Search Results for author: Xiaoming Liu

Found 83 papers, 41 papers with code

WAE_RN: Integrating Wasserstein Autoencoder and Relational Network for Text Sequence

no code implementations CCL 2020 Xinxin Zhang, Xiaoming Liu, Guan Yang, Fangfang Li

In spite of the success of pre-trained language model in many NLP tasks, the learned text representation only contains the correlation among the words in the sentence itself and ignores the implicit relationship between arbitrary tokens in the sequence.

Language Modelling

AdaFace: Quality Adaptive Margin for Face Recognition

1 code implementation3 Apr 2022 Minchul Kim, Anil K. Jain, Xiaoming Liu

In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality.

Face Recognition Face Recognition (Closed-Set) +4

Face Relighting with Geometrically Consistent Shadows

1 code implementation30 Mar 2022 Andrew Hou, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu

Most face relighting methods are able to handle diffuse shadows, but struggle to handle hard shadows, such as those cast by the nose.

Proactive Image Manipulation Detection

1 code implementation29 Mar 2022 Vishal Asnani, Xi Yin, Tal Hassner, Sijia Liu, Xiaoming Liu

That is, a template protected real image, and its manipulated version, is better discriminated compared to the original real image vs. its manipulated one.

Image Manipulation Image Manipulation Detection

Reverse Engineering of Imperceptible Adversarial Image Perturbations

1 code implementation ICLR 2022 Yifan Gong, Yuguang Yao, Yize Li, Yimeng Zhang, Xiaoming Liu, Xue Lin, Sijia Liu

However, carefully crafted, tiny adversarial perturbations are difficult to recover by optimizing a unilateral RED objective.

Data Augmentation Image Denoising

The State of Aerial Surveillance: A Survey

no code implementations9 Jan 2022 Kien Nguyen, Clinton Fookes, Sridha Sridharan, YingLi Tian, Feng Liu, Xiaoming Liu, Arun Ross

The rapid emergence of airborne platforms and imaging sensors are enabling new forms of aerial surveillance due to their unprecedented advantages in scale, mobility, deployment and covert observation capabilities.

Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image

no code implementations NeurIPS 2021 Feng Liu, Xiaoming Liu

With complementary supervision from both 3D detection and reconstruction, one enables the 3D voxel features to be geometry and context preserving, benefiting both tasks. The effectiveness of our approach is demonstrated through 3D detection and reconstruction in single object and multiple object scenarios.

Keypoint Detection

Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images

1 code implementation15 Jun 2021 Vishal Asnani, Xi Yin, Tal Hassner, Xiaoming Liu

To tackle this problem, we propose a framework with two components: a Fingerprint Estimation Network (FEN), which estimates a GM fingerprint from a generated image by training with four constraints to encourage the fingerprint to have desired properties, and a Parsing Network (PN), which predicts network architecture and loss functions from the estimated fingerprints.

DeepFake Detection Face Swapping

Riggable 3D Face Reconstruction via In-Network Optimization

1 code implementation CVPR 2021 Ziqian Bai, Zhaopeng Cui, Xiaoming Liu, Ping Tan

This paper presents a method for riggable 3D face reconstruction from monocular images, which jointly estimates a personalized face rig and per-image parameters including expressions, poses, and illuminations.

3D Face Reconstruction

Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries

1 code implementation CVPR 2021 Saif Imran, Xiaoming Liu, Daniel Morris

Key to our method is the use of an asymmetric loss function that operates on a novel twin-surface representation.

Depth Completion

Unified Detection of Digital and Physical Face Attacks

no code implementations5 Apr 2021 Debayan Deb, Xiaoming Liu, Anil K. Jain

Proposed UniFAD outperforms prevailing defense methods and their fusion with an overall TDR = 94. 73% @ 0. 2% FDR on a large fake face dataset consisting of 341K bona fide images and 448K attack images of 25 types across all 3 categories.

