Search Results for author: Shengjin Wang

Found 71 papers, 23 papers with code

Map Optical Properties to Subwavelength Structures Directly via a Diffusion Model

no code implementations9 Apr 2024 Shijie Rao, Kaiyu Cui, Yidong Huang, Jiawei Yang, YaLi Li, Shengjin Wang, Xue Feng, Fang Liu, Wei zhang

The inverse design methods proposed for these subwavelength structures are vital to the development of new photonic devices.

OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation

no code implementations28 Mar 2024 Zhenyu Wang, YaLi Li, Taichi Liu, Hengshuang Zhao, Shengjin Wang

Specifically, we propose the cycle-modality propagation, aimed at propagating knowledge bridging 2D and 3D modalities, to support the aforementioned functionalities.

3D Object Detection Novel Class Discovery +1

Joint Learning for Scattered Point Cloud Understanding with Hierarchical Self-Distillation

no code implementations28 Dec 2023 Kaiyue Zhou, Ming Dong, Peiyuan Zhi, Shengjin Wang

Numerous point-cloud understanding techniques focus on whole entities and have succeeded in obtaining satisfactory results and limited sparsity tolerance.

Uni3DETR: Unified 3D Detection Transformer

1 code implementation NeurIPS 2023 Zhenyu Wang, YaLi Li, Xi Chen, Hengshuang Zhao, Shengjin Wang

In this paper, we propose Uni3DETR, a unified 3D detector that addresses indoor and outdoor 3D detection within the same framework.

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

Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection

1 code implementation26 Jun 2023 Yujiang Pu, Xiaoyu Wu, Lulu Yang, Shengjin Wang

Additionally, we propose a Prompt-Enhanced Learning (PEL) module that integrates semantic priors using knowledge-based prompts to boost the discriminative capacity of context features while ensuring separability between anomaly sub-classes.

Anomaly Detection In Surveillance Videos Video Anomaly Detection +1

Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval

1 code implementation24 Oct 2022 Zhaopeng Dou, Zhongdao Wang, Weihua Chen, YaLi Li, Shengjin Wang

(3) the data uncertainty and the model uncertainty are jointly learned in a unified network, and they serve as two fundamental criteria for the reliability assessment: if a probe is high-quality (low data uncertainty) and the model is confident in the prediction of the probe (low model uncertainty), the final ranking will be assessed as reliable.

Image Retrieval Retrieval

Self-Supervised Learning via Maximum Entropy Coding

1 code implementation20 Oct 2022 Xin Liu, Zhongdao Wang, YaLi Li, Shengjin Wang

To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the learned representation is less biased and thus generalizes better to unseen downstream tasks.

Instance Segmentation object-detection +4

GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs

1 code implementation19 Oct 2022 Xin Liu, Xiaofei Shao, Bo wang, YaLi Li, Shengjin Wang

First, unlike previous methods, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning.

Autonomous Driving Depth Completion +1

Portrait Interpretation and a Benchmark

no code implementations27 Jul 2022 Yixuan Fan, Zhaopeng Dou, YaLi Li, Shengjin Wang

Furthermore, we focus on representation learning for portrait interpretation and propose a baseline that reflects our systematic perspective.

Attribute Multi-Task Learning +2

Hybrid Physical Metric For 6-DoF Grasp Pose Detection

1 code implementation22 Jun 2022 Yuhao Lu, Beixing Deng, Zhenyu Wang, Peiyuan Zhi, YaLi Li, Shengjin Wang

6-DoF grasp pose detection of multi-grasp and multi-object is a challenge task in the field of intelligent robot.

R(Det)^2: Randomized Decision Routing for Object Detection

no code implementations2 Apr 2022 Ya-Li Li, Shengjin Wang

In this paper, we propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection.

Object object-detection +1

R(Det)2: Randomized Decision Routing for Object Detection

no code implementations CVPR 2022 YaLi Li, Shengjin Wang

In this paper, we propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection.

Object object-detection +1

OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection

no code implementations CVPR 2022 Dongchen Lu, Dongmei Li, YaLi Li, Shengjin Wang

By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for rotated representation, which improves the localization accuracy and acquires high quality detection results.

