no code implementations • EMNLP (WNUT) 2020 • Zhe Hu, Zuohui Fu, Cheng Peng, Weiwei Wang
Cross-sentence attention has been widely applied in text matching, in which model learns the aligned information between two intermediate sequence representations to capture their semantic relationship.
no code implementations • 1 Feb 2024 • Tianhan Xu, Zhe Hu, Ling Chen, Bin Li
In the next stage, we train the skill router using task-specific downstream data and use this router to integrate the acquired skills with LLMs during inference.
no code implementations • 31 Oct 2023 • Zhe Hu, Hou Pong Chan, Yu Yin
Argument generation is a challenging task in natural language processing, which requires rigorous reasoning and proper content organization.
no code implementations • 13 Apr 2023 • Fu-Long Hu, Hai-Tao Zhang, Bowen Xu, Zhe Hu, Wei Ren
Sufficient conditions are derived to guarantee both the minimal-time deadbeat consensus and the instant individual disagreement degree prediction.
1 code implementation • 26 Oct 2022 • Zhe Hu, Hou Pong Chan, Lifu Huang
Teaching neural models to generate narrative coherent texts is a critical problem.
no code implementations • ACL 2022 • Zhe Hu, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Hua Wu, Lifu Huang
Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that require proper content control and planning to form a coherent high-level logical flow.
no code implementations • 14 Sep 2021 • Zhe Hu, Zhiwei Cao, Hou Pong Chan, Jiachen Liu, Xinyan Xiao, Jinsong Su, Hua Wu
Controllable text generation is an appealing but challenging task, which allows users to specify particular attributes of the generated outputs.
no code implementations • EMNLP 2021 • Zhe Hu, Zuohui Fu, Yu Yin, Gerard de Melo
Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations.
1 code implementation • ECCV 2020 • Jinsun Park, Kyungdon Joo, Zhe Hu, Chi-Kuei Liu, In So Kweon
In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion.
Ranked #1 on Depth Completion on NYU-Depth V2
1 code implementation • CVPR 2020 • Hang Dong, Jinshan Pan, Lei Xiang, Zhe Hu, Xinyi Zhang, Fei Wang, Ming-Hsuan Yang
To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme.
Ranked #9 on Image Dehazing on Haze4k
1 code implementation • 2 Mar 2020 • Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, Ming-Hsuan Yang
To address this problem, we propose a dual-branch convolutional neural network to extract base features and recovered features separately.
no code implementations • IJCNLP 2019 • Eva Sharma, Luyang Huang, Zhe Hu, Lu Wang
Human judges further rate our system summaries as more informative and coherent than those by popular summarization models.
no code implementations • 16 Dec 2018 • Yinglan Ma, Hongyu Xiong, Zhe Hu, Lizhuang Ma
As a way to significantly reduce model size and computation time, binarized neural network has only been shown to excel on semantic-level tasks such as image classification and recognition.
no code implementations • 12 Sep 2018 • Zhe Hu, Jia Pan, Tingxiang Fan, Ruigang Yang, Dinesh Manocha
In this paper, we present a robotic navigation algorithm with natural language interfaces, which enables a robot to safely walk through a changing environment with moving persons by following human instructions such as "go to the restaurant and keep away from people".
2 code implementations • 27 Jul 2018 • Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, Ming-Hsuan Yang
Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution.
no code implementations • 15 May 2018 • Jinshan Pan, Wenqi Ren, Zhe Hu, Ming-Hsuan Yang
However, existing methods are less effective as only few edges can be restored from blurry face images for kernel estimation.
no code implementations • 7 Dec 2017 • Zhe Hu, Yinglan Ma, Lizhuang Ma
Traditional approaches to interpolate/extrapolate frames in a video sequence require accurate pixel correspondences between images, e. g., using optical flow.
no code implementations • CVPR 2016 • Jinshan Pan, Zhe Hu, Zhixun Su, Hsin-Ying Lee, Ming-Hsuan Yang
To address these problems, we propose a novel model for object motion deblurring.
no code implementations • CVPR 2016 • Wei-Sheng Lai, Jia-Bin Huang, Zhe Hu, Narendra Ahuja, Ming-Hsuan Yang
Using these datasets, we conduct a large-scale user study to quantify the performance of several representative state-of-the-art blind deblurring algorithms.
no code implementations • CVPR 2016 • Zhe Hu, Lu Yuan, Stephen Lin, Ming-Hsuan Yang
Removing image blur caused by camera shake is an ill-posed problem, as both the latent image and the point spread function (PSF) are unknown.
no code implementations • CVPR 2014 • Zhe Hu, Sunghyun Cho, Jue Wang, Ming-Hsuan Yang
Images taken in low-light conditions with handheld cameras are often blurry due to the required long exposure time.
Ranked #11 on Deblurring on RealBlur-R (trained on GoPro)
no code implementations • CVPR 2014 • Jinshan Pan, Zhe Hu, Zhixun Su, Ming-Hsuan Yang
We propose a simple yet effective L_0-regularized prior based on intensity and gradient for text image deblurring.
no code implementations • CVPR 2014 • Zhe Hu, Li Xu, Ming-Hsuan Yang
The non-uniform blur effect is not only caused by the camera motion, but also the depth variation of the scene.