no code implementations • Findings (EMNLP) 2021 • Siyu Lai, Hui Huang, Dong Jing, Yufeng Chen, Jinan Xu, Jian Liu
Recent multilingual pre-trained models, like XLM-RoBERTa (XLM-R), have been demonstrated effective in many cross-lingual tasks.
Cross-Lingual Sentiment Classification Dialogue State Tracking +4
1 code implementation • COLING 2022 • Hongxiao Zhang, Hui Huang, Jiale Gao, Yufeng Chen, Jinan Xu, Jian Liu
In this paper, we propose an Iterative Constrained Back-Translation (ICBT) method to incorporate in-domain lexical knowledge on the basis of BT for unsupervised domain adaptation of NMT.
no code implementations • 7 Mar 2024 • Hui Huang, Yingqi Qu, Jing Liu, Muyun Yang, Tiejun Zhao
The proliferation of open-source Large Language Models (LLMs) underscores the pressing need for evaluation methods.
no code implementations • 5 Mar 2024 • Hui Huang, Yingqi Qu, Jing Liu, Muyun Yang, Tiejun Zhao
Recently, there has been a growing trend of utilizing Large Language Model (LLM) to evaluate the quality of other LLMs.
1 code implementation • 1 Mar 2024 • Yang Zhou, Zichong Chen, Hui Huang
This paper addresses the complex issue of one-shot face stylization, focusing on the simultaneous consideration of appearance and structure, where previous methods have fallen short.
no code implementations • 2 Feb 2024 • Wentao Chen, Jiwei Li, Xichen Xu, Hui Huang, Siyu Yuan, Miao Zhang, Tianming Xu, Jie Luo, Weimin Zhou
In this study, we investigated unsupervised learning methods for unpaired MRI to PET translation for generating pseudo normal FDG PET for epileptic focus localization.
no code implementations • 15 Jan 2024 • Yiqun Wang, Hui Huang, Radu State
Instead, it learns a mapping function to transform the spectral features of the target domain to the source domain (with labels) while preserving their local structure.
no code implementations • 9 Jan 2024 • Jingyuan Yang, Jiawei Feng, Hui Huang
Recent years have witnessed remarkable progress in image generation task, where users can create visually astonishing images with high-quality.
1 code implementation • 5 Jan 2024 • Yang Zhou, Rongjun Xiao, Dani Lischinski, Daniel Cohen-Or, Hui Huang
This paper addresses the challenge of example-based non-stationary texture synthesis.
no code implementations • 23 Oct 2023 • Zihao Yan, Fubao Su, Mingyang Wang, Ruizhen Hu, Hao Zhang, Hui Huang
We introduce an active 3D reconstruction method which integrates visual perception, robot-object interaction, and 3D scanning to recover both the exterior and interior, i. e., unexposed, geometries of a target 3D object.
no code implementations • 17 Oct 2023 • Juzhan Xu, Minglun Gong, Hao Zhang, Hui Huang, Ruizhen Hu
We present a novel learning framework to solve the transport-and-packing (TAP) problem in 3D.
no code implementations • 20 Sep 2023 • Weidan Xiong, Hongqian Zhang, Botao Peng, Ziyu Hu, Yongli Wu, Jianwei Guo, Hui Huang
In this paper, we present TwinTex, the first automatic texture mapping framework to generate a photo-realistic texture for a piece-wise planar proxy.
1 code implementation • 11 Sep 2023 • Jinzuomu Zhong, Yang Li, Hui Huang, Jie Liu, Zhiba Su, Jing Guo, Benlai Tang, Fengjie Zhu
While human prosody annotation contributes a lot to the performance, it is a labor-intensive and time-consuming process, often resulting in inconsistent outcomes.
no code implementations • ICCV 2023 • Jingyuan Yang, Qirui Huang, Tingting Ding, Dani Lischinski, Daniel Cohen-Or, Hui Huang
Most of the existing work in this area focuses on feature design, while little attention has been paid to dataset construction.
no code implementations • 27 Jun 2023 • Jie Liu, Zhiba Su, Hui Huang, Caiyan Wan, Quanxiu Wang, Jiangli Hong, Benlai Tang, Fengjie Zhu
We propose our novel TranssionADD system as a solution to the challenging problem of model robustness and audio segment outliers in the trace competition.
