Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks366 from public data
- 1,930
- 1,104
- HRank: Filter Pruning Using High-Rank Feature Map922
This paper proposes a novel filter pruning method by exploring the High Rank of feature maps (HRank), inspired by the discovery that the average rank of multiple feature maps generated by a single filter is always the same, regardless of the number of image batches CNNs receive.
- 647
- Towards Optimal Structured CNN Pruning via Generative Adversarial Learning585
This paper proposes an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner and effectively solves the optimization problem by generative adversarial learning (GAL), which learns a sparse soft mask in a label-free and an end to end manner.
- Implicit Diffusion Models for Continuous Super-Resolution407
An Implicit Diffusion Model (IDM) for high-fidelity continuous image super-resolution is introduced, which integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework.
- Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks366
This paper proposes a trellis encoder-decoder network (TEDnet) for crowd counting that achieves the best overall performance in terms of both density map quality and counting accuracy, and proposes a new combinatorial loss to enforce similarities in local coherence and spatial correlation between maps.
- Channel Pruning via Automatic Structure Search293
This paper proposes a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i.e., channel number in each layer, rather than selecting "important" channels as previous works did.
- 289
- Accelerating Convolutional Networks via Global & Dynamic Filter Pruning274
This paper proposes a novel global & dynamic pruning (GDP) scheme to prune redundant filters for CNN acceleration that achieves superior performance to accelerate several cutting-edge CNNs on the ILSVRC 2012 benchmark.
- 251
- Memory Attention Networks for Skeleton-Based Action Recognition204
A newly temporal-then-spatial recalibration method named memory attention networks (MANs) is proposed and deploy MANs using the temporal attention recalibrration module (TARM) and spatiotemporal convolution module (STCM) to handle skeleton-based action recognition.
- Fusion-Mamba for Cross-Modality Object Detection190
This work investigates a novel cross-modality fusion approach by associating cross-modal features in a hidden state space based on an improved Mamba with a gating attention mechanism, and establishes a new baseline for cross-modality object detection.
- Unsupervised Deep Hashing via Binary Latent Factor Models for Large-scale Cross-modal Retrieval180
A novel unsupervised deep learning framework for multimodal data search in a self-taught manner via integrating deep learning and matrix factorization with binary latent factor models that can generate unified binary codes by solving a discrete-constrained objective function directly.
- Land-use scene classification using multi-scale completed local binary patterns170
To further improve the representation power of CLBP, a multi-scale CLBP (MS-CLBP) descriptor is proposed to characterize the dominant texture features in multiple resolutions to improve classification accuracy and computational complexity.
- 157
- 155
- Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression142
KSE is capable of simultaneously compressing each layer in an efficient way, which is significantly faster compared to previous data-driven feature map pruning methods, and significantly outperforms state-of-the-art methods.
- Directional binary code with application to PolyU near-infrared face database139
A new coding scheme, namely directional binary code (DBC), is proposed for near-infrared face recognition and three protocols are provided to evaluate and compare the proposed DBC method with baseline face recognition methods, including Gabor based Eigenface, Fisherface and LBP on the PolyU-NIRFD database.
- Geometric Reinforcement Learning for Path Planning of UAVs132
Extensive experimental results validate the effectiveness and feasibility of GRL on the navigation of UAVs.
- Multi-modal data Alzheimer’s disease detection based on 3D convolution131
An image fusion method to fuse Magnetic Resonance Images (MRI) with Positron Emission To-mography (PET) images from AD patients is proposed and the experimental results show that the proposed model achieves better results in terms of accuracy, accuracy and specificity.
- Multi-block SSD based on small object detection for UAV railway scene surveillance129
Experimental results show that the proposed multi-block SSD method produces an overall accuracy of 96.6% and obtains an improvement of up to 9.2% compared with the traditional SSD.
- 122
- TASTA: Text‐Assisted Spatial and Temporal Attention Network for Video Question Answering118
A novel VideoQA model called TASTA is proposed, which shows the great potential of explicitly modeling attention and is made to be simple, small, clean, and efficient for clear performance justification and possible easy extension.
- Multinomial Distribution Learning for Effective Neural Architecture Search115
A Multinomial Distribution Learning for extremely effective NAS is proposed, which considers the search space as a joint multinomial distribution, and the optimal network structure is obtained by the operations with the most likely probability in this distribution.
- 113
- 113
- NAS-Count: Counting-by-Density with Neural Architecture Search105
This work automates the design of counting models with Neural Architecture Search (NAS) and introduces an end-to-end searched encoder-decoder architecture, Automatic Multi-Scale Network (AMSNet), utilizing a counting-specific two-level search space.
- PAMS: Quantized Super-Resolution via Parameterized Max Scale104
A new quantization scheme termed PArameterized Max Scale (PAMS), which applies the trainable truncated parameter to explore the upper bound of the quantization range adaptively and a structured knowledge transfer (SKT) loss is introduced to fine-tune the quantized network.
- IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization102
This paper proposes a novel zero-shot quantization method called IntraQ, which employs a local object reinforcement that locates the target objects at different scales and positions of the synthetic images and introduces a marginal distance constraint to form class-related features distributed in a coarse area.
- Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation100
This paper introduces projection convolutional neural networks with a discrete back propagation via projection (DBPP) to improve the performance of binarized neural networks (BNNs) and learns a set of diverse quantized kernels that compress the full-precision kernels in a more efficient way than those proposed previously.
- 95
- 93
- 92
- 87
- VisDrone-SOT2018: The Vision Meets Drone Single-Object Tracking Challenge Results87
The evaluation protocol of the VisDrone-SOT2018 challenge is presented and the results of a comparison of 22 trackers on the benchmark dataset are presented, which are publicly available on the challenge website.
- Multi-UAV Mobile Edge Computing and Path Planning Platform Based on Reinforcement Learning86
This work introduces a new multi-UAV Mobile Edge Computing platform, which aims to provide better Quality-of-Service and path planning based on reinforcement learning to address issues of UAV use in complex environments with obstacles and cooperation between UAVs.
