Search Results for author: Haibin Ling

Found 132 papers, 64 papers with code

Multi-target Tracking by Rank-1 Tensor Approximation

no code implementations CVPR 2013 Xinchu Shi, Haibin Ling, Junling Xing, Weiming Hu

In this paper we formulate multi-target tracking (MTT) as a rank-1 tensor approximation problem and propose an 1 norm tensor power iteration solution.

Multi-target Tracking with Motion Context in Tensor Power Iteration

no code implementations CVPR 2014 Xinchu Shi, Haibin Ling, Weiming Hu, Chunfeng Yuan, Junliang Xing

In this paper, we model interactions between neighbor targets by pair-wise motion context, and further encode such context into the global association optimization.

Curvilinear Structure Tracking by Low Rank Tensor Approximation with Model Propagation

no code implementations CVPR 2014 Erkang Cheng, Yu Pang, Ying Zhu, Jingyi Yu, Haibin Ling

Robust tracking of deformable object like catheter or vascular structures in X-ray images is an important technique used in image guided medical interventions for effective motion compensation and dynamic multi-modality image fusion.

Motion Compensation

Saliency Detection on Light Field

no code implementations CVPR 2014 Nianyi Li, Jinwei Ye, Yu Ji, Haibin Ling, Jingyi Yu

Existing saliency detection approaches use images as inputs and are sensitive to foreground/background similarities, complex background textures, and occlusions.

Saliency Detection

Adaptive Objectness for Object Tracking

no code implementations5 Jan 2015 Pengpeng Liang, Chunyuan Liao, Xue Mei, Haibin Ling

Noting that the way we integrate objectness in visual tracking is generic and straightforward, we expect even more improvement by using tracker-specific objectness.

Object Visual Object Tracking +1

Cross-Age Face Verification by Coordinating With Cross-Face Age Verification

no code implementations CVPR 2015 Liang Du, Haibin Ling

As shown in our experiments, the algorithm effectively balances feature sharing and feature exclusion between the two tasks; and, for face verification, the algorithm effectively removes distracting features used in age verification.

Face Verification feature selection +1

DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection

no code implementations19 Oct 2015 Xi Li, Liming Zhao, Lina Wei, Ming-Hsuan Yang, Fei Wu, Yueting Zhuang, Haibin Ling, Jingdong Wang

A key problem in salient object detection is how to effectively model the semantic properties of salient objects in a data-driven manner.

Image Segmentation Multi-Task Learning +6

3D Hand Pose Estimation Using Randomized Decision Forest With Segmentation Index Points

no code implementations ICCV 2015 Peiyi Li, Haibin Ling, Xi Li, Chunyuan Liao

In this paper, we propose a real-time 3D hand pose estimation algorithm using the randomized decision forest framework.

3D Hand Pose Estimation

A Comparative Study of Object Trackers for Infrared Flying Bird Tracking

no code implementations18 Jan 2016 Ying Huang, Hong Zheng, Haibin Ling, Erik Blasch, Hao Yang

Bird strikes present a huge risk for aircraft, especially since traditional airport bird surveillance is mainly dependent on inefficient human observation.

A Richly Annotated Dataset for Pedestrian Attribute Recognition

2 code implementations23 Mar 2016 Dangwei Li, Zhang Zhang, Xiaotang Chen, Haibin Ling, Kaiqi Huang

RAP has in total 41, 585 pedestrian samples, each of which is annotated with 72 attributes as well as viewpoints, occlusions, body parts information.

Attribute Pedestrian Attribute Recognition

Tensor Power Iteration for Multi-Graph Matching

no code implementations CVPR 2016 Xinchu Shi, Haibin Ling, Weiming Hu, Junliang Xing, Yanning Zhang

Due to its wide range of applications, matching between two graphs has been extensively studied and remains an active topic.

Graph Matching

Multi-level Contextual RNNs with Attention Model for Scene Labeling

no code implementations8 Jul 2016 Heng Fan, Xue Mei, Danil Prokhorov, Haibin Ling

Context in image is crucial for scene labeling while existing methods only exploit local context generated from a small surrounding area of an image patch or a pixel, by contrast long-range and global contextual information is ignored.

Scene Labeling

SANet: Structure-Aware Network for Visual Tracking

no code implementations21 Nov 2016 Heng Fan, Haibin Ling

Convolutional neural network (CNN) has drawn increasing interest in visual tracking owing to its powerfulness in feature extraction.

General Classification Object +1

LIME: Low-light Image Enhancement via Illumination Map Estimation

2 code implementations IEEE TIP 2016 Xiaojie Guo, Yu Li, Haibin Ling

When one captures images in low-light conditions, the images often suffer from low visibility.

 Ranked #1 on Low-Light Image Enhancement on 10 Monkey Species (using extra training data)

Low-Light Image Enhancement

Planar Object Tracking in the Wild: A Benchmark

no code implementations23 Mar 2017 Pengpeng Liang, Yifan Wu, Hu Lu, Liming Wang, Chunyuan Liao, Haibin Ling

In this paper, we present a carefully designed planar object tracking benchmark containing 210 videos of 30 planar objects sampled in the natural environment.