1 code implementation • 12 Jun 2023 • Mengke Li, Zhikai Hu, Yang Lu, Weichao Lan, Yiu-ming Cheung, Hui Huang
To rectify this issue, we propose to augment tail classes by grafting the diverse semantic information from head classes, referred to as head-to-tail fusion (H2T).
1 code implementation • 18 May 2023 • Mengke Li, Yiu-ming Cheung, Yang Lu, Zhikai Hu, Weichao Lan, Hui Huang
Based on these perturbed features, two novel logit adjustment methods are proposed to improve model performance at a modest computational overhead.
no code implementations • 4 May 2023 • Guoqing Yang, Fuyou Xue, Qi Zhang, Ke Xie, Chi-Wing Fu, Hui Huang
Besides, we propose B-Seg, a building instance segmentation method to establish UrbanBIS.
1 code implementation • 26 Apr 2023 • Bing Wang, Xinnian Liang, Jian Yang, Hui Huang, Shuangzhi Wu, Peihao Wu, Lu Lu, Zejun Ma, Zhoujun Li
Large Language Models (LLMs) are constrained by their inability to process lengthy inputs, resulting in the loss of critical historical information.
no code implementations • CVPR 2023 • Gengxin Liu, Qian Sun, Haibin Huang, Chongyang Ma, Yulan Guo, Li Yi, Hui Huang, Ruizhen Hu
First, although 3D dataset with fully annotated motion labels is limited, there are existing datasets and methods for object part semantic segmentation at large scale.
1 code implementation • 23 Mar 2023 • Xinnian Liang, Shuangzhi Wu, Hui Huang, Jiaqi Bai, Chao Bian, Zhoujun Li
Retrieval augmented methods have shown promising results in various classification tasks.
1 code implementation • 20 Mar 2023 • Xinnian Liang, Zefan Zhou, Hui Huang, Shuangzhi Wu, Tong Xiao, Muyun Yang, Zhoujun Li, Chao Bian
We conduct extensive experiments on various Chinese NLP tasks to evaluate existing PLMs as well as the proposed MigBERT.
no code implementations • CVPR 2023 • Yang Zhou, Kaijian Chen, Rongjun Xiao, Hui Huang
More importantly, the Guided Correspondence loss can function as a general textural loss in, e. g., training generative networks for real-time controlled synthesis and inversion-based single-image editing.
1 code implementation • CVPR 2023 • Yizhi Wang, Zeyu Huang, Ariel Shamir, Hui Huang, Hao Zhang, Ruizhen Hu
We introduce anchored radial observations (ARO), a novel shape encoding for learning implicit field representation of 3D shapes that is category-agnostic and generalizable amid significant shape variations.
no code implementations • 20 Oct 2022 • Zeyu Huang, Juzhan Xu, Sisi Dai, Kai Xu, Hao Zhang, Hui Huang, Ruizhen Hu
Given a few object manipulation demos, NIFT guides the generation of the interaction imitation for a new object instance by matching the Neural Interaction Template (NIT) extracted from the demos in the target Neural Interaction Field (NIF) defined for the new object.
no code implementations • 12 Oct 2022 • Hongxiao Zhang, Siyu Lai, Songming Zhang, Hui Huang, Yufeng Chen, Jinan Xu, Jian Liu
This paper introduces the system used in our submission to the WMT'22 Translation Suggestion shared task.
no code implementations • 21 Sep 2022 • Yilin Liu, Liqiang Lin, Yue Hu, Ke Xie, Chi-Wing Fu, Hao Zhang, Hui Huang
To reconstruct a new urban scene, we first build the 3D scene proxy, then rely on the predicted reconstruction quality and uncertainty measures by our network, based off of the proxy geometry, to guide the drone path planning.
no code implementations • 15 Sep 2022 • Gengxin Liu, Oliver van Kaick, Hui Huang, Ruizhen Hu
Since the preparation of labeled data for training semantic segmentation networks of point clouds is a time-consuming process, weakly supervised approaches have been introduced to learn from only a small fraction of data.
