Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks184 from public data
- A Transformer-Based Approach Combining Deep Learning Network and Spatial-Temporal Information for Raw EEG Classification314
This work designed Transformer-based models for classifications of motor imagery EEG based on the PhysioNet dataset and revealed a pattern of event-related desynchronization (ERD) which was consistent with the results from the spectral analysis of Mu and beta rhythm over the sensorimotor areas.
- Mask-Guided Attention Network for Occluded Pedestrian Detection223
A novel mask-guided attention network is introduced that emphasizes on visible pedestrian regions while suppressing the occluded ones by modulating full body features and it is empirically demonstrated that coarse-level segmentation annotations provide reasonable approximation to their dense pixel-wise counterparts.
- 209
- From Handcrafted to Deep Features for Pedestrian Detection: A Survey160
An extensive review of single-spectral pedestrian detection that includes handcrafted features based methods and deep features based approaches is presented and it is found that hand crafted features with large freedom degrees in shape and space have better performance.
- 157
- MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation146
A novel lightweight network using a multi-scale context fusion (MSCFNet) scheme, which explores an asymmetric encoder-decoder architecture to alleviate the trade-off between accuracy, inference speed, and model size.
- 139
- 138
- From handcrafted to learned representations for human action recognition: A survey136
This work provides a detailed overview of recent advancements in human action representations and provides comprehensive analysis and comparisons between learning-based and handcrafted action representations respectively, so as to inspire action recognition researchers towards the study of both kinds of representation techniques.
- SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network132
A semi-supervised semantic point cloud segmentation network, named SSPC-Net, where the labels of unlabeled points are inferred from the few annotated 3D points and the pseudo labels of the unsupervised superpoints are generated.
- 122
- Spectral Clustering by Joint Spectral Embedding and Spectral Rotation111
This paper proposes a joint model to simultaneously compute the optimal real matrix and binary matrix which is an orthonormal matrix for spectral clustering and demonstrates the effectiveness of the proposed method on benchmark datasets.
- 106
- 89
- PSTR: End-to-End One-Step Person Search With Transformers88
The proposed PSTR is the first to propose an end-to-end one-step transformer-based person search framework that jointly performs person detection and re-identification (re-id) in a single architecture and sets a new state-of-the-art on both benchmarks.
- 88
- 86
- Progressive Point Cloud Deconvolution Generation Network84
An effective point cloud generation method that can generate multi-resolution point clouds of the same shape from a latent vector is proposed and a shape-preserving adversarial loss is proposed to train the point cloud deconvolution generation network.
- 76
- Learning Cross-Domain Neural Networks for Sketch-Based 3D Shape Retrieval75
Experimental results suggest that both CDNN and PCDNN can outperform state-of-the-art performance, where PCdNN can further improve CDNN when employing a hierarchical structure.
- 74
- 74
- Deep Correlated Metric Learning for Sketch-based 3D Shape Retrieval73
A novel deep correlated metric learning (DCML) method to mitigate the discrepancy between sketch and 3D shape domains is proposed and the experimental results demonstrate the superiority of the proposed method over the state-of-the-art methods.
- 71
- 70
- PSC-Net: learning part spatial co-occurrence for occluded pedestrian detection61
The proposed PSC-Net contains a dedicated module that is designed to explicitly capture both inter and intra-part co-occurrence information of different pedestrian body parts through a graph convolutional network (GCN).
- Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration58
By modeling the point cloud registration task as a Markov decision process, an end-to-end deep model embedded with the cross-entropy method (CEM) for unsupervised 3D registration is proposed and a Geman-McClure estimator based loss is formulated to train the end- to-end registration model.
- Constructing multilayer locality-constrained matrix regression framework for noise robust face super-resolution58
An efficient multilayer locality-constrained matrix regression (MLCMR) framework to learn the representation of the input LR patch and meanwhile preserve the manifold of the original HR space and aims at reducing the inconsistency gap between different manifolds.
- 56
- 51
- 51
- 49
- Effective texture classification by texton encoding induced statistical features49
Experimental results on the CUReT, KTH_TIPS and UIUC datasets demonstrated that the proposed texton learning and encoding scheme is very promising, especially when the number of available training samples is limited.