Multi-Task Learning

Towards High Fidelity Face Relighting with Realistic Shadows

1 code implementation CVPR 2021 Andrew Hou, Ze Zhang, Michel Sarkis, Ning Bi, Yiying Tong, Xiaoming Liu

Furthermore, we introduce a method to use the shadow mask to estimate the ambient light intensity in an image, and are thus able to leverage multiple datasets during training with different global lighting intensities.

Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction

1 code implementation CVPR 2021 Feng Liu, Luan Tran, Xiaoming Liu

That is, for a 2D image of a generic object, we decompose it into latent representations of category, shape and albedo, lighting and camera projection matrix, decode the representations to segmented 3D shape and albedo respectively, and fuse these components to render an image well approximating the input image.

3D Reconstruction

GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection

1 code implementation CVPR 2021 Abhinav Kumar, Garrick Brazil, Xiaoming Liu

In this paper, we present and integrate GrooMeD-NMS -- a novel Grouped Mathematically Differentiable NMS for monocular 3D object detection, such that the network is trained end-to-end with a loss on the boxes after NMS.

2D object detection Monocular 3D Object Detection

PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization

no code implementations19 Mar 2021 Xiaohong Liu, Yaojie Liu, Jun Chen, Xiaoming Liu

To defend against manipulation of image content, such as splicing, copy-move, and removal, we develop a Progressive Spatio-Channel Correlation Network (PSCC-Net) to detect and localize image manipulations.

Image Manipulation Image Manipulation Detection

Infer-AVAE: An Attribute Inference Model Based on Adversarial Variational Autoencoder

no code implementations30 Dec 2020 Yadong Zhou, Zhihao Ding, Xiaoming Liu, Chao Shen, Lingling Tong, Xiaohong Guan

While using the trending graph neural networks (GNNs) as encoder has the problem that GNNs aggregate redundant information from neighborhood and generate indistinguishable user representations, which is known as over-smoothing.

Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation

no code implementations16 Dec 2020 Mehdi Bahri, Eimear O' Sullivan, Shunwang Gong, Feng Liu, Xiaoming Liu, Michael M. Bronstein, Stefanos Zafeiriou

Compared to the previous state-of-the-art learning algorithms for non-rigid registration of face scans, SMF only requires the raw data to be rigidly aligned (with scaling) with a pre-defined face template.

Translation

Physics-Guided Spoof Trace Disentanglement for Generic Face Anti-Spoofing

no code implementations9 Dec 2020 Yaojie Liu, Xiaoming Liu

Additive process describes spoofing as spoof material introducing extra patterns (e. g., moire pattern), where the live counterpart can be recovered by removing those patterns.

Disentanglement Face Anti-Spoofing

Unify Local and Global Information for Top-$N$ Recommendation

no code implementations3 Dec 2020 Xiaoming Liu, Shaocong Wu, Zhaohan Zhang, Chao Shen

To tackle this research gap, we propose a novel duet representation learning framework named \sysname to fuse local information (user-item interaction data) and global information (external knowledge graph) for the top-$N$ recommendation, which is composed of two separate sub-models.

Knowledge Graph Embedding Recommendation Systems

FaceGuard: A Self-Supervised Defense Against Adversarial Face Images

no code implementations28 Nov 2020 Debayan Deb, Xiaoming Liu, Anil K. Jain

During training, FaceGuard automatically synthesizes challenging and diverse adversarial attacks, enabling a classifier to learn to distinguish them from real faces and a purifier attempts to remove the adversarial perturbations in the image space.

Adversarial Attack Adversarial Defense +1

Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence

1 code implementation NeurIPS 2020 Feng Liu, Xiaoming Liu

The goal of this paper is to learn dense 3D shape correspondence for topology-varying objects in an unsupervised manner.

