li, Haotian Jiang, Qianxiao Li
Our results provide the theoretical understanding of approximation properties of the recurrent encoder-decoder architecture, which characterises, in the considered setting, the types of temporal relationships that can be efficiently learned.
no code implementations • 20 Jul 2021 • Haotian Jiang, Zhong Li, Qianxiao Li
We study the approximation properties of convolutional architectures applied to time series modelling, which can be formulated mathematically as a functional approximation problem.
no code implementations • 15 May 2021 • Zhong Li, Liangchen Song, Celong Liu, Junsong Yuan, Yi Xu
In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes.
no code implementations • 30 Apr 2021 • Zhuo Su, Lan Xu, Dawei Zhong, Zhong Li, Fan Deng, Shuxue Quan, Lu Fang
To fill this gap, in this paper, we propose RobustFusion, a robust volumetric performance reconstruction system for human-object interaction scenarios using only a single RGBD sensor, which combines various data-driven visual and interaction cues to handle the complex interaction patterns and severe occlusions.
1 code implementation • 12 Dec 2020 • Yuliang Guo, Zhong Li, Zekun Li, Xiangyu Du, Shuxue Quan, Yi Xu
In this paper, a real-time method called PoP-Net is proposed to predict multi-person 3D poses from a depth image.
no code implementations • ICLR 2021 • Zhong Li, Jiequn Han, Weinan E, Qianxiao Li
We study the approximation properties and optimization dynamics of recurrent neural networks (RNNs) when applied to learn input-output relationships in temporal data.
no code implementations • 14 Sep 2020 • Zhong Li, Chao Ma, Lei Wu
The approach is motivated by approximating the general activation functions with one-dimensional ReLU networks, which reduces the problem to the complexity controls of ReLU networks.
1 code implementation • 16 Jul 2020 • Lele Chen, Guofeng Cui, Celong Liu, Zhong Li, Ziyi Kou, Yi Xu, Chenliang Xu
When people deliver a speech, they naturally move heads, and this rhythmic head motion conveys prosodic information.
no code implementations • 15 Apr 2019 • Zhong Li, Jinwei Ye, Yu Ji, Hao Sheng, Jingyi Yu
Particle Imaging Velocimetry (PIV) estimates the flow of fluid by analyzing the motion of injected particles.
no code implementations • CVPR 2018 • Zhong Li, Minye Wu, Wangyiteng Zhou, Jingyi Yu
The availability of affordable 3D full body reconstruction systems has given rise to free-viewpoint video (FVV) of human shapes.
no code implementations • 31 Jan 2018 • Zhong Li, Yu Ji, Wei Yang, Jinwei Ye, Jingyi Yu
In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc.