Search Results for author: Liang Zheng

Found 121 papers, 57 papers with code

Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments

1 code implementation20 Mar 2024 Yang Yang, Wenhai Wang, Zhe Chen, Jifeng Dai, Liang Zheng

However, in the real-world where test ground truths are not provided, it is non-trivial to find out whether bounding boxes are accurate, thus preventing us from assessing the detector generalization ability.

object-detection Object Detection +1

Training A Small Emotional Vision Language Model for Visual Art Comprehension

1 code implementation17 Mar 2024 Jing Zhang, Liang Zheng, Dan Guo, Meng Wang

This paper develops small vision language models to understand visual art, which, given an art work, aims to identify its emotion category and explain this prediction with natural language.

Language Modelling

Strong and Controllable Blind Image Decomposition

1 code implementation15 Mar 2024 Zeyu Zhang, Junlin Han, Chenhui Gou, Hongdong Li, Liang Zheng

To address this need, we add controllability to the blind image decomposition process, allowing users to enter which types of degradation to remove or retain.

Taylor Videos for Action Recognition

1 code implementation5 Feb 2024 Lei Wang, Xiuyuan Yuan, Tom Gedeon, Liang Zheng

Addressing these challenges, we propose the Taylor video, a new video format that highlights the dominate motions (e. g., a waving hand) in each of its frames named the Taylor frame.

Action Recognition Optical Flow Estimation

Seller-Side Experiments under Interference Induced by Feedback Loops in Two-Sided Platforms

no code implementations29 Jan 2024 Zhihua Zhu, Zheng Cai, Liang Zheng, Nian Si

Two-sided platforms are central to modern commerce and content sharing and often utilize A/B testing for developing new features.

counterfactual

SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control

no code implementations8 Dec 2023 Jaskirat Singh, Jianming Zhang, Qing Liu, Cameron Smith, Zhe Lin, Liang Zheng

To overcome these limitations, we introduce SmartMask, which allows any novice user to create detailed masks for precise object insertion.

Image Inpainting Layout Design +2

Optimizing Camera Configurations for Multi-View Pedestrian Detection

no code implementations4 Dec 2023 Yunzhong Hou, Xingjian Leng, Tom Gedeon, Liang Zheng

Jointly considering multiple camera views (multi-view) is very effective for pedestrian detection under occlusion.

Pedestrian Detection

In Search of Lost Online Test-time Adaptation: A Survey

1 code implementation31 Oct 2023 Zixin Wang, Yadan Luo, Liang Zheng, Zhuoxiao Chen, Sen Wang, Zi Huang

In this paper, we present a comprehensive survey on online test-time adaptation (OTTA), a paradigm focused on adapting machine learning models to novel data distributions upon batch arrival.

Test-time Adaptation

Pre-Training on Large-Scale Generated Docking Conformations with HelixDock to Unlock the Potential of Protein-ligand Structure Prediction Models

no code implementations21 Oct 2023 Lihang Liu, Donglong He, Xianbin Ye, Jingbo Zhou, Shanzhuo Zhang, Xiaonan Zhang, Jun Li, Hua Chai, Fan Wang, Jingzhou He, Liang Zheng, Yonghui Li, Xiaomin Fang

In this work, we show that by pre-training a geometry-aware SE(3)-Equivariant neural network on a large-scale docking conformation generated by traditional physics-based docking tools and then fine-tuning with a limited set of experimentally validated receptor-ligand complexes, we can achieve outstanding performance.

Drug Discovery Molecular Docking

Adaptive Multi-head Contrastive Learning

no code implementations9 Oct 2023 Lei Wang, Piotr Koniusz, Tom Gedeon, Liang Zheng

As such, enforcing a high similarity for positive pairs and a low similarity for negative pairs may not always be achievable, and in the case of some pairs, forcing so may be detrimental to the performance.

Contrastive Learning

Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic

no code implementations6 Oct 2023 Xiaoxiao Sun, Yue Yao, Shengjin Wang, Hongdong Li, Liang Zheng

In this paper, we detail the settings of Alice benchmarks, provide an analysis of existing commonly-used domain adaptation methods, and discuss some interesting future directions.

Domain Adaptation

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis

no code implementations6 Oct 2023 Xiaoxiao Sun, Xingjian Leng, Zijian Wang, Yang Yang, Zi Huang, Liang Zheng

Analyzing model performance in various unseen environments is a critical research problem in the machine learning community.

