1 code implementation • 6 Feb 2023 • Xiaowen Shi, Fan Yang, Ze Wang, Xiaoxu Wu, Muzhi Guan, Guogang Liao, Yongkang Wang, Xingxing Wang, Dong Wang
Then we design a novel omnidirectional attention mechanism in OCPM to capture the context information in the permutation.
no code implementations • 2 Feb 2023 • Ze Wang, Jiang Wang, Zicheng Liu, Qiang Qiu
In the proposed framework, we model energy estimation and data restoration as the forward and backward passes of a single network without any auxiliary components, e. g., an extra decoder.
no code implementations • 15 Nov 2022 • Jingang Qu, Thibault Faney, Ze Wang, Patrick Gallinari, Soleiman Yousef, Jean-Charles de Hemptinne
HMOE uses hypernetworks taking vectors as input to generate experts' weights, which allows experts to share useful meta-knowledge and enables exploring experts' similarities in a low-dimensional vector space.
1 code implementation • 19 Oct 2022 • Lei Zhang, Xiaoke Wang, Michael Rawson, Radu Balan, Edward H. Herskovits, Elias Melhem, Linda Chang, Ze Wang, Thomas Ernst
Evaluation used simulated T1 and T2-weighted axial, coronal, and sagittal images unseen during training, as well as T1-weighted images with motion artifacts from real scans.
2 code implementations • 12 Sep 2022 • Ze Wang, Kailun Yang, Hao Shi, Peng Li, Fei Gao, Jian Bai, Kaiwei Wang
We collect the PALVIO dataset using a Panoramic Annular Lens (PAL) system with an entire FoV of 360\deg x(40\deg-120\deg) and IMU sensor to address the lack of panoramic SLAM datasets.
no code implementations • 13 Jun 2022 • Yiran Li, Ze Wang
The proposed method significantly reduces the number of PLDs from 6 to 2 on ATT and even to single PLD on CBF without sacrificing the SNR.
no code implementations • 7 Jun 2022 • Ziqi Zhou, Li Lian, Yilong Yin, Ze Wang
Guided by that maximum rate, a novel and efficient hierarchical network pruning algorithm is developed to maximally condense the neuronal network structure without sacrificing network performance.
no code implementations • 20 May 2022 • Guogang Liao, Xuejian Li, Ze Wang, Fan Yang, Muzhi Guan, Bingqi Zhu, Yongkang Wang, Xingxing Wang, Dong Wang
Although VCG-based multi-slot auctions (e. g., VCG, WVCG) make it theoretically possible to model global externalities (e. g., the order and positions of ads and so on), they lack an efficient balance of both revenue and social welfare.
no code implementations • 2 Apr 2022 • Ze Wang, Guogang Liao, Xiaowen Shi, Xiaoxu Wu, Chuheng Zhang, Bingqi Zhu, Yongkang Wang, Xingxing Wang, Dong Wang
Ads allocation, which involves allocating ads and organic items to limited slots in feed with the purpose of maximizing platform revenue, has become a research hotspot.
no code implementations • 2 Apr 2022 • Ze Wang, Guogang Liao, Xiaowen Shi, Xiaoxu Wu, Chuheng Zhang, Yongkang Wang, Xingxing Wang, Dong Wang
With the recent prevalence of reinforcement learning (RL), there have been tremendous interests in utilizing RL for ads allocation in recommendation platforms (e. g., e-commerce and news feed sites).
no code implementations • 1 Apr 2022 • Guogang Liao, Xiaowen Shi, Ze Wang, Xiaoxu Wu, Chuheng Zhang, Yongkang Wang, Xingxing Wang, Dong Wang
A mixed list of ads and organic items is usually displayed in feed and how to allocate the limited slots to maximize the overall revenue is a key problem.
1 code implementation • 27 Feb 2022 • Hao Shi, Yifan Zhou, Kailun Yang, Xiaoting Yin, Ze Wang, Yaozu Ye, Zhe Yin, Shi Meng, Peng Li, Kaiwei Wang
PanoFlow achieves state-of-the-art performance on the public OmniFlowNet and the established FlowScape benchmarks.
1 code implementation • 25 Feb 2022 • Ze Wang, Kailun Yang, Hao Shi, Peng Li, Fei Gao, Kaiwei Wang
To tackle this issue, we propose LF-VIO, a real-time VIO framework for cameras with extremely large FoV.
no code implementations • NeurIPS 2021 • Ze Wang, Zichen Miao, XianTong Zhen, Qiang Qiu
In contrast to sparse Gaussian processes, we define a set of dense inducing variables to be of a much larger size than the support set in each task, which collects prior knowledge from experienced tasks.
no code implementations • NeurIPS 2021 • Ze Wang, Seunghyun Hwang, Zichen Miao, Qiang Qiu
In this paper, we model the subspace of convolutional filters with a neural ordinary differential equation (ODE) to enable gradual changes in generated images.
no code implementations • NeurIPS 2021 • Zichen Miao, Ze Wang, Xiuyuan Cheng, Qiang Qiu
In this paper, we introduce spatiotemporal joint filter decomposition to decouple spatial and temporal learning, while preserving spatiotemporal dependency in a video.
