Search Results for author: Di Huang

Found 70 papers, 26 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

DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration

1 code implementation ICCV 2023 Nan Zhou, Jiaxin Chen, Di Huang

Furthermore, to alleviate the interference by semantic drift, we develop the semantic calibration (SC) module to align the global shape and class centers of the pretrained and downstream feature distributions.

General Knowledge Image Classification

MotionGPT: Finetuned LLMs are General-Purpose Motion Generators

no code implementations19 Jun 2023 Yaqi Zhang, Di Huang, Bin Liu, Shixiang Tang, Yan Lu, Lu Chen, Lei Bai, Qi Chu, Nenghai Yu, Wanli Ouyang

Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans.

Flew Over Learning Trap: Learn Unlearnable Samples by Progressive Staged Training

1 code implementation3 Jun 2023 Pucheng Dang, Xing Hu, Kaidi Xu, Jinhao Duan, Di Huang, Husheng Han, Rui Zhang, Zidong Du, Qi Guo, Yunji Chen

Unlearning techniques are proposed to prevent third parties from exploiting unauthorized data, which generate unlearnable samples by adding imperceptible perturbations to data for public publishing.

ANPL: Compiling Natural Programs with Interactive Decomposition

no code implementations29 May 2023 Di Huang, Ziyuan Nan, Xing Hu, Pengwei Jin, Shaohui Peng, Yuanbo Wen, Rui Zhang, Zidong Du, Qi Guo, Yewen Pu, Yunji Chen

Given an ANPL program, the ANPL compiler generates a cohesive Python program that implements the functionalities in hole, while respecting the dataflows specified in sketch.

FR-Net:A Light-weight FFT Residual Net For Gaze Estimation

no code implementations4 May 2023 Tao Xu, Bo Wu, Ruilong Fan, Yun Zhou, Di Huang

Furthermore, our method outperforms existing lightweight methods in terms of accuracy and efficiency for the gaze estimation task.

Gaze Estimation

Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images

1 code implementation25 Apr 2023 Zeyu Lu, Di Huang, Lei Bai, Jingjing Qu, Chengyue Wu, Xihui Liu, Wanli Ouyang

Along with this, we conduct the model capability of AI-Generated images detection evaluation MPBench and the top-performing model from MPBench achieves a 13% failure rate under the same setting used in the human evaluation.

Benchmarking Fake Image Detection

Align-DETR: Improving DETR with Simple IoU-aware BCE loss

1 code implementation15 Apr 2023 Zhi Cai, Songtao Liu, Guodong Wang, Zheng Ge, Xiangyu Zhang, Di Huang

We propose a metric, recall of best-regressed samples, to quantitively evaluate the misalignment problem.

object-detection Object Detection

Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images

1 code implementation CVPR 2023 Bowei Du, Yecheng Huang, Jiaxin Chen, Di Huang

Object detection on drone images with low-latency is an important but challenging task on the resource-constrained unmanned aerial vehicle (UAV) platform.

object-detection Object Detection

NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images

1 code implementation CVPR 2023 Mingwu Zheng, Haiyu Zhang, Hongyu Yang, Di Huang

Realistic face rendering from multi-view images is beneficial to various computer vision and graphics applications.

Neural Rendering

OcTr: Octree-based Transformer for 3D Object Detection

no code implementations CVPR 2023 Chao Zhou, Yanan Zhang, Jiaxin Chen, Di Huang

A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects.

3D Object Detection object-detection

Denoising Diffusion Autoencoders are Unified Self-supervised Learners

1 code implementation ICCV 2023 Weilai Xiang, Hongyu Yang, Di Huang, Yunhong Wang

Inspired by recent advances in diffusion models, which are reminiscent of denoising autoencoders, we investigate whether they can acquire discriminative representations for classification via generative pre-training.

Contrastive Learning Denoising +3

RGB-D Grasp Detection via Depth Guided Learning with Cross-modal Attention

no code implementations28 Feb 2023 Ran Qin, Haoxiang Ma, Boyang Gao, Di Huang

Planar grasp detection is one of the most fundamental tasks to robotic manipulation, and the recent progress of consumer-grade RGB-D sensors enables delivering more comprehensive features from both the texture and shape modalities.

Online Symbolic Regression with Informative Query

no code implementations21 Feb 2023 Pengwei Jin, Di Huang, Rui Zhang, Xing Hu, Ziyuan Nan, Zidong Du, Qi Guo, Yunji Chen

Symbolic regression, the task of extracting mathematical expressions from the observed data $\{ \vx_i, y_i \}$, plays a crucial role in scientific discovery.

regression Symbolic Regression

Ponder: Point Cloud Pre-training via Neural Rendering

no code implementations ICCV 2023 Di Huang, Sida Peng, Tong He, Xiaowei Zhou, Wanli Ouyang

We propose a novel approach to self-supervised learning of point cloud representations by differentiable neural rendering.

3D Reconstruction Image Generation +2

Towards Scale Balanced 6-DoF Grasp Detection in Cluttered Scenes

1 code implementation10 Dec 2022 Haoxiang Ma, Di Huang

Moreover, a Scale Balanced Learning (SBL) loss and an Object Balanced Sampling (OBS) strategy are designed, where SBL enlarges the gradients of the samples whose scales are in low frequency by apriori weights while OBS captures more points on small-scale objects with the help of an auxiliary segmentation network.

Data Augmentation

Reconstructing Hand-Held Objects from Monocular Video

no code implementations30 Nov 2022 Di Huang, Xiaopeng Ji, Xingyi He, Jiaming Sun, Tong He, Qing Shuai, Wanli Ouyang, Xiaowei Zhou

The key idea is that the hand motion naturally provides multiple views of the object and the motion can be reliably estimated by a hand pose tracker.

Hand Pose Estimation

Racial Disparities in Pulse Oximetry Cannot Be Fixed With Race-Based Correction

no code implementations10 Oct 2022 Neal Patwari, Di Huang, Kiki Bonetta-Misteli

Studies have shown pulse oximeter measurements of blood oxygenation have statistical bias that is a function of race, which results in higher rates of occult hypoxemia, i. e., missed detection of dangerously low oxygenation, in patients of color.

STS: Surround-view Temporal Stereo for Multi-view 3D Detection

no code implementations22 Aug 2022 Zengran Wang, Chen Min, Zheng Ge, Yinhao Li, Zeming Li, Hongyu Yang, Di Huang

Instead of using a sole monocular depth method, in this work, we propose a novel Surround-view Temporal Stereo (STS) technique that leverages the geometry correspondence between frames across time to facilitate accurate depth learning.

3D Object Detection Depth Estimation +4

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 +2

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.

Vocal Bursts Intensity Prediction

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

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

1 code implementation21 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

3 code implementations 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

7 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.

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 +2

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

4 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 +4

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.

Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels

2 code implementations 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

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

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.

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 +2

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.

BIG-bench Machine Learning Decision Making

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.

Benchmarking Graph Embedding +1

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 MORPH

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.