Semantic correspondence

DeepApple: Deep Learning-based Apple Detection using a Suppression Mask R-CNN

no code implementations19 Oct 2020 Pengyu Chu, Zhaojian Li, Kyle Lammers, Renfu Lu, Xiaoming Liu

Robotic apple harvesting has received much research attention in the past few years due to growing shortage and rising cost in labor.

Frame

Kinematic 3D Object Detection in Monocular Video

2 code implementations ECCV 2020 Garrick Brazil, Gerard Pons-Moll, Xiaoming Liu, Bernt Schiele

In this work, we propose a novel method for monocular video-based 3D object detection which carefully leverages kinematic motion to improve precision of 3D localization.

Ranked #9 on Monocular 3D Object Detection on KITTI Cars Moderate (using extra training data)

Monocular 3D Object Detection Vehicle Pose Estimation

On Disentangling Spoof Trace for Generic Face Anti-Spoofing

1 code implementation ECCV 2020 Yaojie Liu, Joel Stehouwer, Xiaoming Liu

Prior studies show that the key to face anti-spoofing lies in the subtle image pattern, termed "spoof trace", e. g., color distortion, 3D mask edge, Moire pattern, and many others.

Face Anti-Spoofing

Mitigating Face Recognition Bias via Group Adaptive Classifier

no code implementations CVPR 2021 Sixue Gong, Xiaoming Liu, Anil K. Jain

Our proposed group adaptive classifier mitigates bias by using adaptive convolution kernels and attention mechanisms on faces based on their demographic attributes.

Face Recognition

CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition

1 code implementation CVPR 2020 Yuge Huang, YuHan Wang, Ying Tai, Xiaoming Liu, Pengcheng Shen, Shaoxin Li, Jilin Li, Feiyue Huang

As an emerging topic in face recognition, designing margin-based loss functions can increase the feature margin between different classes for enhanced discriminability.

Ranked #10 on Face Verification on IJB-C (TAR @ FAR=1e-4 metric)

Face Recognition Face Verification

The Edge of Depth: Explicit Constraints between Segmentation and Depth

no code implementations CVPR 2020 Shengjie Zhu, Garrick Brazil, Xiaoming Liu

In this work we study the mutual benefits of two common computer vision tasks, self-supervised depth estimation and semantic segmentation from images.

Monocular Depth Estimation Semantic Segmentation

Noise Modeling, Synthesis and Classification for Generic Object Anti-Spoofing

no code implementations CVPR 2020 Joel Stehouwer, Amin Jourabloo, Yaojie Liu, Xiaoming Liu

Using printed photograph and replaying videos of biometric modalities, such as iris, fingerprint and face, are common attacks to fool the recognition systems for granting access as the genuine user.

Classification General Classification

Camera Trace Erasing

1 code implementation CVPR 2020 Chang Chen, Zhiwei Xiong, Xiaoming Liu, Feng Wu

To reconcile these two demands, we propose Siamese Trace Erasing (SiamTE), in which a novel hybrid loss is designed on the basis of Siamese architecture for network training.

Improving Face Recognition from Hard Samples via Distribution Distillation Loss

2 code implementations ECCV 2020 Yuge Huang, Pengcheng Shen, Ying Tai, Shaoxin Li, Xiaoming Liu, Jilin Li, Feiyue Huang, Rongrong Ji

To improve the performance on those hard samples for general tasks, we propose a novel Distribution Distillation Loss to narrow the performance gap between easy and hard samples, which is a simple, effective and generic for various types of facial variations.

Face Recognition

FAN: Feature Adaptation Network for Surveillance Face Recognition and Normalization

no code implementations26 Nov 2019 Xi Yin, Ying Tai, Yuge Huang, Xiaoming Liu

FAN can leverage both paired and unpaired data as we disentangle the features into identity and non-identity components and adapt the distribution of the identity features, which breaks the limit of current face super-resolution methods.