- 85
- ZONE: Zero-Shot Instruction-Guided Local Editing84
This work proposes a Zero-shot instructiON-guided local image Editing approach, termed ZONE, which allows for arbitrary manipulation of a specific region with a single instruction while preserving the rest.
- Circulant Binary Convolutional Networks: Enhancing the Performance of 1-Bit DCNNs With Circulant Back Propagation84
Newcirculant filters (CiFs) and a circulant binary convolution (CBConv) are proposed to enhance the capacity of binarized convolutional features via the authors' circulants back propagation (CBP).
- Visual object tracking via sample-based Adaptive Sparse Representation (AdaSR)83
A new approach for visual object tracking based on Sample-Based Adaptive Sparse Representation (AdaSR), which ensures that the tracked object is adaptively and compactly expressed with predefined samples, which is better than those of several representative tracking methods.
- Cooperative and Geometric Learning Algorithm (CGLA) for path planning of UAVs with limited information81
Risk evaluation is introduced first time in this paper for UAV navigation and extensive computer simulation results validate the effectiveness and feasibility of CGLA for safe navigation of multiple UAVs.
- 80
- AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning78
This paper proposes a non-incremental learner, named AttriCLIP, to incrementally extract knowledge of new classes or tasks, built upon the pre-trained visual-language model CLIP and compares it with CLIP-based and previous state-of-the-art continual learning methods in realistic settings with domain-shift and long-sequence learning.
- Towards Optimal Fine Grained Retrieval via Decorrelated Centralized Loss with Normalize-Scale Layer77
A novel metric learning scheme, termed Normalize-Scale Layer and Decorrelated Global Centralized Ranking Loss, which achieves extremely efficient and discriminative learning, i.e., 5× speedup over triplet loss and 12% recall boost on CARS196.
- Output Constraint Transfer for Kernelized Correlation Filter in Tracking77
Extensive experiments show that the proposed output constraint transfer (OCT) method significantly improves KCF, and achieves better performance than other state-of-the-art trackers.
- 75
- Deep Fisher discriminant learning for mobile hand gesture recognition72
Two new deep models termed as F-BLSTM and F-BGRU are proposed, which can effectively classify the gesture based on analyzing the acceleration and angular velocity data of the human gestures.
- 67
- ST-CNN: Spatial-Temporal Convolutional Neural Network for crowd counting in videos66
Experimental results show that the proposed Spatial-Temporal Convolutional Neural Network outperforms the state-of-the-art models in terms of mean absolutely error (MAE) and mean squared error (MSE).
- 65
- Face Animation with an Attribute-Guided Diffusion Model61
An Attribute-Guided Conditioning Network (AGCN) is designed to adaptively combine the coarse animation features and 3D face reconstruction results, which can incorporate appearance and motion conditions into the diffusion process to mitigate the uncontrollable synthesis effect of the diffusion model.
- 61
- 60
- Bayesian Optimized 1-Bit CNNs58
This paper proposes a novel approach, called Bayesian optimized 1-bit CNNs (denoted as BONNs), taking the advantage of Bayesian learning, a well-established strategy for hard problems, to significantly improve the performance of extreme 1- bit CNNs.
- One-two-one networks for compression artifacts reduction in remote sensing57
An in-depth investigation into the OTO architecture based on the Taylor expansion is provided, which shows that these two kinds of information can be fused in a nonlinear scheme to gain more capacity of handling complicated image compression artifacts, especially the blocking effect in compression.
- Fast algorithm for color texture image inpainting using the non-local CTV model55
This work proposes a non-local Color Total Variation model and proposes a fast heuristic numerical algorithm based on the split Bregman algorithm with introduction of a threshold function for inpainting color texture images.
- 54
- Q-DETR: An Efficient Low-Bit Quantized Detection Transformer51
This paper forms the DRD as a bi-level optimization problem, which can be derived by generalizing the information bottleneck (IB) principle to the learning of Q-DETR, and introduces a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy.
- 51
- Multi-Temporal Depth Motion Maps-Based Local Binary Patterns for 3-D Human Action Recognition51
A local spatio-temporal descriptor for action recognistion from depth video sequences, which is capable of distinguishing similar actions as well as coping with different speeds of actions is presented.
- 51
- Latent Constrained Correlation Filter49
This paper proposes a new method, named latent constrained correlation filters (LCCF), by mapping the correlation filters to a given latent subspace, and develops a new learning framework in the latent sub space that embeds distribution-related constraints into the original problem.
- 49
- 48
- 48
- RSBuilding: Toward General Remote Sensing Image Building Extraction and Change Detection With Foundation Model43
A comprehensive remote sensing image building understanding model, termed RSBuilding, developed from the perspective of the foundation model, which can concurrently handle two structurally distinct tasks and exhibits robust zero-shot generalization capabilities.
- 42
- 41
- 40
- 40
- 38
- 38
- High-Order Convolutional Attention Networks for Automatic Modulation Classification in Communication35
- TRQ: Ternary Neural Networks With Residual Quantization35
A stem-residual framework which provides new insight into Ternary quantization, termed Residual Quantization (TRQ), to achieve more powerful TNNs and yields great recognition accuracy while being accelerated.
- SiMaN: Sign-to-Magnitude Network Binarization34
This article proves that the learned weights of binarized networks roughly follow a Laplacian distribution that does not allow entropy maximization, and demonstrates that the weight binarization problem can be effectively solved by simply removing the sign function.
- Deformable Gabor Feature Networks for Biomedical Image Classification34
A deformable Gabor convolution (DGConv) is introduced to expand deep networks interpretability and enable complex spatial variations and DGFN is introduced for addressing deep multi-instance multi-label classification on the INbreast dataset for mammograms and on the ChestX-ray14 dataset for pulmonary x-ray images.
- Feature Calibration Network for Occluded Pedestrian Detection34
A novel feature learning method in the deep learning framework, referred to as Feature Calibration Network (FC-Net), to adaptively detect pedestrians under various occlusions, which improves detection performance on occluded pedestrians up to 10% while maintaining excellent performance on non-occluded instances.