Homography Estimation Object +1

Transductive Zero-Shot Learning with a Self-training dictionary approach

no code implementations27 Mar 2017 Yunlong Yu, Zhong Ji, Xi Li, Jichang Guo, Zhongfei Zhang, Haibin Ling, Fei Wu

As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training data.

Transductive Learning Transfer Learning +1

Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking

no code implementations ICCV 2017 Heng Fan, Haibin Ling

In this paper we study the problem from a new perspective and present a novel parallel tracking and verifying (PTAV) framework, by taking advantage of the ubiquity of multi-thread techniques and borrowing from the success of parallel tracking and mapping in visual SLAM.

Visual Tracking

Saliency Pattern Detection by Ranking Structured Trees

1 code implementation ICCV 2017 Lei Zhu, Haibin Ling, Jin Wu, Huiping Deng, Jin Liu

We show that the linear combination of structured labels can well model the saliency distribution in local regions.

object-detection RGB Salient Object Detection +2

Dense Recurrent Neural Networks for Scene Labeling

no code implementations21 Jan 2018 Heng Fan, Haibin Ling

Recently recurrent neural networks (RNNs) have demonstrated the ability to improve scene labeling through capturing long-range dependencies among image units.

Scene Labeling

Parallel Tracking and Verifying

no code implementations30 Jan 2018 Heng Fan, Haibin Ling

Being intensively studied, visual object tracking has witnessed great advances in either speed (e. g., with correlation filters) or accuracy (e. g., with deep features).

Visual Object Tracking

Weighted Bilinear Coding over Salient Body Parts for Person Re-identification

no code implementations22 Mar 2018 Zhigang Chang, Qin Zhou, Heng Fan, Hang Su, Hua Yang, Shibao Zheng, Haibin Ling

Meanwhile, a weighting scheme is applied on the bilinear coding to adaptively adjust the weights of local features at different locations based on their importance in recognition, further improving the discriminability of feature aggregation.

Person Re-Identification

A Single-shot-per-pose Camera-Projector Calibration System For Imperfect Planar Targets

1 code implementation24 Mar 2018 Bingyao Huang, Samed Ozdemir, Ying Tang, Chunyuan Liao, Haibin Ling

Existing camera-projector calibration methods typically warp feature points from a camera image to a projector image using estimated homographies, and often suffer from errors in camera parameters and noise due to imperfect planarity of the calibration target.

Vision Meets Drones: A Challenge

no code implementations20 Apr 2018 Pengfei Zhu, Longyin Wen, Xiao Bian, Haibin Ling, QinGhua Hu

In this paper we present a large-scale visual object detection and tracking benchmark, named VisDrone2018, aiming at advancing visual understanding tasks on the drone platform.

Multi-Object Tracking Object +2

MTFH: A Matrix Tri-Factorization Hashing Framework for Efficient Cross-Modal Retrieval

1 code implementation4 May 2018 Xin Liu, Zhikai Hu, Haibin Ling, Yiu-ming Cheung

More specifically, MTFH exploits an efficient objective function to flexibly learn the modality-specific hash codes with different length settings, while synchronously learning two semantic correlation matrices to semantically correlate the different hash representations for heterogeneous data comparable.

Cross-Modal Retrieval Retrieval +1

Robust and Efficient Graph Correspondence Transfer for Person Re-identification

no code implementations15 May 2018 Qin Zhou, Heng Fan, Hua Yang, Hang Su, Shibao Zheng, Shuang Wu, Haibin Ling

To address this problem, in this paper, we present a robust and efficient graph correspondence transfer (REGCT) approach for explicit spatial alignment in Re-ID.

Graph Matching Person Re-Identification

Privacy-Protective-GAN for Face De-identification

no code implementations23 Jun 2018 Yifan Wu, Fan Yang, Haibin Ling

In this paper, we propose a new framework called Privacy-Protective-GAN (PP-GAN) that adapts GAN with novel verificator and regulator modules specially designed for the face de-identification problem to ensure generating de-identified output with retained structure similarity according to a single input.

De-identification Face Recognition

StructVIO : Visual-inertial Odometry with Structural Regularity of Man-made Environments

no code implementations16 Oct 2018 Danping Zou, Yuanxin Wu, Ling Pei, Haibin Ling, Wenxian Yu

Instead of using Manhattan world assumption, we use Atlanta world model to describe such regularity.

Robotics

Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection

no code implementations9 Nov 2018 Heng Fan, Peng Chu, Longin Jan Latecki, Haibin Ling

Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units.

Scene Labeling

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

12 code implementations12 Nov 2018 Qijie Zhao, Tao Sheng, Yongtao Wang, Zhi Tang, Ying Chen, Ling Cai, Haibin Ling

Finally, we gather up the decoder layers with equivalent scales (sizes) to develop a feature pyramid for object detection, in which every feature map consists of the layers (features) from multiple levels.

