Search Results for author: Di Huang

Found 46 papers, 16 papers with code

Beyond 3DMM Space: Towards Fine-grained 3D Face Reconstruction

1 code implementation ECCV 2020 Xiangyu Zhu, Fan Yang, Di Huang, Chang Yu, Hao Wang, Jianzhu Guo, Zhen Lei, Stan Z. Li

However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space.

3D Face Reconstruction

Neural Program Synthesis with Query

no code implementations ICLR 2022 Di Huang, Rui Zhang, Xing Hu, Xishan Zhang, Pengwei Jin, Nan Li, Zidong Du, Qi Guo, Yunji Chen

In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space.

Program Synthesis

Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement

no code implementations7 May 2022 Bing Li, Jiaxin Chen, Dongming Zhang, Xiuguo Bao, Di Huang

To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net).

Action Recognition Denoising +1

Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection

no code implementations CVPR 2022 Jiaxi Wu, Jiaxin Chen, Mengzhe He, Yiru Wang, Bo Li, Bingqi Ma, Weihao Gan, Wei Wu, Yali Wang, Di Huang

Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain.

Disentanglement Domain Adaptation +2

Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint

no code implementations CVPR 2022 Jiaxi Wu, Jiaxin Chen, Di Huang

Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks by consciously selecting more informative samples to label.

Active Learning object-detection +1

Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape

no code implementations9 Apr 2022 Xiangyu Zhu, Chang Yu, Di Huang, Zhen Lei, Hao Wang, Stan Z. Li

3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori.

CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection

no code implementations CVPR 2022 Yanan Zhang, Jiaxin Chen, Di Huang

In autonomous driving, LiDAR point-clouds and RGB images are two major data modalities with complementary cues for 3D object detection.

3D Object Detection Autonomous Driving +3

ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations

1 code implementation CVPR 2022 Mingwu Zheng, Hongyu Yang, Di Huang, Liming Chen

Precise representations of 3D faces are beneficial to various computer vision and graphics applications.

Face Model

ABPN: Adaptive Blend Pyramid Network for Real-Time Local Retouching of Ultra High-Resolution Photo

1 code implementation CVPR 2022 Biwen Lei, Xiefan Guo, Hongyu Yang, Miaomiao Cui, Xuansong Xie, Di Huang

The network is mainly composed of two components: a context-aware local retouching layer (LRL) and an adaptive blend pyramid layer (BPL).

Photo Retouching

ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization

no code implementations21 Dec 2021 Zichen Yang, Jie Qin, Di Huang

Weakly-supervised temporal action localization (WTAL) in untrimmed videos has emerged as a practical but challenging task since only video-level labels are available.

Weakly-supervised Temporal Action Localization Weakly Supervised Temporal Action Localization

UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery

no code implementations20 Dec 2021 Yecheng Huang, Jiaxin Chen, Di Huang

This paper proposes a novel approach to object detection on drone imagery, namely Multi-Proxy Detection Network with Unified Foreground Packing (UFPMP-Det).

object-detection Object Detection

Segmentation-Reconstruction-Guided Facial Image De-occlusion

no code implementations15 Dec 2021 Xiangnan Yin, Di Huang, Zehua Fu, Yunhong Wang, Liming Chen

The proposed model consists of a 3D face reconstruction module, a face segmentation module, and an image generation module.

3D Face Reconstruction Image Generation

Boundary Guided Context Aggregation for Semantic Segmentation

1 code implementation27 Oct 2021 Haoxiang Ma, Hongyu Yang, Di Huang

The recent studies on semantic segmentation are starting to notice the significance of the boundary information, where most approaches see boundaries as the supplement of semantic details.

Boundary Detection Semantic Segmentation

Identity-aware Graph Memory Network for Action Detection

no code implementations26 Aug 2021 Jingcheng Ni, Jie Qin, Di Huang

Action detection plays an important role in high-level video understanding and media interpretation.

