Search Results for author: Junwei Han

Found 104 papers, 47 papers with code

CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstruction

no code implementations29 Mar 2025 Yuanyuan Gao, Hao Li, Jiaqi Chen, Zhengyu Zou, Zhihang Zhong, Dingwen Zhang, Xiao Sun, Junwei Han

Despite its significant achievements in large-scale scene reconstruction, 3D Gaussian Splatting still faces substantial challenges, including slow processing, high computational costs, and limited geometric accuracy.

$\mathbfΦ$-GAN: Physics-Inspired GAN for Generating SAR Images Under Limited Data

no code implementations4 Mar 2025 Xidan Zhang, Yihan Zhuang, Qian Guo, Haodong Yang, Xuelin Qian, Gong Cheng, Junwei Han, Zhongling Huang

We propose two physical loss functions: one for the generator, guiding it to produce SAR images with physical parameters consistent with real ones, and one for the discriminator, enhancing its robustness by basing decisions on PSC attributes.

Jointly Understand Your Command and Intention:Reciprocal Co-Evolution between Scene-Aware 3D Human Motion Synthesis and Analysis

no code implementations1 Mar 2025 Xuehao Gao, Yang Yang, Shaoyi Du, Guo-Jun Qi, Junwei Han

As two intimate reciprocal tasks, scene-aware human motion synthesis and analysis require a joint understanding between multiple modalities, including 3D body motions, 3D scenes, and textual descriptions.

Diversity Motion Generation +1

Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models

1 code implementation13 Feb 2025 Yiheng Liu, Xiaohui Gao, Haiyang Sun, Bao Ge, Tianming Liu, Junwei Han, Xintao Hu

We use methods similar to those in the field of functional neuroimaging analysis to locate and identify functional networks in LLM.

LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding

no code implementations23 Dec 2024 Hao Li, Roy Qin, Zhengyu Zou, Diqi He, Bohan Li, Bingquan Dai, Dingewn Zhang, Junwei Han

To this end, we propose a Language-Embedded Surface Field (LangSurf), which accurately aligns the 3D language fields with the surface of objects, facilitating precise 2D and 3D segmentation with text query, widely expanding the downstream tasks such as removal and editing.

3D Semantic Segmentation Scene Understanding

Physics-Guided Detector for SAR Airplanes

1 code implementation19 Nov 2024 Zhongling Huang, Long Liu, Shuxin Yang, Zhirui Wang, Gong Cheng, Junwei Han

The main contributions of PGD include the physics-guided self-supervised learning, feature enhancement, and instance perception, denoted as PGSSL, PGFE, and PGIP, respectively.

 Ranked #1 on Object Detection on SAR-AIRcraft-1.0 (using extra training data)

Object Detection Self-Supervised Learning

DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes

no code implementations19 Nov 2024 Hao Li, Yuanyuan Gao, Haosong Peng, Chenming Wu, Weicai Ye, Yufeng Zhan, Chen Zhao, Dingwen Zhang, Jingdong Wang, Junwei Han

This paper presents DGTR, a novel distributed framework for efficient Gaussian reconstruction for sparse-view vast scenes.

Novel View Synthesis

Generative Artificial Intelligence Meets Synthetic Aperture Radar: A Survey

1 code implementation5 Nov 2024 Zhongling Huang, Xidan Zhang, Zuqian Tang, Feng Xu, Mihai Datcu, Junwei Han

To our best knowledge, this survey is the first exhaustive examination of the interdiscipline of SAR and GenAI, encompassing a wide range of topics, including deep neural networks, physical models, computer vision, and SAR images.

Survey

Brain-like Functional Organization within Large Language Models

no code implementations25 Oct 2024 Haiyang Sun, Lin Zhao, Zihao Wu, Xiaohui Gao, Yutao Hu, Mengfei Zuo, Wei zhang, Junwei Han, Tianming Liu, Xintao Hu

In this study, we bridge this gap by directly coupling sub-groups of artificial neurons with functional brain networks (FBNs), the foundational organizational structure of the human brain.