Benchmarking Domain Generalization +1

Training with Product Digital Twins for AutoRetail Checkout

1 code implementation18 Aug 2023 Yue Yao, Xinyu Tian, Zheng Tang, Sujit Biswas, Huan Lei, Tom Gedeon, Liang Zheng

Because the digital twins individually mimic user bias, the resulting DT training set better reflects the characteristics of the target scenario and allows us to train more effective product detection and tracking models.

Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback

no code implementations NeurIPS 2023 Jaskirat Singh, Liang Zheng

Furthermore, we also find that the assertion level alignment scores provide a useful feedback which can then be used in a simple iterative procedure to gradually increase the expression of different assertions in the final image outputs.

Image Generation Visual Question Answering (VQA)

The 7th AI City Challenge

no code implementations15 Apr 2023 Milind Naphade, Shuo Wang, David C. Anastasiu, Zheng Tang, Ming-Ching Chang, Yue Yao, Liang Zheng, Mohammed Shaiqur Rahman, Meenakshi S. Arya, Anuj Sharma, Qi Feng, Vitaly Ablavsky, Stan Sclaroff, Pranamesh Chakraborty, Sanjita Prajapati, Alice Li, Shangru Li, Krishna Kunadharaju, Shenxin Jiang, Rama Chellappa

The AI City Challenge's seventh edition emphasizes two domains at the intersection of computer vision and artificial intelligence - retail business and Intelligent Traffic Systems (ITS) - that have considerable untapped potential.

Retrieval

Large-scale Training Data Search for Object Re-identification

1 code implementation CVPR 2023 Yue Yao, Huan Lei, Tom Gedeon, Liang Zheng

We consider a scenario where we have access to the target domain, but cannot afford on-the-fly training data annotation, and instead would like to construct an alternative training set from a large-scale data pool such that a competitive model can be obtained.

Object Specificity

A Bag-of-Prototypes Representation for Dataset-Level Applications

no code implementations CVPR 2023 Weijie Tu, Weijian Deng, Tom Gedeon, Liang Zheng

The former measures how suitable a training set is for a target domain, while the latter studies how challenging a test set is for a learned model.

Learning to Select Camera Views: Efficient Multiview Understanding at Few Glances

1 code implementation10 Mar 2023 Yunzhong Hou, Stephen Gould, Liang Zheng

Multiview camera setups have proven useful in many computer vision applications for reducing ambiguities, mitigating occlusions, and increasing field-of-view coverage.

Adaptive Calibrator Ensemble for Model Calibration under Distribution Shift

no code implementations9 Mar 2023 Yuli Zou, Weijian Deng, Liang Zheng

In other words, a calibrator optimal on the calibration set would be suboptimal on the OOD test set and thus has degraded performance.

Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation

no code implementations2 Feb 2023 Weijian Deng, Yumin Suh, Stephen Gould, Liang Zheng

This work aims to assess how well a model performs under distribution shifts without using labels.

Large-Scale Traffic Data Imputation with Spatiotemporal Semantic Understanding

no code implementations27 Jan 2023 Kunpeng Zhang, Lan Wu, Liang Zheng, Na Xie, Zhengbing He

Specifically, the proposed model introduces semantic descriptions consisting of network-wide spatial and temporal information of traffic data to help the GT-TDI model capture spatiotemporal correlations at a network level.

Imputation Traffic Data Imputation

CircNet: Meshing 3D Point Clouds with Circumcenter Detection

1 code implementation23 Jan 2023 Huan Lei, Ruitao Leng, Liang Zheng, Hongdong Li

In this paper, we leverage the duality between a triangle and its circumcenter, and introduce a deep neural network that detects the circumcenters to achieve point cloud triangulation.

Surface Reconstruction

How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability

no code implementations ICCV 2023 Zijian Wang, Yadan Luo, Liang Zheng, Zi Huang, Mahsa Baktashmotlagh

This paper focuses on model transferability estimation, i. e., assessing the performance of pre-trained models on a downstream task without performing fine-tuning.