- Anti-bandit Neural Architecture Search for Model Defense34
This paper defends against adversarial attacks using neural architecture search (NAS) which is based on a comprehensive search of denoising blocks, weight-free operations, Gabor filters and convolutions, and incorporates a new operation evaluation measure and search process based on the lower and upper confidence bounds (LCB and UCB).
- 34
- 33
- The 1st Tiny Object Detection Challenge: Methods and Results33
A brief summary of the 1st Tiny Object Detection (TOD) Challenge is provided including brief introductions to the top three methods.
- Self-Learning Scene-Specific Pedestrian Detectors Using a Progressive Latent Model33
Extensive experiments demonstrate that even without annotation the proposed self-learning approach outperforms weakly supervised learning approaches, while achieving comparable performance with transfer learning and fully supervised approaches.
- 32
- Multi-modal Multi-layer Fusion Network with Average Binary Center Loss for Face Anti-spoofing32
A novel Multi-modal Multi-layer Fusion Convolutional Neural Network (mmfCNN), which targets at finding a discriminative model for recognizing the subtle differences between live and spoof faces, and utilizes a multi-layer fusion model to further aggregate the features from different layers.
- 32
- 31
- 31
- 31
- 31
- 31
- DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning30
This paper proposes an efficient and unified NAS framework termed DDPNAS via dynamic distribution pruning, facilitating a theoretical bound on accuracy and efficiency and directly obtains the optimal neural architectures on given constraints, practical for on-device models across diverse search spaces and constraints.
- 30
- Long-Short-Term Features for Dynamic Scene Classification30
A unified framework to extract spatial and temporal features for dynamic scene representation is proposed and two variants of deep convolutional neural networks are deployed to encode spatial appearance and short- term dynamics into short-term deep features (STDF).
- Deepwalk-aware graph convolutional networks29
A deepwalk strategy is introduced into GCNs to efficiently explore the global graph information and can complement the local neighborhood information of a graph, resulting in the more robust representation for the graph data.
- 29
- Binarized Neural Architecture Search29
This work introduces channel sampling and operation space reduction into a differentiable NAS to significantly reduce the cost of searching and achieves a performance comparable to NAS on both CIFAR and ImageNet databases.
- 28
- Realtime multi-aircraft tracking in aerial scene with deep orientation network27
The presented method is efficient for realtime ground target-tracking scenarios and the number of Identity switches has reduced about 67% without affecting the computational complexity of the tracking component.
- Attentional Alignment Networks.27
This work proposes attentional alignment networks (AAN), a novel end-to-end convolutional architecture for direct face alignment without relying on cascaded regression that consistently delivers high performance on all datasets, surpassing previous methods by large margins.
- Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs26
This paper proposes rectified binary convolutional networks (RBCNs), towards optimized BCNNs, by combining full-precision kernels and feature maps to rectify the binarization process in a unified framework.
- IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts25
IPDreamer is introduced, a novel approach that incorporates image prompts to provide specific and comprehensive appearance information for 3D object generation that effectively generates high-quality 3D objects that are consistent with both the provided text and image prompts.
- 25
- 25
- 25
- Spatial Weighting for Bag-of-Features Based Image Retrieval25
Experimental results show that SWBOF significantly improves the performance of the traditional BOF method, and achieves the best performance on the Corel database to the best knowledge.
- 24
- 24
- Towards Comprehensive Monocular Depth Estimation: Multiple Heads are Better Than One24
This work construct multiple base (weak) depth predictors by utilizing different Transformer-based and convolutional neural network (CNN)-based architectures and designs mixers to learn from multiple weak predictions and adaptively fuse them into a strong depth estimate.
- 24
- 24
- An Integrated Deep Learning Framework for Occluded Pedestrian Tracking24
A pedestrian tracking framework is proposed and developed based on the deep learning networks that achieves better performance than the other state-of-the-art trackers in various occlusion situations.
- Superpixel-Based Feature for Aerial Image Scene Recognition24
A novel superpixel-based feature that utilizes landform information establishes top-task superpixel extraction of landforms to bottom-task expression of feature vectors that is higher than those of scene recognition algorithms based on other local features.
- SA-BNN: State-Aware Binary Neural Network23
The proposed SA-BNN is inspired by the observation that the frequent weight flip is more likely to occur, when the gradient magnitude for all quantization states {-1,1} is identical, and proposes to employ independent gradient coefficients for different states when updating the weights.
- 23
- Binarized Neural Architecture Search for Efficient Object Recognition23
Binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing.
- Face recognition based on gradient gabor feature and Efficient Kernel Fisher analysis23
The experiment results show that GGabor yield a powerful tool to model faces, and the Efficient Kernel Fisher classifier can improve the efficiency of the original Kernel Fisher Discriminant analysis method.
- CCExpert: Advancing MLLM Capability in Remote Sensing Change Captioning with Difference-Aware Integration and a Foundational Dataset22
A novel model, CCExpert, based on a new, advanced multimodal large model framework, designed to capture multi-scale differences between bi-temporal images and incorporate them into the original image context, thereby enhancing the signal-to-noise ratio of differential features.
- Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment22
A cross-modal distribution alignment module is proposed, in which a vision-language prototype is introduced for each class to align the distributions, and the Earth Mover's Distance (EMD) is derived to optimize the prototypes.
- A Survey on Human Cancer Categorization Based on Deep Learning22
The most extensively used DL network category is convolutional neural networks (CNNs) and how CNN architectures have evolved is investigated and a discussion of the revealed challenges and trends for upcoming research is held.
- 22
- Hypergraph Induced Convolutional Manifold Networks22
A hypergraph induced Convolutional Manifold Network (H-CMN) to significantly improve the representation capacity of DCNN for the complex data and achieves much better performance than the state-of-the-art.
- 21
- 21
- 21
- 20
- Real-Time Human-UAV Interaction: New Dataset and Two Novel Gesture-Based Interacting Systems20
Two novel gesture-based Human-UAV Interaction (HUI) systems are proposed to launch and control a UAV in real-time utilizing a monocular camera and a ground computer.