1 code implementation • ICLR 2022 • Zichen Miao, Ze Wang, Wei Chen, Qiang Qiu
In this paper, we first enforce a low-rank filter subspace by decomposing convolutional filters within each network layer over a small set of filter atoms.
no code implementations • 29 Sep 2021 • Ze Wang, Yue Lu, Qiang Qiu
We introduce Meta-OLE, a new geometry-regularized method for fast adaptation to novel tasks in few-shot image classification.
no code implementations • 29 Sep 2021 • Ze Wang, Yipin Zhou, Rui Wang, Tsung-Yu Lin, Ashish Shah, Ser-Nam Lim
Anything outside of a given normal population is by definition an anomaly.
no code implementations • 29 Sep 2021 • Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
In other words, a CNN is now reduced to layers of filter atoms, typically a few hundred of parameters per layer, with a common block of subspace coefficients shared across layers.
1 code implementation • 9 Sep 2021 • Guogang Liao, Ze Wang, Xiaoxu Wu, Xiaowen Shi, Chuheng Zhang, Yongkang Wang, Xingxing Wang, Dong Wang
Our model results in higher revenue and better user experience than state-of-the-art baselines in offline experiments.
no code implementations • 1 Sep 2021 • Ze Wang
A large body of literature has shown the substantial inter-regional functional connectivity in the mammal brain.
no code implementations • 1 Sep 2021 • Ze Wang
A few TCM properties were collected to measure LRTC, including the averaged correlation, anti-correlation, the ratio of correlation and anticorrelation, the mean coherent and incoherent duration, and the ratio between the coherent and incoherent time.
no code implementations • ICCV 2021 • Ze Wang, Zichen Miao, Jun Hu, Qiang Qiu
Applying feature dependent network weights have been proved to be effective in many fields.
no code implementations • 5 Dec 2020 • Ze Wang, Sihao Ding, Ying Li, Jonas Fenn, Sohini Roychowdhury, Andreas Wallin, Lane Martin, Scott Ryvola, Guillermo Sapiro, Qiang Qiu
Point density varies significantly across such a long range, and different scanning patterns further diversify object representation in LiDAR.
no code implementations • 19 Nov 2020 • Haoyu Dong, Ze Wang, Qiang Qiu, Guillermo Sapiro
Image retrieval relies heavily on the quality of the data modeling and the distance measurement in the feature space.
no code implementations • 4 Sep 2020 • Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
We then explicitly regularize CNN kernels by enforcing decomposed coefficients to be shared across sub-structures, while leaving each sub-structure only its own dictionary atoms, a few hundreds of parameters typically, which leads to dramatic model reductions.
no code implementations • 15 May 2020 • Danfeng Xie, Yiran Li, Hanlu Yang, Li Bai, Lei Zhang, Ze Wang
The results showed that the learning-from-noise strategy produced better output quality than ASLDN trained with relatively high SNR reference.
no code implementations • 26 Sep 2019 • Ze Wang, Sihao Ding, Ying Li, Minming Zhao, Sohini Roychowdhury, Andreas Wallin, Guillermo Sapiro, Qiang Qiu
To the best of our knowledge, this paper is the first attempt to study cross-range LiDAR adaptation for object detection in point clouds.
no code implementations • 25 Sep 2019 • Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
Domain shifts are frequently encountered in real-world scenarios.
no code implementations • NeurIPS 2020 • Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
In this paper, we consider domain-invariant deep learning by explicitly modeling domain shifts with only a small amount of domain-specific parameters in a Convolutional Neural Network (CNN).
no code implementations • ICLR 2020 • Ze Wang, Xiuyuan Cheng, Guillermo Sapiro, Qiang Qiu
One of these questions is how to efficiently achieve proper diversity and sampling of the multi-mode data space.
no code implementations • 25 Apr 2019 • Jingyuan Wang, Junjie Wu, Ze Wang, Fei Gao, Zhang Xiong
In this paper, we propose a Neighbor-Regularized and context-aware Non-negative Tensor Factorization model (NR-cNTF) to discover interpretable urban dynamics from urban heterogeneous data.
no code implementations • 18 Aug 2018 • Ze Wang, Zehao Xiao, Kai Xie, Qiang Qiu, Xian-Tong Zhen, Xian-Bin Cao
Crowd counting usually addressed by density estimation becomes an increasingly important topic in computer vision due to its widespread applications in video surveillance, urban planning, and intelligence gathering.
2 code implementations • 4 Jul 2018 • Ze Wang, Weiqiang Ren, Qiang Qiu
Lane detection is to detect lanes on the road and provide the accurate location and shape of each lane.
2 code implementations • 23 Jun 2018 • Jingyuan Wang, Ze Wang, Jianfeng Li, Junjie Wu
In light of this, in this paper we propose a wavelet-based neural network structure called multilevel Wavelet Decomposition Network (mWDN) for building frequency-aware deep learning models for time series analysis.
1 code implementation • 1 Apr 2018 • Baochang Zhang, Lian Zhuo, Ze Wang, Jungong Han, Xian-Tong Zhen
Representation learning is a fundamental but challenging problem, especially when the distribution of data is unknown.
no code implementations • 29 Jan 2018 • Danfeng Xie, Li Bai, Ze Wang
Arterial spin labeling perfusion MRI is a noninvasive technique for measuring quantitative cerebral blood flow (CBF), but the measurement is subject to a low signal-to-noise-ratio(SNR).
no code implementations • 17 Jun 2015 • Ze Wang
Based on an empirical analysis of properties of the distance function of the acquired MRF signal and the pre-defined MRF dictionary entries, we proposed a parameter separable MRF DGS method, which breaks the multiplicative computation complexity into an additive one and enabling a resolution scalable multi-resolution DGS process, which was dubbed as MRF ZOOM.