no code implementations • COLING 2022 • Jinfeng Zhou, Bo wang, Zhitong Yang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
In CRS, implicit patterns of user interest sequence guide the smooth transition of dialog utterances to the goal item.
no code implementations • COLING 2022 • Zhitong Yang, Bo wang, Jinfeng Zhou, Yue Tan, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
We design a global reinforcement learning with the planned paths to flexibly adjust the local response generation model towards the global target.
1 code implementation • 24 Jan 2024 • Qi Sun, Kun Huang, Xiaocui Yang, Rong Tong, Kun Zhang, Soujanya Poria
In this paper, we propose a Zero-shot Document-level Relation Triplet Extraction (ZeroDocRTE) framework, which generates labeled data by retrieval and denoising knowledge from LLMs, called GenRDK.
1 code implementation • 12 Jan 2024 • Wenyuan Zhang, Xinghua Zhang, Shiyao Cui, Kun Huang, Xuebin Wang, Tingwen Liu
Aspect sentiment quad prediction (ASQP) aims to predict the quad sentiment elements for a given sentence, which is a critical task in the field of aspect-based sentiment analysis.
1 code implementation • 12 Dec 2023 • Xiao Ma, Zetian Zhang, Zexuan Ji, Kun Huang, Na Su, Songtao Yuan, Qiang Chen
Measurements of spherical equivalent and axial length are the gold standards for identifying high myopia, but the available image data for matching them is scarce.
1 code implementation • 27 Aug 2023 • Yang Wang, Zanyu Shi, Timothy Richardson, Kun Huang, Pathum Weerawarna, Yijie Wang
Due to the use of the chemical-substructure-based graph, it is guaranteed that any subgraphs in a drug identified by our SLGNN are chemically valid structures.
no code implementations • 24 Aug 2023 • Yachao Zhao, Bo wang, Dongming Zhao, Kun Huang, Yan Wang, Ruifang He, Yuexian Hou
We propose that this re-judge inconsistency can be similar to the inconsistency between human's unaware implicit social bias and their aware explicit social bias.
no code implementations • 12 Aug 2023 • Yuhan Zhang, Kun Huang, Mingchao Li, Songtao Yuan, Qiang Chen
We propose a single-horizon disease evolution network (SHENet) to predictively generate post-therapeutic SD-OCT images by inputting pre-therapeutic SD-OCT images with neovascular age-related macular degeneration (nAMD).
no code implementations • 21 Jun 2023 • Kun Huang, Linli Zhou, Shi Pu
Notably, both results are comparable to the convergence rates of centralized RR methods (up to constant factors depending on the network topology) and outperform those of previous distributed random reshuffling algorithms.
1 code implementation • 19 May 2023 • Yihong Tang, Bo wang, Miao Fang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
We design a Contrastive Latent Variable-based model (CLV) that clusters the dense persona descriptions into sparse categories, which are combined with the history query to generate personalized responses.
1 code implementation • 18 May 2023 • Qi Sun, Kun Huang, Xiaocui Yang, Pengfei Hong, Kun Zhang, Soujanya Poria
Therefore, how to select effective pseudo labels to denoise DS data is still a challenge in document-level distant relation extraction.
no code implementations • 11 Apr 2023 • Xiaoqing Huang, Andersen Ang, Kun Huang, Jie Zhang, Yijie Wang
We study estimation of piecewise smooth signals over a graph.
no code implementations • 30 Jan 2023 • Kun Huang, Xiao Li, Shi Pu
Distributed stochastic optimization has drawn great attention recently due to its effectiveness in solving large-scale machine learning problems.
no code implementations • 14 Jan 2023 • Kun Huang, Shi Pu
In this paper, we consider solving the distributed optimization problem over a multi-agent network under the communication restricted setting.
no code implementations • 12 Jan 2023 • Yushan Qian, Bo wang, Shangzhao Ma, Wu Bin, Shuo Zhang, Dongming Zhao, Kun Huang, Yuexian Hou
Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network.
1 code implementation • 17 Dec 2022 • Kun Huang, Edward S. Hu, Dinesh Jayaraman
Physical interactions can often help reveal information that is not readily apparent.
no code implementations • 5 Nov 2022 • Jinfeng Zhou, Bo wang, Minlie Huang, Dongming Zhao, Kun Huang, Ruifang He, Yuexian Hou
Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations with rich explanations.
no code implementations • 27 Jul 2022 • Yiheng Li, Connelly Barnes, Kun Huang, Fang-Lue Zhang
Optical flow computation is essential in the early stages of the video processing pipeline.
no code implementations • 7 May 2022 • Mingchao Li, Kun Huang, Zetian Zhang, Xiao Ma, Qiang Chen
This continuous process allows us to recommend high-quality vessel segmentation with clear caliber and topology.