Object object-detection +1

Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection

1 code implementation18 Jan 2019 Fan Yang, Lei Zhang, Sijia Yu, Danil Prokhorov, Xue Mei, Haibin Ling

To demonstrate the superiority and generality of the proposed method, we evaluate the proposed method on five crack datasets and compare it with state-of-the-art crack detection, edge detection, semantic segmentation methods.

Edge Detection Semantic Segmentation

Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment

no code implementations21 Feb 2019 Peng Chu, Heng Fan, Chiu C. Tan, Haibin Ling

To address this issue, in this paper we propose an instance-aware tracker to integrate SOT techniques for MOT by encoding awareness both within and between target models.

Multi-Object Tracking Online Multi-Object Tracking

Object Discovery From a Single Unlabeled Image by Mining Frequent Itemset With Multi-scale Features

1 code implementation26 Feb 2019 Runsheng Zhang, Yaping Huang, Mengyang Pu, Jian Zhang, Qingji Guan, Qi Zou, Haibin Ling

To tackle this problem, we propose a simple but effective pattern mining-based method, called Object Location Mining (OLM), which exploits the advantages of data mining and feature representation of pre-trained convolutional neural networks (CNNs).

Object Discovery Unsupervised Saliency Detection

PFLD: A Practical Facial Landmark Detector

18 code implementations28 Feb 2019 Xiaojie Guo, Siyuan Li, Jinke Yu, Jiawan Zhang, Jiayi Ma, Lin Ma, Wei Liu, Haibin Ling

Being accurate, efficient, and compact is essential to a facial landmark detector for practical use.

Face Alignment Facial Landmark Detection

Generic Multiview Visual Tracking

no code implementations4 Apr 2019 Minye Wu, Haibin Ling, Ning Bi, Shenghua Gao, Hao Sheng, Jingyi Yu

A natural solution to these challenges is to use multiple cameras with multiview inputs, though existing systems are mostly limited to specific targets (e. g. human), static cameras, and/or camera calibration.

Camera Calibration Trajectory Prediction +1

End-to-end Projector Photometric Compensation

1 code implementation CVPR 2019 Bingyao Huang, Haibin Ling

Such benchmark is not previously available, to our best knowledge, due to the fact that conventional evaluation requests the hardware system to actually project the final results.

FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Tracking

no code implementations ICCV 2019 Peng Chu, Haibin Ling

Data association-based multiple object tracking (MOT) involves multiple separated modules processed or optimized differently, which results in complex method design and requires non-trivial tuning of parameters.

Management Multiple Object Tracking

Clustered Object Detection in Aerial Images

1 code implementation ICCV 2019 Fan Yang, Heng Fan, Peng Chu, Erik Blasch, Haibin Ling

The key components in ClusDet include a cluster proposal sub-network (CPNet), a scale estimation sub-network (ScaleNet), and a dedicated detection network (DetecNet).

Clustering Object +2

Salient Object Detection in the Deep Learning Era: An In-Depth Survey

1 code implementation19 Apr 2019 Wenguan Wang, Qiuxia Lai, Huazhu Fu, Jianbing Shen, Haibin Ling, Ruigang Yang

As an essential problem in computer vision, salient object detection (SOD) has attracted an increasing amount of research attention over the years.

Attribute Object +4

Graph Attribute Aggregation Network with Progressive Margin Folding

no code implementations14 May 2019 Penghui Sun, Jingwei Qu, Xiaoqing Lyu, Haibin Ling, Zhi Tang

Graph convolutional neural networks (GCNNs) have been attracting increasing research attention due to its great potential in inference over graph structures.

Attribute

Efficient and Accurate Face Alignment by Global Regression and Cascaded Local Refinement

no code implementations CVPR 2019 2019 Jinzhan Su, Zhe Wang, Chunyuan Liao, Haibin Ling

In particular, for a given image, our algorithm first estimates its global facial shape through a global regression network (GRegNet) and then using cascaded local refinement networks (LRefNet) to sequentially improve the alignment result.

Face Alignment regression

Hybrid Camera Pose Estimation with Online Partitioning for SLAM

no code implementations5 Aug 2019 Xinyi Li, Haibin Ling

This paper presents a hybrid real-time camera pose estimation framework with a novel partitioning scheme and introduces motion averaging to monocular Simultaneous Localization and Mapping (SLAM) systems.

Pose Estimation Simultaneous Localization and Mapping

CompenNet++: End-to-end Full Projector Compensation

1 code implementation ICCV 2019 Bingyao Huang, Haibin Ling

In this paper, we propose the first end-to-end solution, named CompenNet++, to solve the two problems jointly.

CBNet: A Novel Composite Backbone Network Architecture for Object Detection

6 code implementations9 Sep 2019 Yudong Liu, Yongtao Wang, Siwei Wang, Ting-Ting Liang, Qijie Zhao, Zhi Tang, Haibin Ling

In existing CNN based detectors, the backbone network is a very important component for basic feature extraction, and the performance of the detectors highly depends on it.

Instance Segmentation object-detection +2

Improving Human Annotation in Single Object Tracking

no code implementations7 Nov 2019 Yu Pang, Xinyi Li, Lin Yuan, Haibin Ling

We then use different techniques to smooth the trajectories at certain degree.