Adaptive Calibrator Ensemble: Navigating Test Set Difficulty in Out-of-Distribution Scenarios

1 code implementation ICCV 2023 Yuli Zou, Weijian Deng, Liang Zheng

With this knowledge, we propose a simple and effective method named adaptive calibrator ensemble (ACE) to calibrate OOD datasets whose difficulty is usually higher than the calibration set.

Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing

1 code implementation17 Aug 2022 Jaskirat Singh, Liang Zheng, Cameron Smith, Jose Echevarria

In particular, we propose a novel approach paint2pix, which learns to predict (and adapt) "what a user wants to draw" from rudimentary brushstroke inputs, by learning a mapping from the manifold of incomplete human paintings to their realistic renderings.

Image Generation

Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation

no code implementations17 Aug 2022 Yunzhong Hou, Stephen Gould, Liang Zheng

In this paper, we take the best of both worlds and propose multi-view correlation consistency (MVCC) learning: it considers rich pairwise relationships in self-correlation matrices and matches them across views to provide robust supervision.

Contrastive Learning Data Augmentation +1

Learning to Structure an Image with Few Colors and Beyond

no code implementations17 Aug 2022 Yunzhong Hou, Liang Zheng, Stephen Gould

To this end, we propose a color quantization network, ColorCNN, which learns to structure an image in limited color spaces by minimizing the classification loss.

Image Compression Imitation Learning +1

On the Strong Correlation Between Model Invariance and Generalization

no code implementations14 Jul 2022 Weijian Deng, Stephen Gould, Liang Zheng

Generalization and invariance are two essential properties of any machine learning model.

Multiview Detection with Cardboard Human Modeling

1 code implementation5 Jul 2022 Jiahao Ma, Zicheng Duan, Liang Zheng, Chuong Nguyen

In this paper, we propose a new pedestrian representation scheme based on human point clouds modeling.

Depth Estimation Multiview Detection

Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond

2 code implementations28 Feb 2022 Yue Yao, Liang Zheng, Xiaodong Yang, Milind Napthade, Tom Gedeon

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data.

Attribute Data Augmentation +2

Intelli-Paint: Towards Developing Human-like Painting Agents

no code implementations16 Dec 2021 Jaskirat Singh, Cameron Smith, Jose Echevarria, Liang Zheng

However, current research in this direction is often reliant on a progressive grid-based division strategy wherein the agent divides the overall image into successively finer grids, and then proceeds to paint each of them in parallel.

Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking

no code implementations14 Dec 2021 Yunzhong Hou, Zhongdao Wang, Shengjin Wang, Liang Zheng

In this paper, we design experiments to verify such misfit between global re-ID feature distances and local matching in tracking, and propose a simple yet effective approach to adapt affinity estimations to corresponding matching scopes in MTMCT.

How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?

1 code implementation3 Dec 2021 Yuchi Liu, Zhongdao Wang, Tom Gedeon, Liang Zheng

To this end, we develop a protocol to automatically synthesize large scale MiE training data that allow us to train improved recognition models for real-world test data.

Face Generation Micro-Expression Recognition

Label-Free Model Evaluation with Semi-Structured Dataset Representations

1 code implementation1 Dec 2021 Xiaoxiao Sun, Yunzhong Hou, Hongdong Li, Liang Zheng

In the absence of image labels, based on dataset representations, we estimate model performance for AutoEval with regression.

regression

Hierarchical Image Classification with A Literally Toy Dataset

no code implementations1 Nov 2021 Long He, Dandan song, Liang Zheng

We define the classification task where classes have characteristics above and the flat classes and the base classes are organized hierarchically as hierarchical image classification.

Classification Image Classification +1

Memory-Free Generative Replay For Class-Incremental Learning

1 code implementation1 Sep 2021 Xiaomeng Xin, Yiran Zhong, Yunzhong Hou, Jinjun Wang, Liang Zheng

With the absence of old task images, they often assume that old knowledge is well preserved if the classifier produces similar output on new images.

Class Incremental Learning Incremental Learning

Ranking Models in Unlabeled New Environments

2 code implementations ICCV 2021 Xiaoxiao Sun, Yunzhong Hou, Weijian Deng, Hongdong Li, Liang Zheng

For this problem, we propose to adopt a proxy dataset that 1) is fully labeled and 2) well reflects the true model rankings in a given target environment, and use the performance rankings on the proxy sets as surrogates.