- Realtime Human-UAV Interaction Using Deep Learning20
A robust Human-UAV Interaction (HUI) system that can detect and identify a person gesture to control a micro UAV in real time and build a new dataset with 23 participants to train or fine-tune the deep neural networks for human gesture detection.
- 20
- Constraint Shape Model Using Edge Constraint and Gabor Wavelet Based Search20
Constraint Shape Model is proposed to extract facial feature using two different search methods for contour points and control points individually, which shows that the proposed method performs significantly better in terms of a deliberate performance evaluation method.
- 19
- 19
- 19
- Gabor feature constrained statistical model for efficient landmark localization and face recognition19
A new Constrained Profile Model (CPM), in cooperation with Flexible Shape Model (FSM) to form an efficient localization framework is presented, which not only avoids local minima in landmark localization, but also circumvents the exhaustive global optimization.
- 18
- Dynamic Distribution Pruning for Efficient Network Architecture Search18
A dynamic distribution pruning method towards extremely efficient NAS, which samples architectures from a joint categorical distribution, and the optimal neural architecture is obtained when there is only one structure remained.
- CP-NAS: Child-Parent Neural Architecture Search for 1-bit CNNs17
A Child-Parent model is introduced to a differentiable NAS to search the binarized architecture under the supervision of a full-precision model (Parent) and achieves a comparable accuracy with traditional NAS on both the CIFAR and ImageNet databases.
- Pedestrian detection in images via cascaded L1-norm minimization learning method17
The proposed CLML method, which is designed from the perspective of Vapnic's theory in the statistical learning, integrates feature selection with classifier construction via solving meaningful optimization models.
- 17
- Kernel Learning of Histogram of Local Gabor Phase Patterns for Face Recognition17
A new face recognition method, named kernel learning of histogram of local Gabor phase pattern (K-HLGPP), which is based on Daugman's method for iris recognition and the local XOR pattern (LXP) operator is proposed.
- AQ-DETR: Low-Bit Quantized Detection Transformer with Auxiliary Queries16
A new quantization strategy based on Auxiliary Queries for DETR (AQ-DETR), aiming to enhance the capacity of quantized queries, and a layer-by-layer distillation is proposed to reduce the quantization error between quantized attention and full-precision counterpart.
- 16
- Towards Compact 1-bit CNNs via Bayesian Learning16
A novel Bayesian Optimized compact 1- bit CNNs (BONNs) model is proposed, which has the advantage of Bayesian learning, to improve the performance of 1-bit CNNs significantly and introduces a new Bayesianlearning-based pruning method for 1- Bit CNNs, which significantly increases the model efficiency with very competitive performance.
- Alignment Enhancement Network for Fine-grained Visual Categorization16
A novel Alignment Enhancement Network (AENet) is proposed, including two-level alignments, Cross-layer Alignment (CLA) and Cross-image Aligned (CIA), which exploits the cross-layer relationship between low-level spatial information and high-level semantic information, which contributes to cross- layer feature aggregation to improve the capacity of feature representation for input images.
- 16
- 15
- 15
- Tiny Vehicle Detection for Mid-to-High Altitude UAV Images Based on Visual Attention and Spatial-Temporal Information15
This paper puts forward a vehicle detection method combining the DNNs-based and traditional methods for mid-to-high altitude UAV images that first employs the deep segmentation network to exploit the co-occurrence of the road and vehicles, then detects tiny vehicles based on visual attention mechanism with spatial-temporal constraint information.
- 15
- BiRe-ID: Binary Neural Network for Efficient Person Re-ID15
This work discovers that the significant performance drop of binarized models for Re-ID task is caused by the degraded representation capacity of kernels and features, and proposes the kernel and feature refinement based on generative adversarial learning (KR-GAL and FR- GAL) to enhance the representation capacityof BNNs.
- 15
- Rectified Binary Convolutional Networks with Generative Adversarial Learning15
A Rectified Binary Convolutional Network is introduced by combining full precision kernels and feature maps to rectify the binarization process in a generative adversarial network (GAN) framework and further prune the RBCNs using the GAN framework to increase the model efficiency and promote flexibly in practical applications.
- Cogradient Descent for Bilinear Optimization15
A Cogradient Descent algorithm to address the bilinear problem, based on a theoretical framework to coordinate the gradient of hidden variables via a projection function, which improves the state-of-the-art by a significant margin.
- Enhanced Bird Detection from Low-Resolution Aerial Image Using Deep Neural Networks15
A novel DNN based framework for bird detection in reconstructed HR images, which exploits the mapping function from LR to HR aerial image and detects the birds by the state-of-the-art object feature extraction and localization methods is presented.
- Robust object representation by boosting-like deep learning architecture15
A new deep learning architecture for robust object representation is presented, aiming at efficiently combining the proposed synchronized multi-stage feature (SMF) and a boosting-like algorithm, which obtains more convergence stability than traditional deep learning algorithm.
- 14
- iffDetector: Inference-Aware Feature Filtering for Object Detection14
This article introduces a generic inference-aware feature filtering (IFF) module that can be easily combined with existing detectors, resulting in the iffDetector, which consistently outperforms state-of-the-art methods with significant margins.
- Optimization of bits allocation and path planning with trajectory constraint in UAV-enabled mobile edge computing system14
An Alternating Direction Method of Multipliers (ADMM) method is introduced to solve the optimization problem, which is decomposed into a set of easy sub-problems, to meet the requirement on the efficiency in edge computing.
- 14
- LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation13
This paper proposes a new zero-shot video-to-video translation framework, named \textit{LatentWarp], and finds the bottleneck lies in the unconstrained query tokens and proposes a warping operation in the latent space to constrain the query tokens.
- Context-sensitive zero-shot semantic segmentation model based on meta-learning13
A novel zero-shot semantic segmentation model based on meta-learning that outperforms the existing best methods in the zero- shot segmentation on three datasets of Pascal-VOC 2012, Pascal-Context and Coco-stuff and improves the adaptability of the model parameters by adjusting the parameters of the dual-space through the meta- learning.