Action Detection Temporal Localization +1

iDARTS: Improving DARTS by Node Normalization and Decorrelation Discretization

no code implementations25 Aug 2021 Huiqun Wang, Ruijie Yang, Di Huang, Yunhong Wang

Differentiable ARchiTecture Search (DARTS) uses a continuous relaxation of network representation and dramatically accelerates Neural Architecture Search (NAS) by almost thousands of times in GPU-day.

Neural Architecture Search

PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation

no code implementations ICCV 2021 Guangyuan Zhou, Huiqun Wang, Jiaxin Chen, Di Huang

This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way.

6D Pose Estimation

Image Inpainting via Conditional Texture and Structure Dual Generation

1 code implementation ICCV 2021 Xiefan Guo, Hongyu Yang, Di Huang

Deep generative approaches have recently made considerable progress in image inpainting by introducing structure priors.

Image Inpainting Texture Synthesis

Recurrent Graph Neural Networks for Rumor Detection in Online Forums

1 code implementation8 Aug 2021 Di Huang, Jacob Bartel, John Palowitch

The widespread adoption of online social networks in daily life has created a pressing need for effectively classifying user-generated content.

Double-Dot Network for Antipodal Grasp Detection

no code implementations3 Aug 2021 Yao Wang, Yangtao Zheng, Boyang Gao, Di Huang

This paper proposes a new deep learning approach to antipodal grasp detection, named Double-Dot Network (DD-Net).

object-detection Object Detection

Pixel Sampling for Style Preserving Face Pose Editing

no code implementations14 Jun 2021 Xiangnan Yin, Di Huang, Hongyu Yang, Zehua Fu, Yunhong Wang, Liming Chen

The existing auto-encoder based face pose editing methods primarily focus on modeling the identity preserving ability during pose synthesis, but are less able to preserve the image style properly, which refers to the color, brightness, saturation, etc.

Facial Inpainting

Student-Teacher Feature Pyramid Matching for Anomaly Detection

6 code implementations7 Mar 2021 Guodong Wang, Shumin Han, Errui Ding, Di Huang

Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies.

Ranked #20 on Anomaly Detection on MVTec AD (using extra training data)

Image Classification Unsupervised Anomaly Detection

MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images

no code implementations24 Dec 2020 Ran Qin, Qingjie Liu, Guangshuai Gao, Di Huang, Yunhong Wang

Objects in aerial images usually have arbitrary orientations and are densely located over the ground, making them extremely challenge to be detected.

object-detection Object Detection In Aerial Images +1

PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection

no code implementations18 Dec 2020 Yanan Zhang, Di Huang, Yunhong Wang

LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects.

3D Object Detection Autonomous Driving +2

Multi-Scale Positive Sample Refinement for Few-Shot Object Detection

3 code implementations ECCV 2020 Jiaxi Wu, Songtao Liu, Di Huang, Yunhong Wang

Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited.

Few-Shot Object Detection object-detection

Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation

no code implementations CVPR 2020 Yangtao Zheng, Di Huang, Songtao Liu, Yunhong Wang

Thanks to this coarse-to-fine feature adaptation, domain knowledge in foreground regions can be effectively transferred.

object-detection Object Detection

DWM: A Decomposable Winograd Method for Convolution Acceleration

no code implementations3 Feb 2020 Di Huang, Xishan Zhang, Rui Zhang, Tian Zhi, Deyuan He, Jiaming Guo, Chang Liu, Qi Guo, Zidong Du, Shaoli Liu, Tianshi Chen, Yunji Chen

In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd's minimal filtering algorithm to a wide and general convolutions.

A Feasible Framework for Arbitrary-Shaped Scene Text Recognition

2 code implementations10 Dec 2019 Jinjin Zhang, Wei Wang, Di Huang, Qingjie Liu, Yunhong Wang

Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision.

Instance Segmentation Language Modelling +3

Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism

no code implementations26 Nov 2019 Mingda Wu, Di Huang, Yuanfang Guo, Yunhong Wang

Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but not well handled.