1 code implementation • 2 Feb 2022 • Yifu Wang, Wenqing Jiang, Kun Huang, Sören Schwertfeger, Laurent Kneip
Multi-perspective cameras are quickly gaining importance in many applications such as smart vehicles and virtual or augmented reality.
no code implementations • 31 Dec 2021 • Kun Huang, Xiao Li, Andre Milzarek, Shi Pu, Junwen Qiu
We show that D-RR inherits favorable characteristics of RR for both smooth strongly convex and smooth nonconvex objective functions.
no code implementations • NeurIPS 2021 • Andersen Ang, Jianzhu Ma, Nianjun Liu, Kun Huang, Yijie Wang
We demonstrate that the proposed algorithm can produce a solution of the projection problem with high precision on large scale datasets, and the algorithm is able to significantly outperform the state-of-the-art methods in terms of runtime (about 6-8 times faster than a commercial software with respect to CPU time for input vector with 1 million variables or more).
no code implementations • ICLR 2022 • Edward S. Hu, Kun Huang, Oleh Rybkin, Dinesh Jayaraman
Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data.
1 code implementation • 19 Jul 2021 • Edward S. Hu, Kun Huang, Oleh Rybkin, Dinesh Jayaraman
Training visual control policies from scratch on a new robot typically requires generating large amounts of robot-specific data.
1 code implementation • 14 Jul 2021 • Kun Huang, Yifu Wang, Laurent Kneip
Camera calibration is an important prerequisite towards the solution of 3D computer vision problems.
no code implementations • 7 Jul 2021 • Yifu Wang, Jiaqi Yang, Xin Peng, Peng Wu, Ling Gao, Kun Huang, Jiaben Chen, Laurent Kneip
We present a new solution to tracking and mapping with an event camera.
no code implementations • 3 Jun 2021 • Ju Sun, Le Peng, Taihui Li, Dyah Adila, Zach Zaiman, Genevieve B. Melton, Nicholas Ingraham, Eric Murray, Daniel Boley, Sean Switzer, John L. Burns, Kun Huang, Tadashi Allen, Scott D. Steenburg, Judy Wawira Gichoya, Erich Kummerfeld, Christopher Tignanelli
Conclusions and Relevance: AI-based diagnostic tools may serve as an adjunct, but not replacement, for clinical decision support of COVID-19 diagnosis, which largely hinges on exposure history, signs, and symptoms.
no code implementations • 11 May 2021 • Kun Huang, Shi Pu
To the best of our knowledge, EDAS achieves the shortest transient time when the average of the $n$ cost functions is strongly convex and each cost function is smooth.
1 code implementation • 1 Apr 2021 • Andrew Price, Kun Huang, Dmitry Berenson
In this work, we propose Multihypothesis Segmentation Tracking (MST), a novel method for volumetric segmentation in changing scenes, which allows scene ambiguity to be tracked and our estimates to be adjusted over time as we interact with the scene.
3 code implementations • 14 Dec 2020 • Mingchao Li, Kun Huang, Qiuzhuo Xu, Jiadong Yang, Yuhan Zhang, Zexuan Ji, Keren Xie, Songtao Yuan, Qinghuai Liu, Qiang Chen
Optical coherence tomography angiography (OCTA) is a novel imaging modality that has been widely utilized in ophthalmology and neuroscience studies to observe retinal vessels and microvascular systems.
no code implementations • 9 Aug 2020 • Zhi Huang, Paul Salama, Wei Shao, Jie Zhang, Kun Huang
Towards the goal of precision health and cancer treatments, the proposed algorithm can help understand and interpret high-dimensional heterogeneous genomics data with accurate identification of survival-associated gene clusters.
1 code implementation • CVPR 2018 • Kun Huang, Yifan Wang, Zihan Zhou, Tianjiao Ding, Shenghua Gao, Yi Ma
To this end, we have built a very large new dataset of over 5, 000 images with wireframes thoroughly labelled by humans.
no code implementations • 4 Mar 2020 • Tongxin Wang, Zhengming Ding, Wei Shao, Haixu Tang, Kun Huang
Domain Adaptation (DA) targets at adapting a model trained over the well-labeled source domain to the unlabeled target domain lying in different distributions.
no code implementations • 23 Jul 2019 • Lan Hu, Wanting Xu, Kun Huang, Laurent Kneip
In an effort to increase the capabilities of SLAM systems and produce object-level representations, the community increasingly investigates the imposition of higher-level priors into the estimation process.
no code implementations • CVPR 2019 • Kun Huang, Yifu Wang, Laurent Kneip
The planar motion of ground vehicles is often non-holonomic, which enables a solution of the two-view relative pose problem from a single point feature correspondence.
1 code implementation • CVPR 2019 • Ziheng Zhang, Zhengxin Li, Ning Bi, Jia Zheng, Jinlei Wang, Kun Huang, Weixin Luo, Yanyu Xu, Shenghua Gao
In this paper, we present a novel framework to detect line segments in man-made environments.