Object Video Object Tracking

TracKlinic: Diagnosis of Challenge Factors in Visual Tracking

no code implementations18 Nov 2019 Heng Fan, Fan Yang, Peng Chu, Lin Yuan, Haibin Ling

For the analysis component, given the tracking results on all sequences, it investigates the behavior of the tracker under each individual factor and generates the report automatically.

Visual Tracking

LaFIn: Generative Landmark Guided Face Inpainting

1 code implementation26 Nov 2019 Yang Yang, Xiaojie Guo, Jiayi Ma, Lin Ma, Haibin Ling

It is challenging to inpaint face images in the wild, due to the large variation of appearance, such as different poses, expressions and occlusions.

Attribute Facial Inpainting

Dually Supervised Feature Pyramid for Object Detection and Segmentation

1 code implementation8 Dec 2019 Fan Yang, Cheng Lu, Yandong Guo, Longin Jan Latecki, Haibin Ling

Feature pyramid architecture has been broadly adopted in object detection and segmentation to deal with multi-scale problem.

Object object-detection +2

Semantic-Aware Label Placement for Augmented Reality in Street View

no code implementations15 Dec 2019 Jianqing Jia, Semir Elezovikj, Heng Fan, Shuojin Yang, Jing Liu, Wei Guo, Chiu C. Tan, Haibin Ling

Our solution encodes the constraints for placing labels in an optimization problem to obtain the final label layout, and the labels will be placed in appropriate positions to reduce the chances of overlaying important real-world objects in street view AR scenarios.

Detection and Tracking Meet Drones Challenge

2 code implementations16 Jan 2020 Pengfei Zhu, Longyin Wen, Dawei Du, Xiao Bian, Heng Fan, QinGhua Hu, Haibin Ling

We provide a large-scale drone captured dataset, VisDrone, which includes four tracks, i. e., (1) image object detection, (2) video object detection, (3) single object tracking, and (4) multi-object tracking.

Multi-Object Tracking Object +2

Human-Aware Motion Deblurring

1 code implementation ICCV 2019 Ziyi Shen, Wenguan Wang, Xiankai Lu, Jianbing Shen, Haibin Ling, Tingfa Xu, Ling Shao

This paper proposes a human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG).

Deblurring Image Deblurring

Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification

no code implementations9 Feb 2020 Yifeng Ding, Shaoguo Wen, Jiyang Xie, Dongliang Chang, Zhanyu Ma, Zhongwei Si, Haibin Ling

Classifying the sub-categories of an object from the same super-category (e. g. bird species, car and aircraft models) in fine-grained visual classification (FGVC) highly relies on discriminative feature representation and accurate region localization.

Fine-Grained Image Classification General Classification

DeProCams: Simultaneous Relighting, Compensation and Shape Reconstruction for Projector-Camera Systems

no code implementations6 Mar 2020 Bingyao Huang, Haibin Ling

In this paper, we propose a novel end-to-end trainable model named DeProCams to explicitly learn the photometric and geometric mappings of ProCams, and once trained, DeProCams can be applied simultaneously to the three tasks.

Neural Rendering

Cascaded Human-Object Interaction Recognition

1 code implementation CVPR 2020 Tianfei Zhou, Wenguan Wang, Siyuan Qi, Haibin Ling, Jianbing Shen

The interaction recognition network has two crucial parts: a relation ranking module for high-quality HOI proposal selection and a triple-stream classifier for relation prediction.

Human-Object Interaction Detection Object +1

Graph Neural Network for Hamiltonian-Based Material Property Prediction

no code implementations27 May 2020 Hexin Bai, Peng Chu, Jeng-Yuan Tsai, Nathan Wilson, Xiaofeng Qian, Qimin Yan, Haibin Ling

Development of next-generation electronic devices for applications call for the discovery of quantum materials hosting novel electronic, magnetic, and topological properties.

Band Gap Property Prediction

GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling

1 code implementation27 May 2020 Zhuoying Wang, Yongtao Wang, Zhi Tang, Yangyan Li, Ying Chen, Haibin Ling, Weisi Lin

Existing CNN-based methods for pixel labeling heavily depend on multi-scale features to meet the requirements of both semantic comprehension and detail preservation.

Pose Estimation Semantic Segmentation

Cyclic Differentiable Architecture Search

3 code implementations18 Jun 2020 Hongyuan Yu, Houwen Peng, Yan Huang, Jianlong Fu, Hao Du, Liang Wang, Haibin Ling

First, the search network generates an initial architecture for evaluation, and the weights of the evaluation network are optimized.

Neural Architecture Search

Deep Bilateral Retinex for Low-Light Image Enhancement

no code implementations4 Jul 2020 Jinxiu Liang, Yong Xu, Yuhui Quan, Jingwen Wang, Haibin Ling, Hui Ji

Low-light images, i. e. the images captured in low-light conditions, suffer from very poor visibility caused by low contrast, color distortion and significant measurement noise.