- 13
- Real-time guidewire tracking and segmentation in intraoperative x-ray12
Quantitative and qualitative evaluations on clinical intra-operative images demonstrate that the proposed approach significantly outperforms the authors' baselines as well as the current state of the art and, in comparison, shows higher robustness to low quality images.
- 12
- SEMANTIC-RTAB-MAP (SRM): A semantic SLAM system with CNNs on depth images12
This paper presents a novel method named SEMANTIC-RTAB-MAP (SRM), which uses YOLOv2 network to detect target objects in 2D images, and then uses depth information for precise localization of the targets and finally add semantic information into 3D point clouds.
- 12
- Gesture Recognition Benchmark Based on Mobile Phone12
A gesture recognition benchmark based on sensors of mobile phone using the built-in micro gyroscope and accelerometer to reduce the effect of the phone’s posture variations and the employed methods can effectively recognize the gestures.
- 11
- Amplitude Suppression and Direction Activation in Networks for 1-bit Faster R-CNN11
This paper proposes an amplitude suppression and direction activation for Faster R-CNN (ASDA-FRCNN) framework to significantly compress DCNNs for highly efficient performance and demonstrates the superior performance and strong generalization of the method.
- CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection11
CircleNet implements feature ensemble with the idea of hard negative boosting in an end-to-end manner to achieve feature adaptation by mimicking the process humans looking at low resolution and occluded objects.
- Robust kernelized correlation filter with scale adaption for real-time single object tracking11
A new scale adaptive kernelized correlation filter tracker, termed as SKCF, is proposed, which estimates an accurate scale and models the distribution of correlation response to address the template drifting problem.
- 10
- Weakly Supervised Object Detection Based on Active Learning10
Three strategies of active learning are introduced, including least confidence sampling, margining sampling and weighted classification sampling, and the combination of image-level labeling and active learning can achieve comparable results with the previous state-of-the-art methods with much lower label cost.
- 10
- 10
- Generalized Zero-Shot Vehicle Detection in Remote Sensing Imagery via Coarse-to-Fine Framework10
A novel coarse-to-fine framework is introduced, which decomposes vehicle detection into segmentation-based vehicle localization and generalized zero-shot vehicle classification, and a hierarchical DeepLab v3 model is proposed in the framework, which fully exploits fine-grained features to locate the target on a pixel-wise level, then recognizes vehicles in a coarse- grained manner.
- Boosting-Like Deep Convolutional Network for Pedestrian Detection10
This paper proposes the boosting-like algorithm to enhance the system convergence stability through adjusting the updating rate according to the classification condition of samples in the training process, and theoretically gives the derivation of the algorithm.
- 10
- Sequence-to-point learning based on spatio-temporal attention fusion network for non-intrusive load monitoring9
Extensive experiments on two public datasets such as REDD and UK-DALE show the validity of the proposed spatio-temporal attention fusion network, outperforming the other used methods on NILM tasks.
- P4Q: Learning to Prompt for Quantization in Visual-language Models9
This work proposes a method that balances fine-tuning and quantization named ``Prompt for Quantization'' (P4Q), in which a lightweight architecture is designed to leverage contrastive loss supervision to enhance the recognition performance of a PTQ model.
- POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing9
This paper introduces point-wise operations based on Expectation-Maximization (POEM) into XNOR-Net-based binary neural networks for efficient point cloud processing and leads a well-designed reconstruction loss to calculate learnable scale factors to enhance the representation capacity of 1-bit fully-connected (Bi-FC) layers.
- Interpretable Neural Network Decoupling9
A novel architecture decoupling method to interpret the network from a perspective of investigating its calculation paths, and introduces a novel architecture controlling module in each layer to encode the network architecture by a vector.
- Hybrid Gabor Convolutional Networks9
A new deep model, Hybrid Gabor Convolutional Networks (HGCNs), is proposed in this paper, which achieves a comparable performance while largely reducing the storage memory compared with state-of-the-art networks such as Resnet.
- 9
- Gabor-Kernel Fisher Analysis for Face Recognition9
A novel Gabor-Kernel Fisher analysis method is proposed, which applies Enhanced Kernel Fisher Model (EKFM) on Gaborfaces derived from Gabor wavelet representation of face images, and it is shown that the EKFM outperforms the Generalized Kernel Fisher Analysis (GKFD) model.
- HRGS: Hierarchical Gaussian Splatting for Memory-Efficient High-Resolution 3D Reconstruction8
Hierarchical Gaussian Splatting (HRGS) is proposed, a memory-efficient framework with hierarchical block-level optimization that enables high-quality, high-resolution 3D scene reconstruction even under memory constraints.
- 8
- Representation Disparity-aware Distillation for 3D Object Detection8
A novel representation disparity-aware distillation (RDD) method is presented to address the representation disparity issue and reduce performance gap between compact students and over-parameterized teachers by building the RDD from an innovative perspective of information bottleneck (IB).
- Bi-level Doubly Variational Learning for Energy-based Latent Variable Models8
Bi-level doubly variational learning (BiDVL), which is based on a new bi-level optimization framework and two tractable variational distributions to facilitate learning EBLVMs, achieves impressive image generation performance over related works and demonstrates the significant capacity of testing image reconstruction and out-of-distribution detection.
- 8
- A multi-scale unsupervised learning for deformable image registration8
A novel method for unsupervised deformable image registration is developed by incorporating the HAT module and AFS mechanism into the framework, which provides a new way to obtain a desirable registration field between a pair of images.
- Multi-scale Supervised Attentive Encoder-Decoder Network for Crowd Counting8
A new KL-divergence-based distribution loss is designed to supervise the scale-aware structural differences between two density maps, which complements the pixel-isolated MSE loss and better optimizes AEDN to generate high-quality density maps.
- The Structure Transfer Machine Theory and Applications8
This paper proposes a new representation learning method, named Structure Transfer Machine (STM), which enables feature learning process to converge at the representation expectation in a probabilistic way and theoretically shows that such an expected value of the representation (mean) is achievable if the manifold structure can be transferred from the data space to the feature space.