Mamba Capsule Routing Towards Part-Whole Relational Camouflaged Object Detection

1 code implementation5 Oct 2024 Dingwen Zhang, Liangbo Cheng, Yi Liu, Xinggang Wang, Junwei Han

These type-level mamba capsules are fed into the EM routing algorithm to get the high-layer mamba capsules, which greatly reduce the computation and parameters caused by the pixel-level capsule routing for part-whole relationships exploration.

Mamba object-detection +1

A Survey of Foundation Models for Music Understanding

no code implementations15 Sep 2024 Wenjun Li, Ying Cai, Ziyang Wu, Wenyi Zhang, Yifan Chen, Rundong Qi, Mengqi Dong, Peigen Chen, Xiao Dong, Fenghao Shi, Lei Guo, Junwei Han, Bao Ge, Tianming Liu, Lin Gan, Tuo Zhang

Music is essential in daily life, fulfilling emotional and entertainment needs, and connecting us personally, socially, and culturally.

Survey

Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement

1 code implementation11 Sep 2024 Xianmin Chen, Peiliang Huang, Xiaoxu Feng, Dingwen Zhang, Longfei Han, Junwei Han

Low-light image enhancement, particularly in cross-domain tasks such as mapping from the raw domain to the sRGB domain, remains a significant challenge.

Demosaicking Denoising +3

CONDA: Condensed Deep Association Learning for Co-Salient Object Detection

no code implementations2 Sep 2024 Long Li, Nian Liu, Dingwen Zhang, Zhongyu Li, Salman Khan, Rao Anwer, Hisham Cholakkal, Junwei Han, Fahad Shahbaz Khan

They directly rely on raw associations which are not reliable in complex scenarios, and their image feature optimization approach is not explicit for inter-image association modeling.

Co-Salient Object Detection object-detection +2

X-Fake: Juggling Utility Evaluation and Explanation of Simulated SAR Images

no code implementations28 Jul 2024 Zhongling Huang, Yihan Zhuang, Zipei Zhong, Feng Xu, Gong Cheng, Junwei Han

The distribution inconsistency between real and simulated data is the main obstacle that influences the utility of simulated SAR images.

counterfactual Counterfactual Explanation +1

VDG: Vision-Only Dynamic Gaussian for Driving Simulation

no code implementations26 Jun 2024 Hao Li, Jingfeng Li, Dingwen Zhang, Chenming Wu, Jieqi Shi, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Junwei Han

Dynamic Gaussian splatting has led to impressive scene reconstruction and image synthesis advances in novel views.

Image Generation

Center-Sensitive Kernel Optimization for Efficient On-Device Incremental Learning

no code implementations13 Jun 2024 Dingwen Zhang, Yan Li, De Cheng, Nannan Wang, Junwei Han

Based on an empirical study on the knowledge intensity of the kernel elements of the neural network, we find that the center kernel is the key for maximizing the knowledge intensity for learning new data, while freezing the other kernel elements would get a good balance on the model's capacity for overcoming catastrophic forgetting.

Incremental Learning

Hyper-Transformer for Amodal Completion

no code implementations30 May 2024 Jianxiong Gao, Xuelin Qian, Longfei Liang, Junwei Han, Yanwei Fu

The multi-scale features from the image branch guide the hyper transformer in learning shape priors and in generating the weights for dynamic convolution tailored to each instance.

Auto-selected Knowledge Adapters for Lifelong Person Re-identification

no code implementations29 May 2024 Xuelin Qian, Ruiqi Wu, Gong Cheng, Junwei Han

On the one hand, the appropriate adapters are selected for the inputs to process ReID, and on the other hand, the knowledge interaction and fusion between adapters are enhanced to improve the generalization ability of the model.

Lifelong learning Person Re-Identification

Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports

no code implementations23 May 2024 Guangyu Guo, Jiawen Yao, Yingda Xia, Tony C. W. Mok, Zhilin Zheng, Junwei Han, Le Lu, Dingwen Zhang, Jian Zhou, Ling Zhang

The absence of adequately sufficient expert-level tumor annotations hinders the effectiveness of supervised learning based opportunistic cancer screening on medical imaging.