Low-Light Image Enhancement

Cross-Modal Weighting Network for RGB-D Salient Object Detection

2 code implementations ECCV 2020 Gongyang Li, Zhi Liu, Linwei Ye, Yang Wang, Haibin Ling

In this paper, we propose a novel Cross-Modal Weighting (CMW) strategy to encourage comprehensive interactions between RGB and depth channels for RGB-D SOD.

object-detection Object Localization +3

Recurrent Exposure Generation for Low-Light Face Detection

1 code implementation21 Jul 2020 Jinxiu Liang, Jingwen Wang, Yuhui Quan, Tianyi Chen, Jiaying Liu, Haibin Ling, Yong Xu

REG produces progressively and efficiently intermediate images corresponding to various exposure settings, and such pseudo-exposures are then fused by MED to detect faces across different lighting conditions.

Face Detection Image Enhancement

End-to-end Full Projector Compensation

1 code implementation30 Jul 2020 Bingyao Huang, Tao Sun, Haibin Ling

Full projector compensation aims to modify a projector input image to compensate for both geometric and photometric disturbance of the projection surface.

LaSOT: A High-quality Large-scale Single Object Tracking Benchmark

1 code implementation8 Sep 2020 Heng Fan, Hexin Bai, Liting Lin, Fan Yang, Peng Chu, Ge Deng, Sijia Yu, Harshit, Mingzhen Huang, Juehuan Liu, Yong Xu, Chunyuan Liao, Lin Yuan, Haibin Ling

The average video length of LaSOT is around 2, 500 frames, where each video contains various challenge factors that exist in real world video footage, such as the targets disappearing and re-appearing.

Object Tracking Visual Tracking +1

Pushing the Envelope of Rotation Averaging for Visual SLAM

no code implementations2 Nov 2020 Xinyi Li, Lin Yuan, Longin Jan Latecki, Haibin Ling

As an essential part of structure from motion (SfM) and Simultaneous Localization and Mapping (SLAM) systems, motion averaging has been extensively studied in the past years and continues to attract surging research attention.

Robot Navigation Simultaneous Localization and Mapping

CRACT: Cascaded Regression-Align-Classification for Robust Visual Tracking

no code implementations25 Nov 2020 Heng Fan, Haibin Ling

The key is to bridge box regression and classification via an alignment step, which leads to more accurate features for proposal classification with improved robustness.

Classification General Classification +3

SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers

1 code implementation10 Dec 2020 Bingyao Huang, Haibin Ling

Light-based adversarial attacks use spatial augmented reality (SAR) techniques to fool image classifiers by altering the physical light condition with a controllable light source, e. g., a projector.

Adversarial Attack

Political Posters Identification with Appearance-Text Fusion

no code implementations19 Dec 2020 Xuan Qin, Meizhu Liu, Yifan Hu, Christina Moo, Christian M. Riblet, Changwei Hu, Kevin Yen, Haibin Ling

In this paper, we propose a method that efficiently utilizes appearance features and text vectors to accurately classify political posters from other similar political images.

Modeling Deep Learning Based Privacy Attacks on Physical Mail

1 code implementation22 Dec 2020 Bingyao Huang, Ruyi Lian, Dimitris Samaras, Haibin Ling

Mail privacy protection aims to prevent unauthorized access to hidden content within an envelope since normal paper envelopes are not as safe as we think.

Denoising Image Dehazing

Hypergraph Neural Networks for Hypergraph Matching

1 code implementation ICCV 2021 Xiaowei Liao, Yong Xu, Haibin Ling

Specifically, given two hypergraphs to be matched, we first construct an association hypergraph over them and convert the hypergraph matching problem into a node classification problem on the association hypergraph.

Graph Matching Hypergraph Matching +1

PoGO-Net: Pose Graph Optimization With Graph Neural Networks

1 code implementation ICCV 2021 Xinyi Li, Haibin Ling

Accurate camera pose estimation or global camera re-localization is a core component in Structure-from-Motion (SfM) and SLAM systems.

Pose Estimation

Personal Fixations-Based Object Segmentation with Object Localization and Boundary Preservation

1 code implementation22 Jan 2021 Gongyang Li, Zhi Liu, Ran Shi, Zheng Hu, Weijie Wei, Yong Wu, Mengke Huang, Haibin Ling

In this paper, we focus on Personal Fixations-based Object Segmentation (PFOS) to address issues in previous studies, such as the lack of appropriate dataset and the ambiguity in fixations-based interaction.

Image Segmentation Object +2

On the Robustness of Multi-View Rotation Averaging

no code implementations9 Feb 2021 Xinyi Li, Haibin Ling

Rotation averaging is a synchronization process on single or multiple rotation groups, and is a fundamental problem in many computer vision tasks such as multi-view structure from motion (SfM).

OPANAS: One-Shot Path Aggregation Network Architecture Search for Object Detection

1 code implementation CVPR 2021 TingTing Liang, Yongtao Wang, Zhi Tang, Guosheng Hu, Haibin Ling

Encouraged by the success, we propose a novel One-Shot Path Aggregation Network Architecture Search (OPANAS) algorithm, which significantly improves both searching efficiency and detection accuracy.