- Calibrated Stochastic Gradient Descent for Convolutional Neural Networks8
A theorem is developed to prove that an unbiased estimator for the network variables can be obtained in a probabilistic way based on the Lipschitz hypothesis, and a generic gradient calibration layer is developed which can be easily used to build convolutional neural networks.
- 8
- 8
- Adaptive Multi-class Correlation Filters8
An adaptive multi-class correlation filters (AMCF) method based on an alternating direction method of multipliers (ADMM) framework is proposed, which introduces an adaptive output to alleviate the under-fitting problem in the ADMM iterations.
- Sparsity analysis versus sparse representation classifier8
This paper proposes a new method named Sparse Regression Analysis (SRA) for object representation and recognition, and shows that the discriminative ability of SRC and SRA derives from the fact that the subset which most compactly expresses the input signal is activated in the regression analysis.
- The BeiHang Keystroke Dynamics Systems, Databases and baselines8
An embedded password protection device is designed, an online system is developed, two public databases are collected, and benchmark results of several popular classification algorithms, one-class support vector machine, Gaussian classifier, and nearest neighbor classifier are provided.
- 8
- Weighted Margin Sparse Embedded classifier for brake cylinder detection8
Comparative experimental results on the BH-BC database show that the proposed WMSE classifier can get a much higher detection performance than the state-of-the-art classifiers (Support Vector Machine and Adaboost).
- 7
- 7
- Local convolutional features and metric learning for SAR image registration7
The experimental results demonstrate that the proposed local convolutional neural network features based method to solve the keypoint matching problem outperforms the existing state-of-the-art methods in terms of matching accuracy and efficiency.
- Hierarchical residual stochastic networks for time series recognition7
Experiments show that end-to-end hierarchical residual stochastic networks to effectively and efficiently describe spatio-temporal variations significantly boost the performance of time series recognition and improve the state-of-the-art of skeleton, action, and radar behavior recognition performance.
- A compressed sensing ensemble classifier with application to human detection7
Experimental results on INRIA and SDL databases show that the performance of CSEC is better than two most popular classifiers SVM and AdaBoost, as well as a most recent method CLML.
- DecomCAM: Advancing beyond saliency maps through decomposition and integration6
DecomCAM is a novel decomposition-and-integration method that distills shared patterns from channel activation maps into orthogonal sub-saliency maps (OSSMs), which are then integrated together based on their contribution to the target concept.
- 6
- Uncertainty-aware Binary Neural Networks6
This work introduces an uncertainty-aware BNN (UaBNN) by leveraging a new mapping function called certainty-sign (c-sign) to reduce these weights' uncertainties, and introduces a c-sign function, the first to train BNNs with a decreasing uncertainty for binarization.
- 6
- 6
- 6
- 6
- 6
- Filtered shallow-deep feature channels for pedestrian detection6
This paper proposes integrating deep semantic segmentation feature maps into the original pedestrian detection framework which combines feature channels with AdaBoost classifiers, and develops shallow-deep channels by concatenating shallow hand-crafted and deep segmentation channels.
- Complex background modeling based on Texture Pattern Flow with adaptive threshold propagation6
Experimental results on the public databases testify the effectiveness of the proposed TPF method in comparison to LBP and GMM based background modeling methods.
- Learning Accurate Low-bit Quantization towards Efficient Computational Imaging5
Extensive experiments across a range of image processing tasks, including enhancement, super-resolution, denoising and dehazing, validate the effectiveness of the differentiable quantization search (DQS) method, which achieves a strong generalization performance when composing a detection network for the dark object detection task.
- Normalizing Batch Normalization for Long-Tailed Recognition5
This paper identifies that the bias towards the frequent class may be encoded into features, i.e., the rare-specific features which play a key role in discriminating the rare class are much weaker than the frequent-specific features.
- 5
- 5
- 5
- 5
- Multiple Classifier System for Remote Sensing Images Classification5
Experimental results show that proposed MCS can successfully classify the remote sensing images with high accuracy as well as reduce the computation cost.
- Deep Collaborative Tracking Networks.5
The DCTN is the first generalized framework to model motion and appearance information with deep learning for object tracking and can achieve high tracking performance, which demonstrates the great effectiveness of exploring both motion and appearance information for visual object tracking.
- 5
- 5
- Deep-Patch Orientation Network for Aircraft Detection in Aerial Images5
A Deep-patch Orientation Network (DON) method, which is general and can learn the encoded orientation information based on any off the-shelf deep detection framework, e.g., Faster-RCNN and YOLO, and result into higher performance in airplane target detection and classification tasks.
- 5
- A Routing Algorithm for WiFi-Based Wireless Sensor Network and the Application in Automatic Meter Reading5
A new architecture of WiFi-based wireless sensor network based on the WiFi technology is designed, which is suitable for the next generation AMR system and a new routing algorithm called Energy Saving-Based Hybrid Wireless Mesh Protocol (E-HWMP) is proposed, which can improve the energy saving of the HWMP.
- 5
- 5
- 4
- 4
- 4
- Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler4
A novel Knowledge-driven Differential Filter Sampler~(KDFS) with Masked Filter Modeling~(MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization.
- Automated morphologic analysis of intracranial and extracranial arteries using convolutional neural networks4
An automatic method for analysis of intracranial and extracranial MR vessel wall images simultaneously based on CNN, which can facilitate large-scale quantitative analyses of vessel walls is proposed and is expected to facilitateLarge-scale arterial vessel wall morphological quantification.
- 4
- 4
- Dynamic Neural Network Decoupling.4
A novel architecture decoupling method is proposed, which dynamically discovers the hierarchical path consisting of activated filters for each input image, and subsequently disentangles the filters by limiting the outputs of filter during training.
- 4
- Object detection and tracking benchmark in industry based on improved correlation filter4
Dijkstra-distance based correlation filters (DBCF) is proposed, which establishes a new learning framework that embeds distribution-related constraints into the multi-channel correlation filters(MCCF) and is able to handle the huge variations existing in the industrial data by improving those constraints based on the shortest path among all solutions.