Object object-detection +2

Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification

1 code implementation28 Dec 2021 Jian Han, Ya-Li Li, Shengjin Wang

With the uncertainty-guided alternative optimization, we balance between the exploration of target domain data and the negative effects of noisy labeling.

Clustering Domain Adaptive Person Re-Identification +1

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.

EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation

1 code implementation15 Oct 2021 Yaping Zhao, Mengqi Ji, Ruqi Huang, Bin Wang, Shengjin Wang

In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i. e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence.

Reference-based Video Super-Resolution Video Super-Resolution

Do Different Tracking Tasks Require Different Appearance Models?

1 code implementation NeurIPS 2021 Zhongdao Wang, Hengshuang Zhao, Ya-Li Li, Shengjin Wang, Philip H. S. Torr, Luca Bertinetto

We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks considered.

Multi-Object Tracking Multi-Object Tracking and Segmentation +10

AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes

no code implementations19 Jun 2021 Jingtao Xu, YaLi Li, Shengjin Wang

In this paper, we propose a novel Adaptive Zoom (AdaZoom) network as a selective magnifier with flexible shape and focal length to adaptively zoom the focus regions for object detection.

object-detection Object Detection

Multi-Target Domain Adaptation with Collaborative Consistency Learning

no code implementations CVPR 2021 Takashi Isobe, Xu Jia, Shuaijun Chen, Jianzhong He, Yongjie Shi, Jianzhuang Liu, Huchuan Lu, Shengjin Wang

To obtain a single model that works across multiple target domains, we propose to simultaneously learn a student model which is trained to not only imitate the output of each expert on the corresponding target domain, but also to pull different expert close to each other with regularization on their weights.

Multi-target Domain Adaptation Semantic Segmentation +1

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

no code implementations CVPR 2021 Zhenyu Wang, YaLi Li, Ye Guo, Lu Fang, Shengjin Wang

In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models.

Object object-detection +2

Revisiting Temporal Modeling for Video Super-resolution

2 code implementations13 Aug 2020 Takashi Isobe, Fang Zhu, Xu Jia, Shengjin Wang

Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities.

Computational Efficiency Video Super-Resolution

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

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

Applying BERT to Document Retrieval with Birch

no code implementations IJCNLP 2019 Zeynep Akkalyoncu Yilmaz, Shengjin Wang, Wei Yang, Haotian Zhang, Jimmy Lin

We present Birch, a system that applies BERT to document retrieval via integration with the open-source Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections.

Information Retrieval Retrieval

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

Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning

no code implementations4 Aug 2019 Lanqing He, Zhongdao Wang, Ya-Li Li, Shengjin Wang

The softmax loss and its variants are widely used as objectives for embedding learning, especially in applications like face recognition.

Face Recognition Face Verification

Adversarial View-Consistent Learning for Monocular Depth Estimation

no code implementations4 Aug 2019 Yixuan Liu, Yuwang Wang, Shengjin Wang

To this end, we first design a differentiable depth map warping operation, which is end-to-end trainable, and then propose a pose generator to generate novel views for a given image in an adversarial manner.

Monocular Depth Estimation

CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection

no code implementations30 May 2019 Ye Guo, Ya-Li Li, Shengjin Wang

Generic object detection is one of the most fundamental problems in computer vision, yet it is difficult to provide all the bounding-box-level annotations aiming at large-scale object detection for thousands of categories.

Object object-detection +1

Intra-clip Aggregation for Video Person Re-identification

no code implementations5 May 2019 Takashi Isobe, Jian Han, Fang Zhu, Ya-Li Li, Shengjin Wang

Video-based person re-identification has drawn massive attention in recent years due to its extensive applications in video surveillance.

Data Augmentation Video-Based Person Re-Identification

HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection

no code implementations25 Apr 2019 Ya-Li Li, Shengjin Wang

First, we present the modules of spatial attention, channel attention and aligned attention for single-stage object detection.

Object object-detection +1

Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification

1 code implementation CVPR 2019 Yifan Sun, Qin Xu, Ya-Li Li, Chi Zhang, Yikang Li, Shengjin Wang, Jian Sun

The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images).