Learning Spatial Fusion for Single-Shot Object Detection

1 code implementation21 Nov 2019 Songtao Liu, Di Huang, Yunhong Wang

Pyramidal feature representation is the common practice to address the challenge of scale variation in object detection.

object-detection Object Detection

Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels

1 code implementation ICML 2020 Lu Jiang, Di Huang, Mason Liu, Weilong Yang

Due to the lack of suitable datasets, previous research has only examined deep learning on controlled synthetic label noise, and real-world label noise has never been studied in a controlled setting.

Image Classification

Synthetic vs Real: Deep Learning on Controlled Noise

no code implementations25 Sep 2019 Lu Jiang, Di Huang, Weilong Yang

Performing controlled experiments on noisy data is essential in thoroughly understanding deep learning across a spectrum of noise levels.

ArduCode: Predictive Framework for Automation Engineering

no code implementations6 Sep 2019 Arquimedes Canedo, Palash Goyal, Di Huang, Amit Pandey, Gustavo Quiros

We show that machine learning can be leveraged to assist the automation engineer in classifying automation, finding similar code snippets, and reasoning about the hardware selection of sensors and actuators.

Decision Making

Graph Representation Ensemble Learning

1 code implementation6 Sep 2019 Palash Goyal, Di Huang, Sujit Rokka Chhetri, Arquimedes Canedo, Jaya Shree, Evan Patterson

In this work, we introduce the problem of graph representation ensemble learning and provide a first of its kind framework to aggregate multiple graph embedding methods efficiently.

Ensemble Learning Graph Embedding +1

Benchmarks for Graph Embedding Evaluation

1 code implementation19 Aug 2019 Palash Goyal, Di Huang, Ankita Goswami, Sujit Rokka Chhetri, Arquimedes Canedo, Emilio Ferrara

We use the comparisons on our 100 benchmark graphs to define GFS-score, that can be applied to any embedding method to quantify its performance.

Graph Embedding Link Prediction

CompactNet: Platform-Aware Automatic Optimization for Convolutional Neural Networks

1 code implementation28 May 2019 Weicheng Li, Rui Wang, Zhongzhi Luan, Di Huang, Zidong Du, Yunji Chen, Depei Qian

Convolutional Neural Network (CNN) based Deep Learning (DL) has achieved great progress in many real-life applications.

Image Classification

Learning Continuous Face Age Progression: A Pyramid of GANs

no code implementations10 Jan 2019 Hongyu Yang, Di Huang, Yunhong Wang, Anil K. Jain

The two underlying requirements of face age progression, i. e. aging accuracy and identity permanence, are not well studied in the literature.

Face Recognition

Learning Face Age Progression: A Pyramid Architecture of GANs

1 code implementation CVPR 2018 Hongyu Yang, Di Huang, Yunhong Wang, Anil K. Jain

The two underlying requirements of face age progression, i. e. aging accuracy and identity permanence, are not well studied in the literature.

Feature Map Pooling for Cross-View Gait Recognition Based on Silhouette Sequence Images

no code implementations26 Nov 2017 Qiang Chen, Yunhong Wang, Zheng Liu, Qingjie Liu, Di Huang

In this paper, we develop a novel convolutional neural network based approach to extract and aggregate useful information from gait silhouette sequence images instead of simply representing the gait process by averaging silhouette images.

Gait Recognition

Receptive Field Block Net for Accurate and Fast Object Detection

7 code implementations ECCV 2018 Songtao Liu, Di Huang, Yunhong Wang

Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs.

object-detection Real-Time Object Detection

Defect detection for patterned fabric images based on GHOG and low-rank decomposition

no code implementations18 Feb 2017 Chunlei Li, Guangshuai Gao, Zhoufeng Liu, Di Huang, Sheng Liu, Miao Yu

In order to accurately detect defects in patterned fabric images, a novel detection algorithm based on Gabor-HOG (GHOG) and low-rank decomposition is proposed in this paper.

Defect Detection

Face Aging Effect Simulation using Hidden Factor Analysis Joint Sparse Representation

no code implementations4 Nov 2015 Hongyu Yang, Di Huang, Yunhong Wang, Heng Wang, Yuanyan Tang

Face aging simulation has received rising investigations nowadays, whereas it still remains a challenge to generate convincing and natural age-progressed face images.

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