Clinical Knowledge Descriptive +3

Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentation

1 code implementation22 May 2024 Dingwen Zhang, Hao Li, Diqi He, Nian Liu, Lechao Cheng, Jingdong Wang, Junwei Han

Experimental evaluations conducted on MS COCO, Cityscapes, and CTW1500 datasets indicate that the QEIS models' performance can be significantly improved when pre-trained with our method.

Instance Segmentation Semantic Segmentation +1

GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time

no code implementations15 Mar 2024 Hao Li, Yuanyuan Gao, Chenming Wu, Dingwen Zhang, Yalun Dai, Chen Zhao, Haocheng Feng, Errui Ding, Jingdong Wang, Junwei Han

Specifically, we design a novel joint learning framework that consists of an Iterative Pose Optimization Network (IPO-Net) and a Generalizable 3D-Gaussians (G-3DG) model.

Generalizable Novel View Synthesis NeRF +1

Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure

1 code implementation12 Mar 2024 De Cheng, Yanling Ji, Dong Gong, Yan Li, Nannan Wang, Junwei Han, Dingwen Zhang

It considers the characteristics of the image restoration task with multiple degenerations in continual learning, and the knowledge for different degenerations can be shared and accumulated in the unified network structure.

All Continual Learning +3

VST++: Efficient and Stronger Visual Saliency Transformer

no code implementations18 Oct 2023 Nian Liu, Ziyang Luo, Ni Zhang, Junwei Han

Our previous work, the Visual Saliency Transformer (VST), addressed this constraint from a transformer-based sequence-to-sequence perspective, to unify RGB and RGB-D SOD.

object-detection Object Detection +1

Physics Inspired Hybrid Attention for SAR Target Recognition

1 code implementation27 Sep 2023 Zhongling Huang, Chong Wu, Xiwen Yao, Zhicheng Zhao, Xiankai Huang, Junwei Han

There has been a recent emphasis on integrating physical models and deep neural networks (DNNs) for SAR target recognition, to improve performance and achieve a higher level of physical interpretability.

Feature Importance

Chat2Brain: A Method for Mapping Open-Ended Semantic Queries to Brain Activation Maps

no code implementations10 Sep 2023 Yaonai Wei, Tuo Zhang, Han Zhang, Tianyang Zhong, Lin Zhao, Zhengliang Liu, Chong Ma, Songyao Zhang, Muheng Shang, Lei Du, Xiao Li, Tianming Liu, Junwei Han

In this study, we propose a method called Chat2Brain that combines LLMs to basic text-2-image model, known as Text2Brain, to map open-ended semantic queries to brain activation maps in data-scarce and complex query environments.

Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning

1 code implementation ICCV 2023 Xiang Yuan, Gong Cheng, Kebing Yan, Qinghua Zeng, Junwei Han

The past few years have witnessed the immense success of object detection, while current excellent detectors struggle on tackling size-limited instances.

Contrastive Learning Imitation Learning +3

Discriminative Co-Saliency and Background Mining Transformer for Co-Salient Object Detection

1 code implementation CVPR 2023 Long Li, Junwei Han, Ni Zhang, Nian Liu, Salman Khan, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan

Then, we use two types of pre-defined tokens to mine co-saliency and background information via our proposed contrast-induced pixel-to-token correlation and co-saliency token-to-token correlation modules.

Computational Efficiency Co-Salient Object Detection +3

ChatABL: Abductive Learning via Natural Language Interaction with ChatGPT

no code implementations21 Apr 2023 Tianyang Zhong, Yaonai Wei, Li Yang, Zihao Wu, Zhengliang Liu, Xiaozheng Wei, Wenjun Li, Junjie Yao, Chong Ma, Xiang Li, Dajiang Zhu, Xi Jiang, Junwei Han, Dinggang Shen, Tianming Liu, Tuo Zhang

The proposed method uses the strengths of LLMs' understanding and logical reasoning to correct the incomplete logical facts for optimizing the performance of perceptual module, by summarizing and reorganizing reasoning rules represented in natural language format.