- Manifold Constrained Low-Rank Decomposition4
A new framework that embeds manifold priors into LRD is proposed that efficiently integrates the manifold constraints during the optimization process and is successfully used to calculate low-rank models from face images, hand-written digits and planar surface images.
- GPCA-SIFT: A New Local Feature Descriptor for Scene Image Classification4
A new local feature descriptor called GPCA-SIFT, which gets the key points using the detection method in Scale Invariant Feature Transform and extracts a 41 * 41 patch for each key point and calculates the horizontal and vertical gradient of each pixel in the patch.
- Location recognition on lifelog images via a discriminative combination of generative models4
This paper proposes a principled (discriminative) combination of heterogeneous generative models able to cope with extremely challenging classification tasks and it demonstrates that combining such diverse heterogeneous models is indeed advantageous.
- “Signal, image and video processing” special issue: Semantic representations for social behavior analysis in video surveillance systems4
A number of feature representation approaches have been reported to address the coherence between the extracted features and the semantic interpretations in the gap between the information directly extracted from videos and semantic interpretations by human beings.
- The application of extended geodesic distance in head poses estimation4
This paper proposes an new method called the kc-neighbor, in which the neighbors are defined based on c time distance of the k nearest neighbor, which can avoid the neighborhood graph unconnected and improve the accuracy in computing neighbors.
- The Application of Extended Geodesic Distance in Head Poses Estimation4
This paper proposes an new method called the kc-neighbor, in which the neighbors are defined based on c time distance of the k nearest neighbor, which can avoid the neighborhood graph unconnected and improve the accuracy in computing neighbors.
- 3D Reconstruction based on multi-view stereo in the deep learning era: a survey and comparison of methods3
An in-depth review of deep learning methodologies to address Multi-view Stereo (MVS) challenges and a detailed classification of 3D reconstruction methods, which underscores the significance of multi-view 3D reconstruction.
- Heterogeneous Generative Knowledge Distillation with Masked Image Modeling3
This paper develops the first Heterogeneous Generative Knowledge Distillation (H-GKD) based on MIM, which can efficiently transfer knowledge from large Transformer models to small CNN-based models in a generative self-supervised fashion.
- DCP–NAS: Discrepant Child–Parent Neural Architecture Search for 1-bit CNNs3
This paper introduces Discrepant Child–Parent Neural Architecture Search (DCP–NAS), a new framework of searching the 1-bit model under the supervision of a real-valued model (Parent), and proposes a decoupled optimization method to search an optimized architecture.
- Multi-receptive field spatiotemporal network for action recognition3
A multi-receptive field spatiotemporal (MRF-ST) network to effectively model the spatial and temporal information of different receptive fields and can improve the accuracy of action recognition by learning more visual tempos of different actions.
- Anti-Bandit for Neural Architecture Search3
This paper reformulate NAS as a multi-armed bandit problem and presents Anti-Bandit NAS (ABanditNAS) method, which exploits Upper Confidence Bounds (UCB) to abandon arms for search efficiency and Lower Conf confidence bounds (LCB) for fair competition between arms.
- 3
- 3
- Interpretable Attention Guided Network for Fine-Grained Visual Classification3
This work proposes an Interpretable Attention Guided Network (IAGN) for fine-grained visual classification, which is the first interpretable FGVC method with a competitive performance on several standard FGVC benchmark datasets.
- 3
- 3
- 3
- Manifold constraint transfer for visual structure-driven optimization3
It is shown that manifold constraints can be transferred from the data to the optimized variables if these are linearly correlated and the resulting optimization problem can be solved with an efficient alternating direction method of multipliers that can consistently integrate the manifold constraints during the optimization process.
- 3
- Interval Algorithm for Set-Membership Identification of MIMO LTI System3
The present algorithm can obtain not only the center estimations of parameters, but also the bounds of errors on them, and is compatible with the measured data and the bounded noise.
- 3
- Bilateral Sharpness-Aware Minimization for Flatter Minima2
By merging MaxS and MinS, this article creates a better FI that indicates a flatter direction during the optimization of SAM, and combines this FI with SAM into the proposed bilateral SAM (BSAM), which finds a flatter minimum than SAM.
- 2
- 2
- 2
- DrawingNet for Communication Tower Drawings Recognition2
This work introduces an industrial drawing recognition method based on a new neural architecture, dubbed as DrawingNet, designed based on layer-wise aggregation module and deformable convolution to extract more representational features for input drawing images.
- 2
- A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification2
A lightweight channel-based ensemble method to effectively consolidate multiple inferior PLs into the theoretically guaranteed unbiased and low-variance one, which significantly outperforms state-of-the-art techniques on CIFAR10/100 in terms of effectiveness and efficiency.
- 2
- 2
- 2
- Knowledge Graph Embedding Method Based on Entity Metric Learning2
A path-based negative sampling method is proposed to widen the distance between similar entities to better deal with the aggregation problem of embedding entities in the representation space under one-to-many relation.
- 2
- 2
- Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning2
This paper observes that introducing robustness-promoting regularization into MAML reduces the intrinsic dimension of clean sample features, which results in a lower capacity of clean representations, and proposes a simple strategy, i.e., increasing the number of training shots, to mitigate the loss of intrinsic dimension caused by robusts-promoted regularization.
- Robust and real-time object recognition based on multiple fractal dimension2
It is theoretically proven that the multiple fractal dimensions (MFD) method is shown to be invariant to local variations, i.e., Bi-Lipschitz, which is a desirable characteristic for objects, such as land-scene images, face and pedestrian due to the existence of scale variations, local variations and illumination variations in those images.
- 2
- 2
- Segmentation of Arteriovenous Malformation Based on Weighted Breadth-First Search of Vascular Skeleton2
A weighted breadth-first search tree is created from the result of vascular skeletonization, and the AVM is automatically detected and extracted and the method is effective and is helpful for the treatment of vascular interventional surgery.