- Siamese CNN-BiLSTM Architecture for 3D Shape Representation Learning48
A siamese CNN-BiLSTM network for 3D shape representation learning, which minimizes a discriminative loss function to learn a deep nonlinear transformation, mapping 3D shapes from the original space into a nonlinear feature space.
- 47
- Self-Supervised 3D Scene Flow Estimation Guided by Superpoints46
An iterative end-to-end super point based scene flow estimation framework, where the superpoints can be dynamically updated to guide the point-level flow prediction, and which can achieve promising performance on several different datasets.
- 46
- Cross-Modal Local Calibration and Global Context Modeling Network for RGB–Infrared Remote-Sensing Object Detection43
The experimental results on popular RGB–infrared remote-sensing object detection datasets, namely DRoneVehicle and VEDAI, demonstrate the effectiveness and efficiency of the proposed cross-modal local calibration and global context modeling network.
- SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering40
A self-supervised point cloud upsampling network (SSPU-Net) to generate dense point clouds without using ground truth to exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images.
- Count- and Similarity-Aware R-CNN for Pedestrian Detection35
A count-weighted detection loss function that assigns higher weights to the detection errors occurring at highly overlapping pedestrians, and a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity to identify distinct proposals.
- 32
- 31
- Attentive Alignment Network for Multispectral Pedestrian Detection30
An attentive alignment network, consisting of an attentive position alignment (APA) module and an attentive modality alignment (AMA) module, is proposed, which surpasses the current state-of-the-art performance on both datasets.
- 29
- Learning a Dynamic Cross-Modal Network for Multispectral Pedestrian Detection28
This work introduces a multispectral pedestrian detection framework that comprises a novel dynamic cross-modal network (DCMNet), which strives to adaptively utilize the local and non-local complementary information between multi- modal features.
- Image decomposition based matrix regression with applications to robust face recognition27
This work aims to simplify the complex images and propose a simple and robust matrix regression based classification model, called ID-NMR, which performs favorably compared with state-of-the-art regression based Classification methods.
- 26
- Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation25
The proposed network aims to build the long-range dependencies of point clouds for the accurate segmentation with a novel cascaded non-local module, which consists of the neighborhood-level, superpoint-level and global-level non- local blocks.
- 25
- 23
- Action Candidate Based Clipped Double Q-learning for Discrete and Continuous Action Tasks23
This paper proposes an action candidate based clipped double estimator for Double Q-learning and proves that the algorithm can more accurately estimate the maximum expected action value on some toy environments and yield good performance on several benchmark problems.
- Metric-based Generative Adversarial Network23
This paper proposes a novel metric-based generative adversarial network (MBGAN), which uses the distance-criteria to distinguish between real and fake samples, and adopts a triplet structure and learns a deep nonlinear transformation.
- Remote Sensing Image Dehazing via a Local Context-Enriched Transformer22
A CNN-based adaptive local context enrichment module (ALCEM) to extract contextual information within local regions and a novel Transformer-based dehazing network termed LCEFormer is proposed, which combines the advantages of CNN and Transformer.
- CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation21
A simple encoder-decoder network, called CLIP-VIS, to adapt CLIP for open-vocabulary video instance segmentation, which adopts frozen CLIP and introduces three modules, including class-agnostic mask generation, temporal topK-enhanced matching, and weighted open-vocabulary classification.
- 21
- A Study of Hand Back Skin Texture Patterns for Personal Identification and Gender Classification21
The results show that HBST can be used to assist human identification and gender classification and an efficient texton learning based method is presented.
- Learning Adversarial 3D Model Generation With 2D Image Enhancer20
A novel GAN-based deep neural network that can not only generate high-quality 3D models, but also successfully learn discriminative shape representation for classification and retrieval without supervision is developed.
- Context and detail interaction network for stereo rain streak and raindrop removal19
A general coarse-to-fine deraining framework for stereo rain streak and raindrop removal, called CDINet, comprising a stereo rain removal subnet and a stereo detail recovery subnet to restore images progressively and demonstrates that this method sets new state-of-the-art deraining performance in terms of both quantitative and qualitative metrics with faster speed.