Person Re-Identification

Multiview Detection with Shadow Transformer (and View-Coherent Data Augmentation)

1 code implementation12 Aug 2021 Yunzhong Hou, Liang Zheng

Multiview detection incorporates multiple camera views to deal with occlusions, and its central problem is multiview aggregation.

Data Augmentation Multiview Detection +1

Synthetic Data Are as Good as the Real for Association Knowledge Learning in Multi-object Tracking

no code implementations30 Jun 2021 Yuchi Liu, Zhongdao Wang, Xiangxin Zhou, Liang Zheng

We show that compared with real data, association knowledge obtained from synthetic data can achieve very similar performance on real-world test sets without domain adaption techniques.

Domain Adaptation Multi-Object Tracking

Invertible Attention

1 code implementation16 Jun 2021 Jiajun Zha, Yiran Zhong, Jing Zhang, Richard Hartley, Liang Zheng

Attention has been proved to be an efficient mechanism to capture long-range dependencies.

Image Reconstruction

What Does Rotation Prediction Tell Us about Classifier Accuracy under Varying Testing Environments?

no code implementations10 Jun 2021 Weijian Deng, Stephen Gould, Liang Zheng

In this work, we train semantic classification and rotation prediction in a multi-task way.

VTNet: Visual Transformer Network for Object Goal Navigation

no code implementations ICLR 2021 Heming Du, Xin Yu, Liang Zheng

In this paper, we introduce a Visual Transformer Network (VTNet) for learning informative visual representation in navigation.

Object

Boosting Semi-Supervised Face Recognition with Noise Robustness

1 code implementation10 May 2021 Yuchi Liu, Hailin Shi, Hang Du, Rui Zhu, Jun Wang, Liang Zheng, Tao Mei

This paper presents an effective solution to semi-supervised face recognition that is robust to the label noise aroused by the auto-labelling.

Face Recognition

Visualizing Adapted Knowledge in Domain Transfer

1 code implementation CVPR 2021 Yunzhong Hou, Liang Zheng

We visualize the adapted knowledge on several datasets with different UDA methods and find that generated images successfully capture the style difference between the two domains.

Explainable artificial intelligence Translation +1

Positive Sample Propagation along the Audio-Visual Event Line

2 code implementations CVPR 2021 Jinxing Zhou, Liang Zheng, Yiran Zhong, Shijie Hao, Meng Wang

To encourage the network to extract high correlated features for positive samples, a new audio-visual pair similarity loss is proposed.

audio-visual event localization

Sparse Attention Guided Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning

no code implementations14 Feb 2021 Jaskirat Singh, Liang Zheng

However, we argue that the sample variance for a multi-scene environment is best minimized by treating each scene as a distinct MDP, and then learning a joint value function V(s, M) dependent on both state s and MDP M. We further demonstrate that the true joint value function for a multi-scene environment, follows a multi-modal distribution which is not captured by traditional CNN / LSTM based critic networks.

reinforcement-learning Reinforcement Learning (RL)

Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings

1 code implementation CVPR 2021 Jaskirat Singh, Liang Zheng

2) We also introduce invariance to the position and scale of the foreground object through a neural alignment model, which combines object localization and spatial transformer networks in an end to end manner, to zoom into a particular semantic instance.

Model-based Reinforcement Learning Object +3

Enhanced Scene Specificity with Sparse Dynamic Value Estimation

no code implementations25 Nov 2020 Jaskirat Singh, Liang Zheng

Recently, Singh et al. [1] tried to address this by proposing a dynamic value estimation approach that models the true joint value function distribution as a Gaussian mixture model (GMM).

Specificity

Source Free Domain Adaptation with Image Translation

no code implementations17 Aug 2020 Yunzhong Hou, Liang Zheng

In this paper, we study the problem of source free domain adaptation (SFDA), whose distinctive feature is that the source domain only provides a pre-trained model, but no source data.

Image Classification Source-Free Domain Adaptation +1

Learning Object Relation Graph and Tentative Policy for Visual Navigation

1 code implementation ECCV 2020 Heming Du, Xin Yu, Liang Zheng

Aiming to improve these two components, this paper proposes three complementary techniques, object relation graph (ORG), trial-driven imitation learning (IL), and a memory-augmented tentative policy network (TPN).

