Search Results for author: Hui Huang

Found 70 papers, 25 papers with code

Iterative Constrained Back-Translation for Unsupervised Domain Adaptation of Machine Translation

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.

Machine Translation NMT +4

Self-Evaluation of Large Language Model based on Glass-box Features

no code implementations7 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.

Language Modelling Large Language Model

Deformable One-shot Face Stylization via DINO Semantic Guidance

1 code implementation1 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.

One-Shot Face Stylization

Unsupervised Generation of Pseudo Normal PET from MRI with Diffusion Model for Epileptic Focus Localization

no code implementations2 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.

Lesion Detection Translation

Cross Domain Early Crop Mapping using CropGAN and CNN Classifier

no code implementations15 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.

Generative Adversarial Network

EmoGen: Emotional Image Content Generation with Text-to-Image Diffusion Models

no code implementations9 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.

Attribute Image Generation

Generating Non-Stationary Textures using Self-Rectification

1 code implementation5 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.

Texture Synthesis

Interaction-Driven Active 3D Reconstruction with Object Interiors

no code implementations23 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.

3D Reconstruction Object

TwinTex: Geometry-aware Texture Generation for Abstracted 3D Architectural Models

no code implementations20 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.

Texture Synthesis

Multi-Modal Automatic Prosody Annotation with Contrastive Pretraining of SSWP

1 code implementation11 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.

TranssionADD: A multi-frame reinforcement based sequence tagging model for audio deepfake detection

no code implementations27 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.

Data Augmentation DeepFake Detection +1

Feature Fusion from Head to Tail for Long-Tailed Visual Recognition

1 code implementation12 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).

Adjusting Logit in Gaussian Form for Long-Tailed Visual Recognition

1 code implementation18 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.

Enhancing Large Language Model with Self-Controlled Memory Framework

1 code implementation26 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.

Document Summarization Instruction Following +4

Semi-Weakly Supervised Object Kinematic Motion Prediction

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.

motion prediction Object +3

Character, Word, or Both? Revisiting the Segmentation Granularity for Chinese Pre-trained Language Models

1 code implementation20 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.

Neural Texture Synthesis With Guided Correspondence

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.

Texture Synthesis

ARO-Net: Learning Implicit Fields from Anchored Radial Observations

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.

Surface Reconstruction

NIFT: Neural Interaction Field and Template for Object Manipulation

no code implementations20 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.

Descriptive Imitation Learning +1

Learning Reconstructability for Drone Aerial Path Planning

no code implementations21 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.

3D Scene Reconstruction

Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation

no code implementations15 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.

Active Learning Scene Segmentation +2

Photo-to-Shape Material Transfer for Diverse Structures

1 code implementation9 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.

Segmentation Translation

Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interaction

no code implementations3 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.

Object

ARM3D: Attention-based relation module for indoor 3D object detection

1 code implementation20 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.

3D Object Detection Graph Embedding +3

3DRM:Pair-wise relation module for 3D object detection

1 code implementation20 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.

3D Object Detection Object +3

Point cloud completion via structured feature maps using a feedback network

no code implementations17 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.

Point Cloud Completion

FEAT: Face Editing with Attention

no code implementations6 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.

Disentanglement

ShapeFormer: Transformer-based Shape Completion via Sparse Representation

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.

Learning Practically Feasible Policies for Online 3D Bin Packing

2 code implementations31 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.

3D Bin Packing Collision Avoidance

Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset

2 code implementations9 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.

3D Reconstruction Instance Segmentation +1

Consistent Two-Flow Network for Tele-Registration of Point Clouds

1 code implementation1 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.

Vocal Bursts Valence Prediction

VGF-Net: Visual-Geometric Fusion Learning for Simultaneous Drone Navigation and Height Mapping

no code implementations7 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.

Drone navigation

Shape-driven Coordinate Ordering for Star Glyph Sets via Reinforcement Learning

no code implementations3 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.

Perceptual Distance reinforcement-learning +1

Hausdorff Point Convolution with Geometric Priors

no code implementations24 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.

Semantic Segmentation

On Learning the Right Attention Point for Feature Enhancement

no code implementations11 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.

Classification Point Cloud Classification +1

TAP-Net: Transport-and-Pack using Reinforcement Learning

no code implementations3 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.

reinforcement-learning Reinforcement Learning (RL)

Object Properties Inferring from and Transfer for Human Interaction Motions

no code implementations20 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.

Fine-grained Action Recognition Object

Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition

no code implementations29 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.

Anomaly Detection Clustering +2

Predictive and Generative Neural Networks for Object Functionality

1 code implementation28 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.

Object

RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud

1 code implementation26 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.

Semantic Segmentation

Sparse Gaussian Process Based On Hat Basis Functions

no code implementations15 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.

regression

GraftNet: An Engineering Implementation of CNN for Fine-grained Multi-label Task

no code implementations27 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.

General Classification Multi-Label Classification

Graph2Plan: Learning Floorplan Generation from Layout Graphs

no code implementations27 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.

Efficient q-Integer Linear Decomposition of Multivariate Polynomials

no code implementations1 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

Consensus-Based Optimization on the Sphere: Convergence to Global Minimizers and Machine Learning

1 code implementation31 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.

BIG-bench Machine Learning Retrieval

Consensus-Based Optimization on Hypersurfaces: Well-Posedness and Mean-Field Limit

no code implementations31 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.

ETNet: Error Transition Network for Arbitrary Style Transfer

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.

Style Transfer

Active Scene Understanding via Online Semantic Reconstruction

no code implementations18 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.

Scene Understanding Semantic Segmentation

LOGAN: Unpaired Shape Transform in Latent Overcomplete Space

no code implementations25 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.

Generative Adversarial Network Translation

Multi-Scale Context Intertwining for Semantic Segmentation

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.

Image Segmentation Segmentation +1

Neural Material: Learning Elastic Constitutive Material and Damping Models from Sparse Data

no code implementations15 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

Structure-aware Generative Network for 3D-Shape Modeling

1 code implementation12 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

Specular-to-Diffuse Translation for Multi-View Reconstruction

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.

3D Reconstruction Generative Adversarial Network +4

Non-Stationary Texture Synthesis by Adversarial Expansion

1 code implementation11 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.

Generative Adversarial Network Texture Synthesis

Full 3D Reconstruction of Transparent Objects

no code implementations9 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.

3D Reconstruction Transparent objects

P2P-NET: Bidirectional Point Displacement Net for Shape Transform

no code implementations25 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.

Cascaded Feature Network for Semantic Segmentation of RGB-D Images

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".

Semantic Segmentation

Learning to Aggregate Ordinal Labels by Maximizing Separating Width

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.

Recurrent 3D Attentional Networks for End-to-End Active Object Recognition

no code implementations14 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.

Object Recognition

Faster gradient descent and the efficient recovery of images

no code implementations12 Aug 2013 Hui Huang, Uri Ascher

For unconstrained convex quadratic optimization these methods can converge much faster than steepest descent.

Deblurring Denoising +1

Cannot find the paper you are looking for? You can Submit a new open access paper.