Face Recognition Super-Resolution

Jointly De-biasing Face Recognition and Demographic Attribute Estimation

1 code implementation ECCV 2020 Sixue Gong, Xiaoming Liu, Anil K. Jain

We address the problem of bias in automated face recognition and demographic attribute estimation algorithms, where errors are lower on certain cohorts belonging to specific demographic groups.

Face Recognition

On the Detection of Digital Face Manipulation

1 code implementation CVPR 2020 Hao Dang, Feng Liu, Joel Stehouwer, Xiaoming Liu, Anil Jain

Instead of simply using multi-task learning to simultaneously detect manipulated images and predict the manipulated mask (regions), we propose to utilize an attention mechanism to process and improve the feature maps for the classification task.

Face Detection Face Generation +2

On Learning Disentangled Representations for Gait Recognition

no code implementations5 Sep 2019 Ziyuan Zhang, Luan Tran, Feng Liu, Xiaoming Liu

The LSTM integrates pose features over time as a dynamic gait feature while canonical features are averaged as a static gait feature.

Disentanglement Face Recognition +1

Towards High-fidelity Nonlinear 3D Face Morphable Model

no code implementations CVPR 2019 Luan Tran, Feng Liu, Xiaoming Liu

By improving the nonlinear 3D morphable model in both learning objective and network architecture, we present a model which is superior in capturing higher level of details than the linear or its precedent nonlinear counterparts.

3D Face Reconstruction

Depth Coefficients for Depth Completion

no code implementations CVPR 2019 Saif Imran, Yunfei Long, Xiaoming Liu, Daniel Morris

We also show that the standard Mean Squared Error (MSE) loss function can promote depth mixing, and thus propose instead to use cross-entropy loss for DC.

Depth Completion Object Detection

3D Face Modeling From Diverse Raw Scan Data

1 code implementation ICCV 2019 Feng Liu, Luan Tran, Xiaoming Liu

Traditional 3D face models learn a latent representation of faces using linear subspaces from limited scans of a single database.

3D FACE MODELING 3D Face Reconstruction +1

Pedestrian Detection with Autoregressive Network Phases

1 code implementation CVPR 2019 Garrick Brazil, Xiaoming Liu

We present an autoregressive pedestrian detection framework with cascaded phases designed to progressively improve precision.

Pedestrian Detection Region Proposal

Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos

1 code implementation1 Nov 2018 Ying Tai, Yicong Liang, Xiaoming Liu, Lei Duan, Jilin Li, Chengjie Wang, Feiyue Huang, Yu Chen

In recent years, heatmap regression based models have shown their effectiveness in face alignment and pose estimation.

Face Alignment Pose Estimation +1

Recurrent Flow-Guided Semantic Forecasting

1 code implementation21 Sep 2018 Adam M. Terwilliger, Garrick Brazil, Xiaoming Liu

Understanding the world around us and making decisions about the future is a critical component to human intelligence.

Autonomous Vehicles Frame +1

On Learning 3D Face Morphable Model from In-the-wild Images

1 code implementation28 Aug 2018 Luan Tran, Xiaoming Liu

To address these problems, this paper proposes an innovative framework to learn a nonlinear 3DMM model from a large set of in-the-wild face images, without collecting 3D face scans.

3D Reconstruction Face Alignment +1

Face De-Spoofing: Anti-Spoofing via Noise Modeling

1 code implementation ECCV 2018 Amin Jourabloo, Yaojie Liu, Xiaoming Liu

In this work, motivated by the noise modeling and denoising algorithms, we identify a new problem of face de-spoofing, for the purpose of anti-spoofing: inversely decomposing a spoof face into a spoof noise and a live face, and then utilizing the spoof noise for classification.

Denoising Face Anti-Spoofing

Nonlinear 3D Face Morphable Model

1 code implementation CVPR 2018 Luan Tran, Xiaoming Liu

As a classic statistical model of 3D facial shape and texture, 3D Morphable Model (3DMM) is widely used in facial analysis, e. g., model fitting, image synthesis.

