no code implementations • 2 Aug 2024 • Dong Huo, Zixin Guo, Xinxin Zuo, Zhihao Shi, Juwei Lu, Peng Dai, Songcen Xu, Li Cheng, Yee-Hong Yang
For view consistent sampling, first of all we maintain a texture map in RGB space that is parameterized by the denoising step and updated after each sampling step of the diffusion model to progressively reduce the view discrepancy.
no code implementations • 19 Apr 2024 • Jie Wang, Zhihai Wang, Xijun Li, Yufei Kuang, Zhihao Shi, Fangzhou Zhu, Mingxuan Yuan, Jia Zeng, Yongdong Zhang, Feng Wu
Moreover, we observe that (P3) what order of selected cuts to prefer significantly impacts the efficiency of MILP solvers as well.
no code implementations • 5 Apr 2024 • Xize Liang, Chao Chen, Shuang Qiu, Jie Wang, Yue Wu, Zhihang Fu, Zhihao Shi, Feng Wu, Jieping Ye
Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses.
1 code implementation • 26 Sep 2023 • Zhihao Shi, Jie Wang, Fanghua Lu, Hanzhu Chen, Defu Lian, Zheng Wang, Jieping Ye, Feng Wu
The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias.
Ranked #1 on Node Property Prediction on ogbn-proteins
no code implementations • 20 Sep 2023 • Jie Wang, Hanzhu Chen, Qitan Lv, Zhihao Shi, Jiajun Chen, Huarui He, Hongtao Xie, Defu Lian, Enhong Chen, Feng Wu
This implies the great potential of the semantic correlations for the entity-independent inductive link prediction task.
no code implementations • 17 Mar 2023 • Jie Wang, Zhihao Shi, Xize Liang, Defu Lian, Shuiwang Ji, Bin Li, Enhong Chen, Feng Wu
During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i. e., the exponentially increasing dependencies of nodes with the number of MP iterations.
1 code implementation • 19 Feb 2023 • Jie Wang, Rui Yang, Zijie Geng, Zhihao Shi, Mingxuan Ye, Qi Zhou, Shuiwang Ji, Bin Li, Yongdong Zhang, Feng Wu
The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics.
1 code implementation • 2 Feb 2023 • Zhihao Shi, Xize Liang, Jie Wang
The key idea of LMC is to retrieve the discarded messages in backward passes based on a message passing formulation of backward passes.
no code implementations • 24 Mar 2022 • Jie Wang, Zhanqiu Zhang, Zhihao Shi, Jianyu Cai, Shuiwang Ji, Feng Wu
Semantic matching models -- which assume that entities with similar semantics have similar embeddings -- have shown great power in knowledge graph embeddings (KGE).
1 code implementation • CVPR 2022 • Zhihao Shi, Xiangyu Xu, Xiaohong Liu, Jun Chen, Ming-Hsuan Yang
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field.
no code implementations • 26 Mar 2021 • Xiaohong Liu, Yongrui Ma, Zhihao Shi, Linhui Dai, Jun Chen
We develop a new physical model for the rain effect and show that the well-known atmosphere scattering model (ASM) for the haze effect naturally emerges as its homogeneous continuous limit.
no code implementations • 25 Mar 2021 • Xiaohong Liu, Zhihao Shi, Zijun Wu, Jun Chen
We also propose a novel intra-task knowledge transfer mechanism that can memorize and take advantage of synthetic domain knowledge to assist the learning process on the translated data.
no code implementations • 25 Feb 2021 • Zhihao Shi, Xiaohong Liu, Chengqi Li, Linhui Dai, Jun Chen, Timothy N. Davidson, Jiying Zhao
Recent years have seen considerable research activities devoted to video enhancement that simultaneously increases temporal frame rate and spatial resolution.
Optical Flow Estimation Space-time Video Super-resolution +2
1 code implementation • 24 Aug 2020 • Zhihao Shi, Xiaohong Liu, Kangdi Shi, Linhui Dai, Jun Chen
Video frame interpolation aims at synthesizing intermediate frames from nearby source frames while maintaining spatial and temporal consistencies.
1 code implementation • ICCV 2019 • Xiaohong Liu, Yongrui Ma, Zhihao Shi, Jun Chen
The proposed hazing method does not rely on the atmosphere scattering model, and we provide an explanation as to why it is not necessarily beneficial to take advantage of the dimension reduction offered by the atmosphere scattering model for image dehazing, even if only the dehazing results on synthetic images are concerned.
Ranked #4 on Image Dehazing on RS-Haze