Imitation Learning Relation +2

CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions

no code implementations ECCV 2020 Zhongdao Wang, Jingwei Zhang, Liang Zheng, Yixuan Liu, Yifan Sun, Ya-Li Li, Shengjin Wang

This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering.

Clustering Multi-Object Tracking +2

Are Labels Always Necessary for Classifier Accuracy Evaluation?

no code implementations CVPR 2021 Weijian Deng, Liang Zheng

As the classification accuracy of the model on each sample (dataset) is known from the original dataset labels, our task can be solved via regression.

Object Recognition regression

Learning to simulate complex scenes

1 code implementation25 Jun 2020 Zhenfeng Xue, Weijie Mao, Liang Zheng

To optimize the attribute values and obtain a training set of similar content to real-world data, we propose a scalable discretization-and-relaxation (SDR) approach.

Attribute Semantic Segmentation +1

Dynamic Value Estimation for Single-Task Multi-Scene Reinforcement Learning

no code implementations25 May 2020 Jaskirat Singh, Liang Zheng

Training deep reinforcement learning agents on environments with multiple levels / scenes / conditions from the same task, has become essential for many applications aiming to achieve generalization and domain transfer from simulation to the real world.

Clustering reinforcement-learning +2

Correlating Edge, Pose with Parsing

1 code implementation CVPR 2020 Ziwei Zhang, Chi Su, Liang Zheng, Xiaodong Xie

Compared with the existing practice of feature concatenation, we find that uncovering the correlation among the three factors is a superior way of leveraging the pivotal contextual cues provided by edges and poses.

Feature Correlation Human Parsing

Circle Loss: A Unified Perspective of Pair Similarity Optimization

11 code implementations CVPR 2020 Yifan Sun, Changmao Cheng, Yuhan Zhang, Chi Zhang, Liang Zheng, Zhongdao Wang, Yichen Wei

This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming to maximize the within-class similarity $s_p$ and minimize the between-class similarity $s_n$.

 Ranked #1 on Face Verification on IJB-C (training dataset metric)

Face Recognition Face Verification +4

Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking

1 code implementation27 Nov 2019 Yunzhong Hou, Liang Zheng, Zhongdao Wang, Shengjin Wang

Due to the continuity of target trajectories, tracking systems usually restrict their data association within a local neighborhood.

Multi-Object Tracking

Towards Real-Time Multi-Object Tracking

12 code implementations ECCV 2020 Zhongdao Wang, Liang Zheng, Yixuan Liu, Ya-Li Li, Shengjin Wang

In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model.

Multiple Object Tracking Multi-Task Learning +2

Learning to Adapt Invariance in Memory for Person Re-identification

no code implementations1 Aug 2019 Zhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang

This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain.

Person Re-Identification Unsupervised Domain Adaptation

Linkage Based Face Clustering via Graph Convolution Network

4 code implementations CVPR 2019 Zhongdao Wang, Liang Zheng, Ya-Li Li, Shengjin Wang

The key idea is that we find the local context in the feature space around an instance (face) contains rich information about the linkage relationship between this instance and its neighbors.

Clustering Face Clustering +1

Image Classification base on PCA of Multi-view Deep Representation

no code implementations12 Mar 2019 Yaoqi Sun, Liang Li, Liang Zheng, Ji Hu, Yatong Jiang, Chenggang Yan

In the age of information explosion, image classification is the key technology of dealing with and organizing a large number of image data.

Classification General Classification +1

Learning from Web Data: the Benefit of Unsupervised Object Localization

no code implementations21 Dec 2018 Xiaoxiao Sun, Liang Zheng, Yu-Kun Lai, Jufeng Yang

In this work, we first systematically study the built-in gap between the web and standard datasets, i. e. different data distributions between the two kinds of data.

Fine-Grained Image Classification General Classification +2

Dissecting Person Re-identification from the Viewpoint of Viewpoint

1 code implementation CVPR 2019 Xiaoxiao Sun, Liang Zheng

Second, on the 3D data engine, we quantitatively analyze the influence of pedestrian rotation angle on re-ID accuracy.

Person Re-Identification

Domain Alignment with Triplets

no code implementations3 Dec 2018 Weijian Deng, Liang Zheng, Jianbin Jiao

When aligning the distributions in the embedding space, SCA enforces a similarity-preserving constraint to maintain class-level relations among the source and target images, i. e., if a source image and a target image are of the same class label, their corresponding embeddings are supposed to be aligned nearby, and vise versa.