3D Reconstruction Face Alignment +1

Face Alignment in Full Pose Range: A 3D Total Solution

1 code implementation2 Apr 2018 Xiangyu Zhu, Xiaoming Liu, Zhen Lei, Stan Z. Li

In this paper, we propose to tackle these three challenges in an new alignment framework termed 3D Dense Face Alignment (3DDFA), in which a dense 3D Morphable Model (3DMM) is fitted to the image via Cascaded Convolutional Neural Networks.

3D Pose Estimation Depth Image Estimation +3

Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition

no code implementations CVPR 2018 Feng Liu, Ronghang Zhu, Dan Zeng, Qijun Zhao, Xiaoming Liu

This paper proposes an encoder-decoder network to disentangle shape features during 3D face reconstruction from single 2D images, such that the tasks of reconstructing accurate 3D face shapes and learning discriminative shape features for face recognition can be accomplished simultaneously.

3D Face Reconstruction Face Identification +1

Feature Transfer Learning for Deep Face Recognition with Under-Represented Data

no code implementations23 Mar 2018 Xi Yin, Xiang Yu, Kihyuk Sohn, Xiaoming Liu, Manmohan Chandraker

In this paper, we propose a center-based feature transfer framework to augment the feature space of under-represented subjects from the regular subjects that have sufficiently diverse samples.

Disentanglement Face Recognition +1

Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild

1 code implementation CVPR 2019 Luan Tran, Kihyuk Sohn, Xiang Yu, Xiaoming Liu, Manmohan Chandraker

Recent developments in deep domain adaptation have allowed knowledge transfer from a labeled source domain to an unlabeled target domain at the level of intermediate features or input pixels.

Domain Adaptation Image Generation +1

FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors

3 code implementations CVPR 2018 Yu Chen, Ying Tai, Xiaoming Liu, Chunhua Shen, Jian Yang

We present a novel deep end-to-end trainable Face Super-Resolution Network (FSRNet), which makes full use of the geometry prior, i. e., facial landmark heatmaps and parsing maps, to super-resolve very low-resolution (LR) face images without well-aligned requirement.

Face Alignment Super-Resolution

Do Convolutional Neural Networks Learn Class Hierarchy?

no code implementations17 Oct 2017 Bilal Alsallakh, Amin Jourabloo, Mao Ye, Xiaoming Liu, Liu Ren

We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data.

Image Classification

Monocular Video-Based Trailer Coupler Detection Using Multiplexer Convolutional Neural Network

no code implementations ICCV 2017 Yousef Atoum, Joseph Roth, Michael Bliss, Wende Zhang, Xiaoming Liu

This paper presents an automated monocular-camera-based computer vision system for autonomous self-backing-up a vehicle towards a trailer, by continuously estimating the 3D trailer coupler position and feeding it to the vehicle control system, until the alignment of the tow hitch with the trailers coupler.

Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition

no code implementations9 Aug 2017 Feng Liu, Qijun Zhao, Xiaoming Liu, Dan Zeng

Extensive experiments show that the proposed method can achieve the state-of-the-art accuracy in both face alignment and 3D face reconstruction, and benefit face recognition owing to its reconstructed PEN 3D face.

3D Face Reconstruction Face Alignment +1

Image Super-Resolution via Deep Recursive Residual Network

1 code implementation CVPR 2017 Ying Tai, Jian Yang, Xiaoming Liu

Specifically, residual learning is adopted, both in global and local manners, to mitigate the difficulty of training very deep networks; recursive learning is used to control the model parameters while increasing the depth.

Image Super-Resolution

Missing Modalities Imputation via Cascaded Residual Autoencoder

no code implementations CVPR 2017 Luan Tran, Xiaoming Liu, Jiayu Zhou, Rong Jin

To leverage the valuable information in the corrupted data, we propose to impute the missing data by leveraging the relatedness among different modalities.