1 code implementation • 9 May 2022 • Ruizhen Hu, Xiangyu Su, Xiangkai Chen, Oliver van Kaick, Hui Huang
The image translation network translates the color from the exemplar to a projection of the 3D shape and the part segmentation from the projection to the exemplar.
no code implementations • 3 Apr 2022 • Qijin She, Ruizhen Hu, Juzhan Xu, Min Liu, Kai Xu, Hui Huang
To resolve the sample efficiency issue in learning the high-dimensional and complex control of dexterous grasping, we propose an effective representation of grasping state characterizing the spatial interaction between the gripper and the target object.
1 code implementation • 20 Feb 2022 • Yuqing Lan, Yao Duan, Chenyi Liu, Chenyang Zhu, Yueshan Xiong, Hui Huang, Kai Xu
In the field of 3D object detection, previous methods have been taking the advantage of context encoding, graph embedding, or explicit relation reasoning to extract relation context.
1 code implementation • 20 Feb 2022 • Yuqing Lan, Yao Duan, Yifei Shi, Hui Huang, Kai Xu
Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding.
no code implementations • 17 Feb 2022 • Zejia Su, Haibin Huang, Chongyang Ma, Hui Huang, Ruizhen Hu
To efficiently exploit local structures and enhance point distribution uniformity, we propose IFNet, a point upsampling module with a self-correction mechanism that can progressively refine details of the generated dense point cloud.
no code implementations • 6 Feb 2022 • Xianxu Hou, Linlin Shen, Or Patashnik, Daniel Cohen-Or, Hui Huang
In this paper, we build on the StyleGAN generator, and present a method that explicitly encourages face manipulation to focus on the intended regions by incorporating learned attention maps.
1 code implementation • CVPR 2022 • Xingguang Yan, Liqiang Lin, Niloy J. Mitra, Dani Lischinski, Daniel Cohen-Or, Hui Huang
We present ShapeFormer, a transformer-based network that produces a distribution of object completions, conditioned on incomplete, and possibly noisy, point clouds.
2 code implementations • 31 Aug 2021 • Hang Zhao, Chenyang Zhu, Xin Xu, Hui Huang, Kai Xu
In this problem, the items are delivered to the agent without informing the full sequence information.
2 code implementations • 9 Jul 2021 • Liqiang Lin, Yilin Liu, Yue Hu, Xingguang Yan, Ke Xie, Hui Huang
We present UrbanScene3D, a large-scale data platform for research of urban scene perception and reconstruction.
1 code implementation • 1 Jun 2021 • Zihao Yan, Zimu Yi, Ruizhen Hu, Niloy J. Mitra, Daniel Cohen-Or, Hui Huang
In this paper, we present a learning-based technique that alleviates this problem, and allows registration between point clouds, presented in arbitrary poses, and having little or even no overlap, a setting that has been referred to as tele-registration.
no code implementations • 7 Apr 2021 • Yilin Liu, Ke Xie, Hui Huang
The drone navigation requires the comprehensive understanding of both visual and geometric information in the 3D world.
no code implementations • 3 Mar 2021 • Ruizhen Hu, Bin Chen, Juzhan Xu, Oliver van Kaick, Oliver Deussen, Hui Huang
Given a set of star glyphs associated to multiple class labels, we propose to use shape context descriptors to measure the perceptual distance between pairs of glyphs, and use the derived silhouette coefficient to measure the perception of class separability within the entire set.
no code implementations • 24 Dec 2020 • Pengdi Huang, Liqiang Lin, Fuyou Xue, Kai Xu, Danny Cohen-Or, Hui Huang
We show that HPC constitutes a powerful point feature learning with a rather compact set of only four types of geometric priors as kernels.
no code implementations • 11 Dec 2020 • Liqiang Lin, Pengdi Huang, Chi-Wing Fu, Kai Xu, Hao Zhang, Hui Huang
We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e. g., classification and segmentation.