Unsupervised Domain Adaptation

Similarity-preserving Image-image Domain Adaptation for Person Re-identification

no code implementations26 Nov 2018 Weijian Deng, Liang Zheng, Qixiang Ye, Yi Yang, Jianbin Jiao

It first preserves two types of unsupervised similarity, namely, self-similarity of an image before and after translation, and domain-dissimilarity of a translated source image and a target image.

Domain Adaptation Generative Adversarial Network +2

Query Adaptive Late Fusion for Image Retrieval

no code implementations31 Oct 2018 Zhongdao Wang, Liang Zheng, Shengjin Wang

That is to say, for some queries, a feature may be neither discriminative nor complementary to existing ones, while for other queries, the feature suffices.

Image Retrieval Person Recognition +2

Query Attack via Opposite-Direction Feature:Towards Robust Image Retrieval

2 code implementations7 Sep 2018 Zhedong Zheng, Liang Zheng, Yi Yang, Fei Wu

Opposite-Direction Feature Attack (ODFA) effectively exploits feature-level adversarial gradients and takes advantage of feature distance in the representation space.

Adversarial Attack General Classification +3

Generalizing A Person Retrieval Model Hetero- and Homogeneously

1 code implementation ECCV 2018 Zhun Zhong, Liang Zheng, Shaozi Li, Yi Yang

Person re-identification (re-ID) poses unique challenges for unsupervised domain adaptation (UDA) in that classes in the source and target sets (domains) are entirely different and that image variations are largely caused by cameras.

Person Re-Identification Person Retrieval +2

Attention-based Pyramid Aggregation Network for Visual Place Recognition

no code implementations1 Aug 2018 Yingying Zhu, Jiong Wang, Lingxi Xie, Liang Zheng

Visual place recognition is challenging in the urban environment and is usually viewed as a large scale image retrieval task.

Image Retrieval Retrieval +1

Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification

2 code implementations CVPR 2018 Weijian Deng, Liang Zheng, Qixiang Ye, Guoliang Kang, Yi Yang, Jianbin Jiao

To this end, we propose to preserve two types of unsupervised similarities, 1) self-similarity of an image before and after translation, and 2) domain-dissimilarity of a translated source image and a target image.

Generative Adversarial Network Person Re-Identification +2

Random Erasing Data Augmentation

17 code implementations16 Aug 2017 Zhun Zhong, Liang Zheng, Guoliang Kang, Shaozi Li, Yi Yang

In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).

General Classification Image Augmentation +4

PatchShuffle Regularization

no code implementations22 Jul 2017 Guoliang Kang, Xuanyi Dong, Liang Zheng, Yi Yang

This paper focuses on regularizing the training of the convolutional neural network (CNN).

General Classification

Few-Example Object Detection with Model Communication

1 code implementation26 Jun 2017 Xuanyi Dong, Liang Zheng, Fan Ma, Yi Yang, Deyu Meng

Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.

Object object-detection

Part-based Deep Hashing for Large-scale Person Re-identification

no code implementations5 May 2017 Fuqing Zhu, Xiangwei Kong, Liang Zheng, Haiyan Fu, Qi Tian

In the experiment, we show that the proposed Part-based Deep Hashing method yields very competitive re-id accuracy on the large-scale Market-1501 and Market-1501+500K datasets.

Deep Hashing Large-Scale Person Re-Identification

Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval

no code implementations20 Mar 2017 Yuting Hu, Liang Zheng, Yi Yang, Yongfeng Huang

Second, texts in these datasets are written in well-organized language, leading to inconsistency with realistic applications.

Optical Character Recognition (OCR) Retrieval +1

A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval

no code implementations10 Mar 2017 Ruoyu Liu, Yao Zhao, Liang Zheng, Shikui Wei, Yi Yang

Additionally, a trivial solution, \ie, directly using the predicted class label for cross-media retrieval, is tested.

Benchmarking Image Retrieval +1

Re-ranking Person Re-identification with k-reciprocal Encoding

no code implementations CVPR 2017 Zhun Zhong, Liang Zheng, Donglin Cao, Shaozi Li

Specifically, given an image, a k-reciprocal feature is calculated by encoding its k-reciprocal nearest neighbors into a single vector, which is used for re-ranking under the Jaccard distance.