Neural Architecture Search object-detection +1

One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking

1 code implementation CVPR 2021 Minghao Chen, Houwen Peng, Jianlong Fu, Haibin Ling

In this paper, we propose a one-shot neural ensemble architecture search (NEAS) solution that addresses the two challenges.

Neural Architecture Search

TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking

no code implementations1 Apr 2021 Peng Chu, Jiang Wang, Quanzeng You, Haibin Ling, Zicheng Liu

TransMOT effectively models the interactions of a large number of objects by arranging the trajectories of the tracked objects as a set of sparse weighted graphs, and constructing a spatial graph transformer encoder layer, a temporal transformer encoder layer, and a spatial graph transformer decoder layer based on the graphs.

Ranked #2 on Multi-Object Tracking on 2DMOT15 (using extra training data)

Multi-Object Tracking Multiple Object Tracking +2

TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation

no code implementations28 May 2021 Xinyi Li, Haibin Ling

Camera pose estimation or camera relocalization is the centerpiece in numerous computer vision tasks such as visual odometry, structure from motion (SfM) and SLAM.

Camera Relocalization Computational Efficiency +2

Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification

no code implementations7 Jun 2021 Yifeng Ding, Shuwei Dong, Yujun Tong, Zhanyu Ma, Bo Xiao, Haibin Ling

Classifying the sub-categories of an object from the same super-category (e. g., bird) in a fine-grained visual classification (FGVC) task highly relies on mining multiple discriminative features.

Fine-Grained Image Classification

CBNet: A Composite Backbone Network Architecture for Object Detection

5 code implementations1 Jul 2021 TingTing Liang, Xiaojie Chu, Yudong Liu, Yongtao Wang, Zhi Tang, Wei Chu, Jingdong Chen, Haibin Ling

With multi-scale testing, we push the current best single model result to a new record of 60. 1% box AP and 52. 3% mask AP without using extra training data.

Ranked #6 on Object Detection on COCO-O (using extra training data)

Instance Segmentation Object +2

AutoFormer: Searching Transformers for Visual Recognition

2 code implementations ICCV 2021 Minghao Chen, Houwen Peng, Jianlong Fu, Haibin Ling

Specifically, the performance of these subnets with weights inherited from the supernet is comparable to those retrained from scratch.

AutoML Fine-Grained Image Classification

RINDNet: Edge Detection for Discontinuity in Reflectance, Illumination, Normal and Depth

1 code implementation ICCV 2021 Mengyang Pu, Yaping Huang, Qingji Guan, Haibin Ling

Taking into consideration the distinct attributes of each type of edges and the relationship between them, RINDNet learns effective representations for each of them and works in three stages.

Edge Detection

AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric Learning

1 code implementation ICCV 2021 Hong Wang, Yuefan Deng, Shinjae Yoo, Haibin Ling, Yuewei Lin

The attention knowledge is obtained from a weight-fixed model trained on a clean dataset, referred to as a teacher model, and transferred to a model that is under training on adversarial examples (AEs), referred to as a student model.

Adversarial Attack Adversarial Robustness +2

Adaptive Edge Attention for Graph Matching with Outliers

2 code implementations International Joint Conference on Artificial Intelligence 2021 Jingwei Qu, Haibin Ling, Chenrui Zhang, Xiaoqing Lyu, Zhi Tang

To explore the potential of edges, EAGM learns edge attention on the assignment graph to 1) reveal the impact of each edge on graph matching, as well as 2) adjust the learning of edge representations adaptively.

Ranked #10 on Graph Matching on PASCAL VOC (matching accuracy metric)

Edge Classification Graph Matching

Joint Graph Learning and Matching for Semantic Feature Correspondence

2 code implementations1 Sep 2021 He Liu, Tao Wang, Yidong Li, Congyan Lang, Yi Jin, Haibin Ling

In this paper, we propose a joint \emph{graph learning and matching} network, named GLAM, to explore reliable graph structures for boosting graph matching.

Graph Learning Graph Matching

Deep Learning Approach Protecting Privacy in Camera-Based Critical Applications

no code implementations4 Oct 2021 Gautham Ramajayam, Tao Sun, Chiu C. Tan, Lannan Luo, Haibin Ling

Many critical applications rely on cameras to capture video footage for analytical purposes.

Osteoporosis Prescreening using Panoramic Radiographs through a Deep Convolutional Neural Network with Attention Mechanism

no code implementations19 Oct 2021 Heng Fan, Jiaxiang Ren, Jie Yang, Yi-Xian Qin, Haibin Ling

The aim of this study was to investigate whether a deep convolutional neural network (CNN) with an attention module can detect osteoporosis on panoramic radiographs.

Searching the Search Space of Vision Transformer

1 code implementation NeurIPS 2021 Minghao Chen, Kan Wu, Bolin Ni, Houwen Peng, Bei Liu, Jianlong Fu, Hongyang Chao, Haibin Ling

Vision Transformer has shown great visual representation power in substantial vision tasks such as recognition and detection, and thus been attracting fast-growing efforts on manually designing more effective architectures.