no code implementations • 3 Sep 2020 • Ruizhen Hu, Juzhan Xu, Bin Chen, Minglun Gong, Hao Zhang, Hui Huang
Using a learning-based approach, a trained network can learn and encode solution patterns to guide the solution of new problem instances instead of executing an expensive online search.
no code implementations • 20 Aug 2020 • Qian Zheng, Weikai Wu, Hanting Pan, Niloy Mitra, Daniel Cohen-Or, Hui Huang
In this paper, we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone.
no code implementations • 29 Jun 2020 • Chunhua Jia, Wenhai Yi, Yu Wu, Hui Huang, Lei Zhang, Leilei Wu
We present a work-flow which aims at capturing residents' abnormal activities through the passenger flow of elevator in multi-storey residence buildings.
1 code implementation • 28 Jun 2020 • Ruizhen Hu, Zihao Yan, Jingwen Zhang, Oliver van Kaick, Ariel Shamir, Hao Zhang, Hui Huang
Given a 3D object in isolation, our functional similarity network (fSIM-NET), a variation of the triplet network, is trained to predict the functionality of the object by inferring functionality-revealing interaction contexts.
1 code implementation • 26 Jun 2020 • Zihao Yan, Ruizhen Hu, Xingguang Yan, Luanmin Chen, Oliver van Kaick, Hao Zhang, Hui Huang
We show results of simultaneous motion and part predictions from synthetic and real scans of 3D objects exhibiting a variety of part mobilities, possibly involving multiple movable parts.
no code implementations • 15 Jun 2020 • Wenqi Fang, Huiyun Li, Hui Huang, Shaobo Dang, Zhejun Huang, Zheng Wang
Based on hat basis functions, we propose a new sparse Gaussian process method to solve the unconstrained regression problem.
no code implementations • 27 Apr 2020 • Chunhua Jia, Lei Zhang, Hui Huang, Weiwei Cai, Hao Hu, Rohan Adivarekar
Multi-label networks with branches are proved to perform well in both accuracy and speed, but lacks flexibility in providing dynamic extension onto new labels due to the low efficiency of re-work on annotating and training.
no code implementations • 27 Apr 2020 • Ruizhen Hu, Zeyu Huang, Yuhan Tang, Oliver van Kaick, Hao Zhang, Hui Huang
The core component of our learning framework is a deep neural network, Graph2Plan, which converts a layout graph, along with a building boundary, into a floorplan that fulfills both the layout and boundary constraints.
no code implementations • 1 Feb 2020 • Mark Giesbrecht, Hui Huang, George Labahn, Eugene Zima
We present two new algorithms for the computation of the q-integer linear decomposition of a multivariate polynomial.
Symbolic Computation Rings and Algebras
1 code implementation • 31 Jan 2020 • Massimo Fornasier, Hui Huang, Lorenzo Pareschi, Philippe Sünnen
To quantify the performances of the new approach, we show that the algorithm is able to perform essentially as good as ad hoc state of the art methods in challenging problems in signal processing and machine learning, namely the phase retrieval problem and the robust subspace detection.
no code implementations • 31 Jan 2020 • Massimo Fornasier, Hui Huang, Lorenzo Pareschi, Philippe Sünnen
We introduce a new stochastic differential model for global optimization of nonconvex functions on compact hypersurfaces.
1 code implementation • NeurIPS 2019 • Chunjin Song, Zhijie Wu, Yang Zhou, Minglun Gong, Hui Huang
Numerous valuable efforts have been devoted to achieving arbitrary style transfer since the seminal work of Gatys et al.
no code implementations • 18 Jun 2019 • Lintao Zheng, Chenyang Zhu, Jiazhao Zhang, Hang Zhao, Hui Huang, Matthias Niessner, Kai Xu
In our method, the exploratory robot scanning is both driven by and targeting at the recognition and segmentation of semantic objects from the scene.
no code implementations • 25 Mar 2019 • Kangxue Yin, Zhiqin Chen, Hui Huang, Daniel Cohen-Or, Hao Zhang
Our network consists of an autoencoder to encode shapes from the two input domains into a common latent space, where the latent codes concatenate multi-scale shape features, resulting in an overcomplete representation.