Decipherment Logical Reasoning

Threatening Patch Attacks on Object Detection in Optical Remote Sensing Images

1 code implementation13 Feb 2023 Xuxiang Sun, Gong Cheng, Lei Pei, Hongda Li, Junwei Han

Advanced Patch Attacks (PAs) on object detection in natural images have pointed out the great safety vulnerability in methods based on deep neural networks.

Adversarial Attack Object +2

Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt

no code implementations CVPR 2023 Hao Li, Dingwen Zhang, Nian Liu, Lechao Cheng, Yalun Dai, Chao Zhang, Xinggang Wang, Junwei Han

Inspired by the recent success of the Prompting technique, we introduce a new pre-training method that boosts QEIS models by giving Saliency Prompt for queries/kernels.

Instance Segmentation Semantic Segmentation +1

Fewer is More: Efficient Object Detection in Large Aerial Images

1 code implementation26 Dec 2022 Xingxing Xie, Gong Cheng, Qingyang Li, Shicheng Miao, Ke Li, Junwei Han

Current mainstream object detection methods for large aerial images usually divide large images into patches and then exhaustively detect the objects of interest on all patches, no matter whether there exist objects or not.

4k Object +2

Progressively Dual Prior Guided Few-shot Semantic Segmentation

no code implementations20 Nov 2022 Qinglong Cao, Yuntian Chen, Xiwen Yao, Junwei Han

Few-shot semantic segmentation task aims at performing segmentation in query images with a few annotated support samples.

Few-Shot Semantic Segmentation Segmentation +1

Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentation

1 code implementation13 Oct 2022 Yuanwei Liu, Nian Liu, Xiwen Yao, Junwei Han

To solve this problem, we are the first to introduce an intermediate prototype for mining both deterministic category information from the support and adaptive category knowledge from the query.

Few-Shot Semantic Segmentation Semantic Segmentation

Towards Large-Scale Small Object Detection: Survey and Benchmarks

no code implementations28 Jul 2022 Gong Cheng, Xiang Yuan, Xiwen Yao, Kebing Yan, Qinghua Zeng, Xingxing Xie, Junwei Han

Then, to catalyze the development of SOD, we construct two large-scale Small Object Detection dAtasets (SODA), SODA-D and SODA-A, which focus on the Driving and Aerial scenarios respectively.

Benchmarking Object +3

Brain Cortical Functional Gradients Predict Cortical Folding Patterns via Attention Mesh Convolution

no code implementations21 May 2022 Li Yang, Zhibin He, Changhe Li, Junwei Han, Dajiang Zhu, Tianming Liu, Tuo Zhang

The convolution on mesh considers the spatial organization of functional gradients and folding patterns on a cortical sheet and the newly designed channel attention block enhances the interpretability of the contribution of different functional gradients to cortical folding prediction.

Anatomy Functional Connectivity

Structured Attention Composition for Temporal Action Localization

2 code implementations20 May 2022 Le Yang, Junwei Han, Tao Zhao, Nian Liu, Dingwen Zhang

To tackle this issue, we make an early effort to study temporal action localization from the perspective of multi-modality feature learning, based on the observation that different actions exhibit specific preferences to appearance or motion modality.

Action Detection Temporal Action Localization

Learning Non-target Knowledge for Few-shot Semantic Segmentation

1 code implementation CVPR 2022 Yuanwei Liu, Nian Liu, Qinglong Cao, Xiwen Yao, Junwei Han, Ling Shao

Then, a BG Eliminating Module and a DO Eliminating Module are proposed to successively filter out the BG and DO information from the query feature, based on which we can obtain a BG and DO-free target object segmentation result.

Contrastive Learning Few-Shot Semantic Segmentation +3

Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation

1 code implementation21 Apr 2022 Chunbo Lang, Binfei Tu, Gong Cheng, Junwei Han

Few-shot segmentation, which aims to segment unseen-class objects given only a handful of densely labeled samples, has received widespread attention from the community.

Decoder Few-Shot Semantic Segmentation +3

Cross-Modality High-Frequency Transformer for MR Image Super-Resolution

no code implementations29 Mar 2022 Chaowei Fang, Dingwen Zhang, Liang Wang, Yulun Zhang, Lechao Cheng, Junwei Han

Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis.