Person Re-Identification Re-Ranking +1

Pose Invariant Embedding for Deep Person Re-identification

no code implementations26 Jan 2017 Liang Zheng, Yujia Huang, Huchuan Lu, Yi Yang

Second, to reduce the impact of pose estimation errors and information loss during PoseBox construction, we design a PoseBox fusion (PBF) CNN architecture that takes the original image, the PoseBox, and the pose estimation confidence as input.

Person Re-Identification Pose Estimation +1

A Discriminatively Learned CNN Embedding for Person Re-identification

4 code implementations17 Nov 2016 Zhedong Zheng, Liang Zheng, Yi Yang

We revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i. e, verification and classification models.

General Classification Image Retrieval +2

Person Re-identification: Past, Present and Future

no code implementations10 Oct 2016 Liang Zheng, Yi Yang, Alexander G. Hauptmann

Person re-identification (re-ID) has become increasingly popular in the community due to its application and research significance.

Image Classification Person Re-Identification +1

SIFT Meets CNN: A Decade Survey of Instance Retrieval

1 code implementation5 Aug 2016 Liang Zheng, Yi Yang, Qi Tian

This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods.

Content-Based Image Retrieval Retrieval

Coarse2Fine: Two-Layer Fusion For Image Retrieval

no code implementations4 Jul 2016 Gaipeng Kong, Le Dong, Wenpu Dong, Liang Zheng, Qi Tian

Departing from the previous methods fusing multiple image descriptors simultaneously, C2F is featured by a layered procedure composed by filtering and refining.

Image Retrieval Retrieval +1

InterActive: Inter-Layer Activeness Propagation

no code implementations CVPR 2016 Lingxi Xie, Liang Zheng, Jingdong Wang, Alan Yuille, Qi Tian

An increasing number of computer vision tasks can be tackled with deep features, which are the intermediate outputs of a pre-trained Convolutional Neural Network.

Descriptive General Classification

Person Re-identification in the Wild

no code implementations CVPR 2017 Liang Zheng, Hengheng Zhang, Shaoyan Sun, Manmohan Chandraker, Yi Yang, Qi Tian

Our baselines address three issues: the performance of various combinations of detectors and recognizers, mechanisms for pedestrian detection to help improve overall re-identification accuracy and assessing the effectiveness of different detectors for re-identification.

Benchmarking Pedestrian Detection +2

Good Practice in CNN Feature Transfer

no code implementations1 Apr 2016 Liang Zheng, Yali Zhao, Shengjin Wang, Jingdong Wang, Qi Tian

The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification.

General Classification Image Retrieval

Scalable Person Re-Identification: A Benchmark

no code implementations ICCV 2015 Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, Qi Tian

As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor.

Image Retrieval Person Re-Identification

Person Re-identification Meets Image Search

no code implementations7 Feb 2015 Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jiahao Bu, Qi Tian

In the light of recent advances in image search, this paper proposes to treat person re-identification as an image search problem.

Image Retrieval Person Re-Identification

Visual Reranking with Improved Image Graph

no code implementations3 Jun 2014 Ziqiong Liu, Shengjin Wang, Liang Zheng, Qi Tian

This paper introduces an improved reranking method for the Bag-of-Words (BoW) based image search.

Image Retrieval

Seeing the Big Picture: Deep Embedding with Contextual Evidences

no code implementations1 Jun 2014 Liang Zheng, Shengjin Wang, Fei He, Qi Tian

Specifically, the Convolutional Neural Network (CNN) is employed to extract features from regional and global patches, leading to the so-called "Deep Embedding" framework.

Image Classification Image Retrieval +1

Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval

no code implementations CVPR 2014 Liang Zheng, Shengjin Wang, Wengang Zhou, Qi Tian

Albeit simple, Bayes merging can be well applied in various merging tasks, and consistently improves the baselines on multi-vocabulary merging.

Image Retrieval Quantization +1

Lp-Norm IDF for Large Scale Image Search

no code implementations CVPR 2013 Liang Zheng, Shengjin Wang, Ziqiong Liu, Qi Tian

Further, by counting for the term-frequency in each image, the proposed L p -norm IDF helps to alleviate the visual word burstiness phenomenon.

Image Retrieval

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