Neural Architecture Search object-detection +4

Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images

1 code implementation2 Dec 2021 Gongyang Li, Zhi Liu, Weisi Lin, Haibin Ling

In this paper, we propose a novel Multi-Content Complementation Network (MCCNet) to explore the complementarity of multiple content for RSI-SOD.

object-detection Object Detection +1

Forward Propagation, Backward Regression, and Pose Association for Hand Tracking in the Wild

1 code implementation CVPR 2022 Mingzhen Huang, Supreeth Narasimhaswamy, Saif Vazir, Haibin Ling, Minh Hoai

The first stage is Forward Propagation, where the features from frame t-1 are propagated to frame t based on previously detected hands and their estimated motion.

 Ranked #1 on Multiple Object Tracking on YouTube-Hands (using extra training data)

Multiple Object Tracking regression

Deep Probabilistic Graph Matching

no code implementations5 Jan 2022 He Liu, Tao Wang, Yidong Li, Congyan Lang, Songhe Feng, Haibin Ling

Most previous learning-based graph matching algorithms solve the \textit{quadratic assignment problem} (QAP) by dropping one or more of the matching constraints and adopting a relaxed assignment solver to obtain sub-optimal correspondences.

Graph Matching

Consistency and Diversity induced Human Motion Segmentation

no code implementations10 Feb 2022 Tao Zhou, Huazhu Fu, Chen Gong, Ling Shao, Fatih Porikli, Haibin Ling, Jianbing Shen

Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance.

Motion Segmentation Segmentation +1

Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiography

no code implementations CVPR 2022 Jiaxiang Ren, Kicheon Park, Yingtian Pan, Haibin Ling

With the structural information and appearance feature from noisy image as references, our model can remove larger BMA and produce better visualizing result.

Image Inpainting

EDTER: Edge Detection with Transformer

1 code implementation CVPR 2022 Mengyang Pu, Yaping Huang, Yuming Liu, Qingji Guan, Haibin Ling

In Stage I, a global transformer encoder is used to capture long-range global context on coarse-grained image patches.

Edge Detection

Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images

1 code implementation25 Mar 2022 Gongyang Li, Zhi Liu, Dan Zeng, Weisi Lin, Haibin Ling

As the key component of ACCoNet, ACCoM activates the salient regions of output features of the encoder and transmits them to the decoder.

object-detection Object Detection +1

Safe Self-Refinement for Transformer-based Domain Adaptation

1 code implementation CVPR 2022 Tao Sun, Cheng Lu, Tianshuo Zhang, Haibin Ling

Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain.

Transfer Learning Unsupervised Domain Adaptation

Prior Knowledge Guided Unsupervised Domain Adaptation

1 code implementation18 Jul 2022 Tao Sun, Cheng Lu, Haibin Ling

We propose a general rectification module that uses such prior knowledge to refine model generated pseudo labels.

Unsupervised Domain Adaptation

Uncertainty-Driven Action Quality Assessment

no code implementations29 Jul 2022 Caixia Zhou, Yaping Huang, Haibin Ling

Automatic action quality assessment (AQA) has attracted increasing attention due to its wide applications.

Action Quality Assessment

Domain Adaptation with Adversarial Training on Penultimate Activations

1 code implementation26 Aug 2022 Tao Sun, Cheng Lu, Haibin Ling

We show that this strategy is more efficient and better correlated with the objective of boosting prediction confidence than adversarial training on input images or intermediate features, as used in previous works.

Unsupervised Domain Adaptation

Local Context-Aware Active Domain Adaptation

1 code implementation ICCV 2023 Tao Sun, Cheng Lu, Haibin Ling

In this paper, we propose a Local context-aware ADA framework, named LADA, to address this issue.

Domain Adaptation

Backdoor Cleansing with Unlabeled Data

1 code implementation CVPR 2023 Lu Pang, Tao Sun, Haibin Ling, Chao Chen

In experiments, we show that our method, trained without labels, is on-par with state-of-the-art defense methods trained using labels.

Knowledge Distillation

Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment

no code implementations1 Jan 2023 Libo Zhang, Wenzhang Zhou, Heng Fan, Tiejian Luo, Haibin Ling

To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning.

Domain Adaptation object-detection +1

The Cascaded Forward Algorithm for Neural Network Training

1 code implementation17 Mar 2023 Gongpei Zhao, Tao Wang, Yidong Li, Yi Jin, Congyan Lang, Haibin Ling

Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of deep learning.

Image Classification

CCTV-Gun: Benchmarking Handgun Detection in CCTV Images

1 code implementation19 Mar 2023 Srikar Yellapragada, Zhenghong Li, Kevin Bhadresh Doshi, Purva Makarand Mhasakar, Heng Fan, Jie Wei, Erik Blasch, Bin Zhang, Haibin Ling

In this paper, we present a meticulously crafted and annotated benchmark, called \textbf{CCTV-Gun}, which addresses the challenges of detecting handguns in real-world CCTV images.

Benchmarking object-detection +1

The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector

1 code implementation CVPR 2023 Caixia Zhou, Yaping Huang, Mengyang Pu, Qingji Guan, Li Huang, Haibin Ling

Deep learning-based edge detectors heavily rely on pixel-wise labels which are often provided by multiple annotators.