Image Super-Resolution Vocal Bursts Intensity Prediction

Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation

1 code implementation19 Mar 2022 Junwen Pan, Pengfei Zhu, Kaihua Zhang, Bing Cao, Yu Wang, Dingwen Zhang, Junwei Han, QinGhua Hu

Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention recently.

Pseudo Label Segmentation +3

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

1 code implementation CVPR 2022 Chunbo Lang, Gong Cheng, Binfei Tu, Junwei Han

Specifically, we apply an additional branch (base learner) to the conventional FSS model (meta learner) to explicitly identify the targets of base classes, i. e., the regions that do not need to be segmented.

Few-Shot Semantic Segmentation Meta-Learning +1

Colar: Effective and Efficient Online Action Detection by Consulting Exemplars

1 code implementation CVPR 2022 Le Yang, Junwei Han, Dingwen Zhang

Based on the exemplar-consultation mechanism, the long-term dependencies can be captured by regarding historical frames as exemplars, while the category-level modeling can be achieved by regarding representative frames from a category as exemplars.

Online Action Detection

Adaptive neighborhood Metric learning

no code implementations20 Jan 2022 Kun Song, Junwei Han, Gong Cheng, Jiwen Lu, Feiping Nie

In this paper, we reveal that metric learning would suffer from serious inseparable problem if without informative sample mining.

Metric Learning Triplet

Cross-Modality Deep Feature Learning for Brain Tumor Segmentation

no code implementations7 Jan 2022 Dingwen Zhang, Guohai Huang, Qiang Zhang, Jungong Han, Junwei Han, Yizhou Yu

Recent advances in machine learning and prevalence of digital medical images have opened up an opportunity to address the challenging brain tumor segmentation (BTS) task by using deep convolutional neural networks.

Brain Tumor Segmentation Segmentation +1

Exploring Effective Data for Surrogate Training Towards Black-Box Attack

1 code implementation CVPR 2022 Xuxiang Sun, Gong Cheng, Hongda Li, Lei Pei, Junwei Han

Finally, in accordance with the in-depth observations for the methods based on proxy data, we argue that leveraging the proxy data is still an effective way for surrogate training.

Adversarial Attack Diversity

Robust Region Feature Synthesizer for Zero-Shot Object Detection

1 code implementation CVPR 2022 Peiliang Huang, Junwei Han, De Cheng, Dingwen Zhang

Zero-shot object detection aims at incorporating class semantic vectors to realize the detection of (both seen and) unseen classes given an unconstrained test image.

Generalized Zero-Shot Object Detection Object +2

Weakly Supervised Rotation-Invariant Aerial Object Detection Network

1 code implementation CVPR 2022 Xiaoxu Feng, Xiwen Yao, Gong Cheng, Junwei Han

Object rotation is among long-standing, yet still unexplored, hard issues encountered in the task of weakly supervised object detection (WSOD) from aerial images.

Object object-detection +1

Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis

no code implementations CVPR 2022 Chaowei Fang, Liang Wang, Dingwen Zhang, Jun Xu, Yixuan Yuan, Junwei Han

Under this circumstance, the models learned from different views can distill valuable knowledge to guide the learning processes of each other.

Self-Supervised Learning

Pixel Distillation: A New Knowledge Distillation Scheme for Low-Resolution Image Recognition

1 code implementation17 Dec 2021 Guangyu Guo, Dingwen Zhang, Longfei Han, Nian Liu, Ming-Ming Cheng, Junwei Han

Then, a Teacher-Assistant-Student (TAS) framework is further established to disentangle pixel distillation into the model compression stage and input compression stage, which significantly reduces the overall complexity of pixel distillation and the difficulty of distilling intermediate knowledge.

Image Classification Knowledge Distillation +5

Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching

no code implementations17 Dec 2021 Dingwen Zhang, Wenyuan Zeng, Guangyu Guo, Chaowei Fang, Lechao Cheng, Ming-Ming Cheng, Junwei Han

Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model.

Knowledge Distillation Weakly supervised Semantic Segmentation +1

Background-Click Supervision for Temporal Action Localization

1 code implementation24 Nov 2021 Le Yang, Junwei Han, Tao Zhao, Tianwei Lin, Dingwen Zhang, Jianxin Chen

Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion.