1 code implementation • ACM Transactions on Graphics (Proc. SIGGRAPH ASIA) 2019 • Hao Wang, Nadav Schor, Ruizhen Hu, Haibin Huang, Daniel Cohen-Or, Hui Huang
We also introduce new means to measure and evaluate the performance of an adversarial generative model.
3 code implementations • CVPR 2019 • Wang Yifan, Shihao Wu, Hui Huang, Daniel Cohen-Or, Olga Sorkine-Hornung
We present a detail-driven deep neural network for point set upsampling.
no code implementations • 26 Nov 2018 • Zhijie Wu, Chunjin Song, Yang Zhou, Minglun Gong, Hui Huang
Style transfer has been an important topic both in computer vision and graphics.
no code implementations • ECCV 2018 • Di Lin, Yuanfeng Ji, Dani Lischinski, Daniel Cohen-Or, Hui Huang
Accurate semantic image segmentation requires the joint consideration of local appearance, semantic information, and global scene context.
no code implementations • 15 Aug 2018 • Bin Wang, Paul Kry, Yuanmin Deng, Uri Ascher, Hui Huang, Baoquan Chen
The challenge is that such data is sparse as it is consistently given only on part of the surface.
Graphics
1 code implementation • 12 Aug 2018 • Zhijie Wu, Xiang Wang, Di Lin, Dani Lischinski, Daniel Cohen-Or, Hui Huang
The key idea is that during the analysis, the two branches exchange information between them, thereby learning the dependencies between structure and geometry and encoding two augmented features, which are then fused into a single latent code.
Graphics
no code implementations • ECCV 2018 • Shihao Wu, Hui Huang, Tiziano Portenier, Matan Sela, Danny Cohen-Or, Ron Kimmel, Matthias Zwicker
To alleviate this restriction, we introduce S2Dnet, a generative adversarial network for transferring multiple views of objects with specular reflection into diffuse ones, so that multi-view reconstruction methods can be applied more effectively.
1 code implementation • 11 May 2018 • Yang Zhou, Zhen Zhu, Xiang Bai, Dani Lischinski, Daniel Cohen-Or, Hui Huang
We demonstrate that this conceptually simple approach is highly effective for capturing large-scale structures, as well as other non-stationary attributes of the input exemplar.
no code implementations • 9 May 2018 • Bojian Wu, Yang Zhou, Yiming Qian, Minglun Gong, Hui Huang
Numerous techniques have been proposed for reconstructing 3D models for opaque objects in past decades.
no code implementations • 25 Mar 2018 • Kangxue Yin, Hui Huang, Daniel Cohen-Or, Hao Zhang
We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e. g., meso-skeletons and surfaces, partial and complete scans, etc.
no code implementations • ICCV 2017 • Di Lin, Guangyong Chen, Daniel Cohen-Or, Pheng-Ann Heng, Hui Huang
Our approach is to use the available depth to split the image into layers with common visual characteristic of objects/scenes, or common "scene-resolution".
Ranked #70 on Semantic Segmentation on NYU Depth v2
no code implementations • ICML 2017 • Guangyong Chen, Shengyu Zhang, Di Lin, Hui Huang, Pheng Ann Heng
While crowdsourcing has been a cost and time efficient method to label massive samples, one critical issue is quality control, for which the key challenge is to infer the ground truth from noisy or even adversarial data by various users.
no code implementations • 14 Oct 2016 • Min Liu, Yifei Shi, Lintao Zheng, Kai Xu, Hui Huang, Dinesh Manocha
Active vision is inherently attention-driven: The agent actively selects views to attend in order to fast achieve the vision task while improving its internal representation of the scene being observed.
no code implementations • 12 Aug 2013 • Hui Huang, Uri Ascher
For unconstrained convex quadratic optimization these methods can converge much faster than steepest descent.