Person Re-Identification

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

Intention Oriented Image Captions with Guiding Objects

no code implementations CVPR 2019 Yue Zheng, Ya-Li Li, Shengjin Wang

In this paper, we propose a novel approach for generating image captions with guiding objects (CGO).

Image Captioning Object

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

DeepDeblur: Fast one-step blurry face images restoration

no code implementations27 Nov 2017 Lingxiao Wang, Ya-Li Li, Shengjin Wang

Comprehensive experiments demonstrate that our proposed method can handle various blur kenels and achieve state-of-the-art results for small size blurry face images restoration.

Deblurring Face Recognition

Progressive Representation Adaptation for Weakly Supervised Object Localization

1 code implementation12 Oct 2017 Dong Li, Jia-Bin Huang, Ya-Li Li, Shengjin Wang, Ming-Hsuan Yang

In classification adaptation, we transfer a pre-trained network to a multi-label classification task for recognizing the presence of a certain object in an image.

Classification General Classification +4

SegFlow: Joint Learning for Video Object Segmentation and Optical Flow

1 code implementation ICCV 2017 Jingchun Cheng, Yi-Hsuan Tsai, Shengjin Wang, Ming-Hsuan Yang

This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos.

Image Segmentation Object +7

Learning to Segment Instances in Videos with Spatial Propagation Network

no code implementations14 Sep 2017 Jingchun Cheng, Sifei Liu, Yi-Hsuan Tsai, Wei-Chih Hung, Shalini De Mello, Jinwei Gu, Jan Kautz, Shengjin Wang, Ming-Hsuan Yang

In addition, we apply a filter on the refined score map that aims to recognize the best connected region using spatial and temporal consistencies in the video.

Object Segmentation +1

Learning Structured Semantic Embeddings for Visual Recognition

no code implementations5 Jun 2017 Dong Li, Hsin-Ying Lee, Jia-Bin Huang, Shengjin Wang, Ming-Hsuan Yang

First, we exploit the discriminative constraints to capture the intra- and inter-class relationships of image embeddings.

General Classification Multi-Label Classification +2

Metric Learning in Codebook Generation of Bag-of-Words for Person Re-identification

no code implementations8 Apr 2017 Lu Tian, Shengjin Wang

Person re-identification is generally divided into two part: first how to represent a pedestrian by discriminative visual descriptors and second how to compare them by suitable distance metrics.

Clustering Metric Learning +1

Weakly Supervised Object Localization With Progressive Domain Adaptation

no code implementations CVPR 2016 Dong Li, Jia-Bin Huang, Ya-Li Li, Shengjin Wang, Ming-Hsuan Yang

In this paper, we address this problem by progressive domain adaptation with two main steps: classification adaptation and detection adaptation.

Classification Domain Adaptation +5

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

Person Re-Identification by Discriminative Selection in Video Ranking

no code implementations23 Jan 2016 Taiqing Wang, Shaogang Gong, Xiatian Zhu, Shengjin Wang

Current person re-identification (ReID) methods typically rely on single-frame imagery features, whilst ignoring space-time information from image sequences often available in the practical surveillance scenarios.

Gait Recognition Person Re-Identification

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

Fast Orthogonal Projection Based on Kronecker Product

no code implementations ICCV 2015 Xu Zhang, Felix X. Yu, Ruiqi Guo, Sanjiv Kumar, Shengjin Wang, Shi-Fu Chang

We propose a family of structured matrices to speed up orthogonal projections for high-dimensional data commonly seen in computer vision applications.

Image Retrieval Quantization

Deep Transfer Network: Unsupervised Domain Adaptation

no code implementations2 Mar 2015 Xu Zhang, Felix Xinnan Yu, Shih-Fu Chang, Shengjin Wang

In this paper, we propose a new domain adaptation framework named Deep Transfer Network (DTN), where the highly flexible deep neural networks are used to implement such a distribution matching process.

Unsupervised Domain Adaptation

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

Beyond $χ^2$ Difference: Learning Optimal Metric for Boundary Detection

no code implementations4 Jun 2014 Fei He, Shengjin Wang

To improve the performance of boundary detection, a Learning-based Boundary Metric (LBM) is proposed to replace $\chi^2$ difference adopted by the classical algorithm mPb.

Boundary Detection

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.