Position Weakly-supervised Temporal Action Localization +1

Physically Explainable CNN for SAR Image Classification

1 code implementation27 Oct 2021 Zhongling Huang, Xiwen Yao, Ying Liu, Corneliu Octavian Dumitru, Mihai Datcu, Junwei Han

In this paper, we first propose a novel physically explainable convolutional neural network for SAR image classification, namely physics guided and injected learning (PGIL).

Classification Explainable Models +1

Anchor-free Oriented Proposal Generator for Object Detection

1 code implementation5 Oct 2021 Gong Cheng, Jiabao Wang, Ke Li, Xingxing Xie, Chunbo Lang, Yanqing Yao, Junwei Han

Nowadays, oriented detectors mostly use horizontal boxes as intermedium to derive oriented boxes from them.

Object object-detection +2

Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance

1 code implementation2 Oct 2021 Nian Liu, Wangbo Zhao, Dingwen Zhang, Junwei Han, Ling Shao

On the other hand, instead of processing the twokinds of data separately, we build a novel dual graph modelto guide the focal stack fusion process using all-focus pat-terns.

Graph Learning Saliency Detection

Summarize and Search: Learning Consensus-aware Dynamic Convolution for Co-Saliency Detection

1 code implementation ICCV 2021 Ni Zhang, Junwei Han, Nian Liu, Ling Shao

In this paper, we propose a novel consensus-aware dynamic convolution model to explicitly and effectively perform the "summarize and search" process.

Co-Salient Object Detection

Oriented R-CNN for Object Detection

5 code implementations ICCV 2021 Xingxing Xie, Gong Cheng, Jiabao Wang, Xiwen Yao, Junwei Han

Current state-of-the-art two-stage detectors generate oriented proposals through time-consuming schemes.

Ranked #14 on Object Detection In Aerial Images on DOTA (using extra training data)

Object object-detection +3

Instance-Level Relative Saliency Ranking with Graph Reasoning

no code implementations8 Jul 2021 Nian Liu, Long Li, Wangbo Zhao, Junwei Han, Ling Shao

Conventional salient object detection models cannot differentiate the importance of different salient objects.

Image Retargeting object-detection +2

Strengthen Learning Tolerance for Weakly Supervised Object Localization

1 code implementation CVPR 2021 Guangyu Guo, Junwei Han, Fang Wan, Dingwen Zhang

Weakly supervised object localization (WSOL) aims at learning to localize objects of interest by only using the image-level labels as the supervision.

Object Weakly-Supervised Object Localization

Large-scale Unsupervised Semantic Segmentation

3 code implementations6 Jun 2021 ShangHua Gao, Zhong-Yu Li, Ming-Hsuan Yang, Ming-Ming Cheng, Junwei Han, Philip Torr

In this work, we propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to help the research progress.

Diversity Representation Learning +2

Visual Saliency Transformer

2 code implementations ICCV 2021 Nian Liu, Ni Zhang, Kaiyuan Wan, Ling Shao, Junwei Han

We also develop a token-based multi-task decoder to simultaneously perform saliency and boundary detection by introducing task-related tokens and a novel patch-task-attention mechanism.

Boundary Detection Decoder +5

Weakly Supervised Object Localization and Detection: A Survey

no code implementations16 Apr 2021 Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang

As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade.

Object Survey +1

Weakly Supervised Video Salient Object Detection

1 code implementation CVPR 2021 Wangbo Zhao, Jing Zhang, Long Li, Nick Barnes, Nian Liu, Junwei Han

Significant performance improvement has been achieved for fully-supervised video salient object detection with the pixel-wise labeled training datasets, which are time-consuming and expensive to obtain.

Object object-detection +4

Densely Nested Top-Down Flows for Salient Object Detection

1 code implementation18 Feb 2021 Chaowei Fang, HaiBin Tian, Dingwen Zhang, Qiang Zhang, Jungong Han, Junwei Han

To this end, this paper revisits the role of top-down modeling in salient object detection and designs a novel densely nested top-down flows (DNTDF)-based framework.