- 17
- 17
- 16
- 16
- Identifying Visual Attention Features Accurately Discerning Between Autism and Typically Developing: a Deep Learning Framework15
A new systematic framework combining high accuracy deep learning classification, deep learning segmentation, image ablation and a direct measurement of classification ability to identify the discriminative features for autism identification is developed.
- 14
- Heat Diffusion Long-Short Term Memory Learning for 3D Shape Analysis14
This work addresses the temporal dynamics of heat flows on 3D shapes using the long-short term memory (LSTM) to guide 3D shape descriptors toward discriminative representations by feeding heat distributions throughout time as inputs to units of heat diffusion LSTM (HD-L STM) blocks with a supervised learning structure.
- Transformer-Based Stereo-Aware 3D Object Detection From Binocular Images13
This paper presents TS3D, a Transformer-based Stereo-aware 3D object detector, and proposes a Stereo Preserving Feature Pyramid Network (SPFPN), designed to preserve the correspondence information while fusing intra-scale and aggregating cross-scale stereo features.
- 13
- 13
- Transfer Vision Patterns for Multi-Task Pixel Learning13
A multi-task vision pattern transformation (VPT) method to adaptively correlate and transfer cross-task visual patterns by leveraging the powerful transformer mechanism and achieves the state-of-that-art performance in three pixel-level visual tasks.
- C2BG-Net: Cross-modality and cross-scale balance network with global semantics for multi-modal 3D object detection12
A cross-modality balance network (CMN) and a cross-scale balance network (CSN) are proposed that incorporate cross-modality attention mechanisms and introduces an auxiliary 2D detection head to balance the significance of both modalities.
- UnDeepLIO: Unsupervised Deep Lidar-Inertial Odometry12
This paper designs a novel framework for unsupervised lidar odometry with the IMU, which is never used in other deep methods and achieves comparable performances against other state-of-the-art methods.
- 10
- Complementary Feature Pyramid Network for Object Detection10
A Spatial Complementary Module (SCM) and a Channel Complementaries Module (CCM) are designed and embedded in CFPN to enhance useful information and suppress irrelevant information during feature fusions along spatial and channel dimensions, respectively.
- 10
- 10
- Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder10
A novel learning paradigm for extracting a concise data-driven shape descriptor to address challenging issues posed by structural deformation variations and noise present in 3D models and is robust to large deformations.
- 9
- 9
- 9
- 9
- 9
- 9
- Structure-Aware 3D Shape Synthesis from Single-View Images.9
This work aims to address above restrictions by proposing an improved 3D shape synthesis method that relies on a single input image and can achieve the state-of-the-art performance on the ShapeNet datasets.
- 9
- 8
- 8
- 8
- 7
- Human-in-the-loop image segmentation and annotation7
A human-in-theloop segmentation (HISE) framework is proposed, which is combined with a classic semantic segmentation model, i.e., FCN, and experimental results show that HISE can achieve comparable performance with much fewer human annotations and output a seg-
- Learning to Synthesize 3D Indoor Scenes from Monocular Images7
This work considers the scenarios where depth images are not available in the testing data, and proposes to learn a convolutional long short-term memory (Conv LSTM) network and a regressionconvolutional neural network (regression ConvNet) using only monocular RGB images.
- 7
- 6
- 6
- 6
- 6
- 6
- 5
- Multispectral remote sensing object detection via selective cross-modal interaction and aggregation5
This work proposes a novel framework, termed Selective cross-modal Interaction and Aggregation (SIA), which comprises two key components: the Selective Cross-modal Interaction (SCI) module and the Selective Feature Aggregation (SFA) module, which addresses the inefficiency of traditional cross-modal attention mechanisms by selectively prioritizing the most informative long-range dependencies.
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Image Restoration Based on PDEs and a Non-local Algorithm1
Experiments show that this method using the NL algorithm can improve the performance efficiently and significantly, and the proposed algorithm can take advantage of all the possible self-predictions provided by the image.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-16. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.