Edge Detection

Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder

1 code implementation27 Mar 2023 Tao Sun, Lu Pang, Chao Chen, Haibin Ling

It detects possible triggers in the token space using image structural similarity and label consistency between the test image and MAE restorations.

backdoor defense Image Generation

CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network

1 code implementation ICCV 2023 Ruyi Lian, Haibin Ling

Firstly, CheckerPose densely samples 3D keypoints from the surface of the 3D object and finds their 2D correspondences progressively in the 2D image.

Pose Estimation

DIR-AS: Decoupling Individual Identification and Temporal Reasoning for Action Segmentation

no code implementations4 Apr 2023 Peiyao Wang, Haibin Ling

Fully supervised action segmentation works on frame-wise action recognition with dense annotations and often suffers from the over-segmentation issue.

Action Recognition Action Segmentation +1

Free-Form Composition Networks for Egocentric Action Recognition

no code implementations13 Jul 2023 Haoran Wang, Qinghua Cheng, Baosheng Yu, Yibing Zhan, Dapeng Tao, Liang Ding, Haibin Ling

We evaluated our method on three popular egocentric action recognition datasets, Something-Something V2, H2O, and EPIC-KITCHENS-100, and the experimental results demonstrate the effectiveness of the proposed method for handling data scarcity problems, including long-tailed and few-shot egocentric action recognition.

Action Recognition Temporal Action Localization

Divert More Attention to Vision-Language Object Tracking

1 code implementation19 Jul 2023 Mingzhe Guo, Zhipeng Zhang, Liping Jing, Haibin Ling, Heng Fan

To thoroughly evidence the effectiveness of our method, we integrate the proposed framework on three tracking methods with different designs, i. e., the CNN-based SiamCAR, the Transformer-based OSTrack, and the hybrid structure TransT.

Attribute Object +1

INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization

no code implementations8 Sep 2023 Xi Yu, Huan-Hsin Tseng, Shinjae Yoo, Haibin Ling, Yuewei Lin

Specifically, we first propose an information theory inspired loss function to ensure the disentangled class-relevant features contain sufficient class label information and the other disentangled auxiliary feature has sufficient domain information.

Disentanglement Domain Generalization

Automated Assessment of Critical View of Safety in Laparoscopic Cholecystectomy

no code implementations13 Sep 2023 Yunfan Li, Himanshu Gupta, Haibin Ling, IV Ramakrishnan, Prateek Prasanna, Georgios Georgakis, Aaron Sasson

Compared with classical open cholecystectomy, laparoscopic cholecystectomy (LC) is associated with significantly shorter recovery period, and hence is the preferred method.

Semantic Segmentation

Transparent Object Tracking with Enhanced Fusion Module

1 code implementation13 Sep 2023 Kalyan Garigapati, Erik Blasch, Jie Wei, Haibin Ling

However, with the existing fusion techniques, the addition of new features causes a change in the latent space making it impossible to incorporate transparency awareness on trackers with fixed latent spaces.

Object Object Tracking +1

Salient Object Detection in Optical Remote Sensing Images Driven by Transformer

1 code implementation15 Sep 2023 Gongyang Li, Zhen Bai, Zhi Liu, Xinpeng Zhang, Haibin Ling

KTM models the contextual correlation knowledge of two middle-level features of different scales based on the self-attention mechanism, and transfers the knowledge to the raw features to generate more discriminative features.

object-detection Object Detection +2

Attention-Enhancing Backdoor Attacks Against BERT-based Models

no code implementations23 Oct 2023 Weimin Lyu, Songzhu Zheng, Lu Pang, Haibin Ling, Chao Chen

Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models.

Sentiment Analysis Topic Classification

CompenHR: Efficient Full Compensation for High-resolution Projector

1 code implementation22 Nov 2023 Yuxi Wang, Haibin Ling, Bingyao Huang

Full projector compensation is a practical task of projector-camera systems.

BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision

no code implementations7 Feb 2024 Xin Zhao, Shiyu Hu, Yipei Wang, Jing Zhang, Yimin Hu, Rongshuai Liu, Haibin Ling, Yin Li, Renshu Li, Kun Liu, Jiadong Li

These challenges are especially manifested in videos captured by unmanned aerial vehicles (UAV), where the target is usually far away from the camera and often with significant motion relative to the camera.

Autonomous Driving Object Tracking +1

Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance

no code implementations8 Mar 2024 Liting Lin, Heng Fan, Zhipeng Zhang, YaoWei Wang, Yong Xu, Haibin Ling

The shared embeddings, which describe the absolute coordinates of multi-resolution images (namely, the template and search images), are inherited from the pre-trained backbones.

Inductive Bias Position +1

Visibility-Aware Keypoint Localization for 6DoF Object Pose Estimation

no code implementations21 Mar 2024 Ruyi Lian, Haibin Ling

Since keypoint visibility information is currently missing in dataset collection process, we propose an efficient way to generate binary visibility labels from available object-level annotations, for keypoints of both asymmetric objects and symmetric objects.

Object Pose Estimation

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