Object object-detection +2

Learning Dual Priors for JPEG Compression Artifacts Removal

no code implementations ICCV 2021 Xueyang Fu, Xi Wang, Aiping Liu, Junwei Han, Zheng-Jun Zha

Specifically, we design a variational model to formulate the image de-blocking problem and propose two prior terms for the image content and gradient, respectively.

Blocking

Learning Selective Mutual Attention and Contrast for RGB-D Saliency Detection

1 code implementation12 Oct 2020 Nian Liu, Ni Zhang, Ling Shao, Junwei Han

Early fusion and the result fusion schemes fuse RGB and depth information at the input and output stages, respectively, hence incur the problem of distribution gap or information loss.

object-detection RGB-D Salient Object Detection +2

Revisiting Anchor Mechanisms for Temporal Action Localization

1 code implementation22 Aug 2020 Le Yang, Houwen Peng, Dingwen Zhang, Jianlong Fu, Junwei Han

To address this problem, this paper proposes a novel anchor-free action localization module that assists action localization by temporal points.

Temporal Action Localization

Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization

no code implementations18 Aug 2020 Tao Zhao, Junwei Han, Le Yang, Dingwen Zhang

The existing methods can be categorized into two localization-by-classification pipelines, i. e., the pre-classification pipeline and the post-classification pipeline.

Classification General Classification +2

Embedded Deep Bilinear Interactive Information and Selective Fusion for Multi-view Learning

no code implementations13 Jul 2020 Jinglin Xu, Wenbin Li, Jiantao Shen, Xinwang Liu, Peicheng Zhou, Xiangsen Zhang, Xiwen Yao, Junwei Han

That is, we seamlessly embed various intra-view information, cross-view multi-dimension bilinear interactive information, and a new view ensemble mechanism into a unified framework to make a decision via the optimization.

Classification General Classification +1

Bifurcated backbone strategy for RGB-D salient object detection

2 code implementations6 Jul 2020 Yingjie Zhai, Deng-Ping Fan, Jufeng Yang, Ali Borji, Ling Shao, Junwei Han, Liang Wang

In particular, first, we propose to regroup the multi-level features into teacher and student features using a bifurcated backbone strategy (BBS).

Object object-detection +3

Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities

no code implementations3 May 2020 Gong Cheng, Xingxing Xie, Junwei Han, Lei Guo, Gui-Song Xia

Considering the rapid evolution of this field, this paper provides a systematic survey of deep learning methods for remote sensing image scene classification by covering more than 160 papers.

Classification Deep Learning +4

Object Detection in Optical Remote Sensing Images: A Survey and A New Benchmark

1 code implementation31 Aug 2019 Ke Li, Gang Wan, Gong Cheng, Liqiu Meng, Junwei Han

However, the current survey of datasets and deep learning based methods for object detection in optical remote sensing images is not adequate.

Deep Learning Diversity +4

Robust and Efficient Fuzzy C-Means Clustering Constrained on Flexible Sparsity

no code implementations19 Aug 2019 Jinglin Xu, Junwei Han, Mingliang Xu, Feiping Nie, Xuelong. Li

Clustering is an effective technique in data mining to group a set of objects in terms of some attributes.

Clustering

PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection

2 code implementations15 Dec 2018 Nian Liu, Junwei Han, Ming-Hsuan Yang

We propose three specific formulations of the PiCANet via embedding the pixel-wise contextual attention mechanism into the pooling and convolution operations with attending to global or local contexts.

object-detection RGB Salient Object Detection +3

Reinforcement Cutting-Agent Learning for Video Object Segmentation

no code implementations CVPR 2018 Junwei Han, Le Yang, Dingwen Zhang, Xiaojun Chang, Xiaodan Liang

In this paper, we formulate this problem as a Markov Decision Process, where agents are learned to segment object regions under a deep reinforcement learning framework.

Decision Making Deep Reinforcement Learning +6

Supervision by Fusion: Towards Unsupervised Learning of Deep Salient Object Detector

no code implementations ICCV 2017 Dingwen Zhang, Junwei Han, Yu Zhang

Based on this insight, we combine an intra-image fusion stream and a inter-image fusion stream in the proposed framework to generate the learning curriculum and pseudo ground-truth for supervising the training of the deep salient object detector.