Imputation Object Recognition

Illuminating Pedestrians via Simultaneous Detection & Segmentation

2 code implementations ICCV 2017 Garrick Brazil, Xi Yin, Xiaoming Liu

When placed properly, the additional supervision helps guide features in shared layers to become more sophisticated and helpful for the downstream pedestrian detector.

Autonomous Driving Pedestrian Detection +1

Representation Learning by Rotating Your Faces

no code implementations31 May 2017 Luan Tran, Xi Yin, Xiaoming Liu

First, the encoder-decoder structure of the generator enables DR-GAN to learn a representation that is both generative and discriminative, which can be used for face image synthesis and pose-invariant face recognition.

Face Recognition Image Generation +3

Towards Large-Pose Face Frontalization in the Wild

no code implementations ICCV 2017 Xi Yin, Xiang Yu, Kihyuk Sohn, Xiaoming Liu, Manmohan Chandraker

Despite recent advances in face recognition using deep learning, severe accuracy drops are observed for large pose variations in unconstrained environments.

3D Reconstruction Face Recognition

Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition

1 code implementation15 Feb 2017 Xi Yin, Xiaoming Liu

First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity classification is the main task and pose, illumination, and expression estimations are the side tasks.

Face Recognition Multi-Task Learning +1

Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting

no code implementations CVPR 2016 Amin Jourabloo, Xiaoming Liu

Large-pose face alignment is a very challenging problem in computer vision, which is used as a prerequisite for many important vision tasks, e. g, face recognition and 3D face reconstruction.

3D Face Reconstruction Face Alignment +1

Adaptive 3D Face Reconstruction From Unconstrained Photo Collections

no code implementations CVPR 2016 Joseph Roth, Yiying Tong, Xiaoming Liu

Given a collection of "in-the-wild" face images captured under a variety of unknown pose, expression, and illumination conditions, this paper presents a method for reconstructing a 3D face surface model of an individual along with albedo information.

3D Face Reconstruction

Temporally Robust Global Motion Compensation by Keypoint-based Congealing

no code implementations12 Mar 2016 S. Morteza Safdarnejad, Yousef Atoum, Xiaoming Liu

Global motion compensation (GMC) removes the impact of camera motion and creates a video in which the background appears static over the progression of time.

Activity Recognition Frame +3

Face Alignment Across Large Poses: A 3D Solution

no code implementations CVPR 2016 Xiangyu Zhu, Zhen Lei, Xiaoming Liu, Hailin Shi, Stan Z. Li

Face alignment, which fits a face model to an image and extracts the semantic meanings of facial pixels, has been an important topic in CV community.

3D Face Reconstruction Face Alignment +2

Pose-Invariant 3D Face Alignment

no code implementations ICCV 2015 Amin Jourabloo, Xiaoming Liu

Face alignment aims to estimate the locations of a set of landmarks for a given image.

3D Face Alignment Face Alignment

Unconstrained 3D Face Reconstruction

no code implementations CVPR 2015 Joseph Roth, Yiying Tong, Xiaoming Liu

Second, by leveraging emerging face alignment techniques and our novel normal field-based Laplace editing, a combination of landmark constraints and photometric stereo-based normals drives our surface reconstruction.

3D Face Reconstruction Face Alignment +1

Joint Multi-Leaf Segmentation, Alignment and Tracking from Fluorescence Plant Videos

1 code implementation2 May 2015 Xi Yin, Xiaoming Liu, Jin Chen, David M. Kramer

First, leaf segmentation and alignment are applied on the last frame of a plant video to find a number of well-aligned leaf candidates.

Frame

SLPA: Uncovering Overlapping Communities in Social Networks via A Speaker-listener Interaction Dynamic Process

1 code implementation26 Sep 2011 Jierui Xie, Boleslaw K. Szymanski, Xiaoming Liu

Overlap is one of the characteristics of social networks, in which a person may belong to more than one social group.

Social and Information Networks Data Structures and Algorithms Physics and Society

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