Object object-detection +2

SPFTN: A Self-Paced Fine-Tuning Network for Segmenting Objects in Weakly Labelled Videos

no code implementations CVPR 2017 Dingwen Zhang, Le Yang, Deyu Meng, Dong Xu, Junwei Han

Object segmentation in weakly labelled videos is an interesting yet challenging task, which aims at learning to perform category-specific video object segmentation by only using video-level tags.

Object Semantic Segmentation +3

Learning Category-Specific 3D Shape Models From Weakly Labeled 2D Images

no code implementations CVPR 2017 Dingwen Zhang, Junwei Han, Yang Yang, Dong Huang

Recently, researchers have made great processes to build category-specific 3D shape models from 2D images with manual annotations consisting of class labels, keypoints, and ground truth figure-ground segmentations.

3D Shape Reconstruction Segmentation +2

Remote Sensing Image Scene Classification: Benchmark and State of the Art

4 code implementations1 Mar 2017 Gong Cheng, Junwei Han, Xiaoqiang Lu

During the past years, significant efforts have been made to develop various datasets or present a variety of approaches for scene classification from remote sensing images.

Classification Diversity +2

A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection

2 code implementations6 Oct 2016 Nian Liu, Junwei Han

Furthermore, the proposed DSCLSTM model can significantly boost the saliency detection performance by incorporating both global spatial interconnections and scene context modulation, which may uncover novel inspirations for studies on them in computational saliency models.

Saliency Detection

Discriminatively Embedded K-Means for Multi-View Clustering

no code implementations CVPR 2016 Jinglin Xu, Junwei Han, Feiping Nie

In real world applications, more and more data, for example, image/video data, are high dimensional and represented by multiple views which describe different perspectives of the data.

Clustering

RIFD-CNN: Rotation-Invariant and Fisher Discriminative Convolutional Neural Networks for Object Detection

no code implementations CVPR 2016 Gong Cheng, Peicheng Zhou, Junwei Han

This is achieved by introducing and learning a rotation-invariant layer and a Fisher discriminative layer, respectively, on the basis of the existing high-capacity CNN architectures.

Object object-detection +1

Object Co-Segmentation via Graph Optimized-Flexible Manifold Ranking

no code implementations CVPR 2016 Rong Quan, Junwei Han, Dingwen Zhang, Feiping Nie

Aiming at automatically discovering the common objects contained in a set of relevant images and segmenting them as foreground simultaneously, object co-segmentation has become an active research topic in recent years.

Object Segmentation

DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection

no code implementations CVPR 2016 Nian Liu, Junwei Han

Then a novel hierarchical recurrent convolutional neural network (HRCNN) is adopted to further hierarchically and progressively refine the details of saliency maps step by step via integrating local context information.

Ranked #18 on RGB Salient Object Detection on DUTS-TE (max F-measure metric)

Object object-detection +2

Learning Coarse-to-Fine Sparselets for Efficient Object Detection and Scene Classification

no code implementations CVPR 2015 Gong Cheng, Junwei Han, Lei Guo, Tianming Liu

Part model-based methods have been successfully applied to object detection and scene classification and have achieved state-of-the-art results.

General Classification object-detection +2

Predicting Eye Fixations Using Convolutional Neural Networks

no code implementations CVPR 2015 Nian Liu, Junwei Han, Dingwen Zhang, Shifeng Wen, Tianming Liu

It is believed that eye movements in free-viewing of natural scenes are directed by both bottom-up visual saliency and top-down visual factors.

Co-Saliency Detection via Looking Deep and Wide

no code implementations CVPR 2015 Dingwen Zhang, Junwei Han, Chao Li, Jingdong Wang

In the proposed framework, the wide and deep information are explored for the object proposal windows extracted in each image, and the co-saliency scores are calculated by integrating the intra-image contrast and intra group consistency via a principled Bayesian formulation.

Co-Salient Object Detection Image Retrieval +1

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