- ASiam: adaptive Siamese regression tracking with adversarial template generation and motion‐based failure recovery2
A new adaptive Siamese (ASiam) tracker is proposed, which integrates a novel adversarial template generation module and a motion-based failure recovery module and is optimised via adversarial learning to achieve accurate appearance prediction and sharp template quality.
- 2
- Multilinear Local Fisher Discriminant Analysis for Face Recognition2
A multilinear local fisher discriminant analysis framework is introduced for tensor object dimensionality reduction and recognition and the experimental result shows that MLFDA has an outperformance.
- Scale Invariant Kernelized Correlation Filter Based on Gaussian Output2
A new method is proposed, named Scale Invariant KCF (SIKCF), which estimates an accurate scale and models the distribution of correlation response to address the template drifting problem.
- 2
- 2
- 2
- Local Kernel Feature Analysis (LKFA) for object recognition2
Experimental results on palmprint and face recognitions demonstrated the effectiveness of the proposed LKFA that significantly improved the performance of the local feature based object recognition method.
- 2
- Discriminant Analysis Based on Kernelized Decision Boundary for Face Recognition2
A novel nonlinear discriminant analysis method, Kernelized Decision Boundary Analysis (KDBA), is proposed in this paper, whose Decision Boundaries feature vectors are the normal vector of the optimal decision Boundary in terms of the Structure Risk Minimization principle.
- 1
- 1
- Big2Small: Learning from masked image modelling with heterogeneous self‐supervised knowledge distillation1
The authors develop the first heterogeneous self‐supervised knowledge distillation (HSKD) based on MIM, which can efficiently transfer knowledge from large transformer models to small CNN‐based models in a self‐supervised fashion.
- 1
- 1
- 1
- 1
- Decom--CAM: Tell Me What You See, In Details! Feature-Level Interpretation via Decomposition Class Activation Map1
A new two-stage interpretability method called the Decomposition Class Activation Map (Decom-CAM) is proposed, which offers a feature-level interpretation of the model's prediction and could pave the way for a new direction for understanding the decision-making process of deep neural networks.
- 1
- 1
- 1
- 1
- Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluation1
This paper proposes to use multiple factors to measure and rank the relative generalization of DNNs based on a new concept of confidence dimension (CD), and provides a feasible framework in this CD to theoretically calculate the upper bound of generalization based on the conventional Vapnik-Chervonenk dimension (VC-dimension) and Hoeffding's inequality.
- 1
- 1
- HSI-GCN: hyperspectral image classification algorithm based on Gabor convolutional networks1
HSI-GCN is able to extract deep joint spatial–spectral features more rapidly and accurately despite the shortage of training samples, and has shown unexpectable results with an excellent classification accuracy.
- 1
- 1
- Tailored Pruning via Rollback Learning1
This paper proposes rollback learning for pruning (RLP)-an algorithm to efficiently prune networks while maintaining performance and adds rollback pruning into generative adversarial learning to compute a soft mask to scale the output of the network structures by defining a new objective function.
- 1
- Efficient Facial Landmark Localization Based on Binarized Neural Networks1
This paper introduces a new network architecture to calculate the binarized models, referred to as Amplitude Convolutional Networks (ACNs), based on the proposed asynchronous back propagation algorithm, and reduces the storage space of convolutional filters by a factor of 32 compared with the full-precision models on dataset LFW+Webface, CelebA, BioID and 300W.
- Few-Shot Learning with Complex-valued Neural Networks1
This paper introduces complex metric module (CMM) into metric learning, aiming to better measure the inter-and intra-class relations based on both amplitude and phase information, and introduces a new transductive method into CMM, which improves the performance over other approaches and achieves the state-of-the-art results.
- 1
- 1
- 1
- 1
- 1
- A 3D Reconstruction System for Large Scene Based on RGB-D Image1
A 3D scene reconstruction system based on RGB-D images, achieving a better performance in accuracy and real time and developing a better algorithm for large-scale complex scene modeling.
- 1
- 1
- 1
- 1
- Cloud-Based Video Surveillance System Using EFD-GMM for Object Detection1
This paper deploys the framework of a cloud-based video surveillance system and proposes an EFD-GMM approach for object detection in the overhead video processing and shows that the proposed approach is more efficient than GMM in video processing of cloud- based system.
- Local Dual-Cross Ternary Pattern for Feature Representation1
LDCTP is a feature representation inspired by the sole textural structure of human faces that is efficient and only quadruples the cost of computing Local Binary Pattern and Dual-Cross Pattern.
- Human Facial Expression Recognition Based on 3D Cuboids and Improved K-means Clustering Algorithm1
This paper combines discrete linear filter with key parameters selection procedure to extract 3D cuboids and proposes a novel seed spot selection method to optimize K-means clustering algorithm.
- A Panoramic Video System Based on Exposure Adjustment and Non-linear Fusion1
This paper proposes a new video stitch method based on the exposure adjustment and nonlinear fusion algorithm, which achieves a much better performance than traditional linear fusion method, especially when there is a big disparity between cameras.
- A Non-negative Low Rank and Sparse Model for Action Recognition1
A novel non-negative low rank and sparse coding model is developed to encode descriptors for action recognition, which is different from previous methods such as spatio-temporal pyramid matching (STPM).
- An Improved Adaptive Weighted LTP Algorithm for Face Recognition Based on Single Training Sample1
An adaptive weighted LTP algorithm with a novel weighted method involving the standard deviation of the sub-images’ feature histogram is proposed for the single training sample per person (SSPP) problem.
- 1
- 1
- 1
- 1
- –
- –
- P4Q: Learning to Prompt for Quantization in Low-Bit CLIP–
The “Prompt for Quantization” (P4Q) is proposed, by integrating PTQ with Parameter-Efficient Fine-Tuning (PEFT) techniques, and demonstrates that P4Q significantly enhances the performance of low-bit CLIP while reducing deployment costs.
- –
- MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training–
With MEC-Qaunt, the limit of QAT is pushed to the x-bit activation for the first time and the accuracy of MEC-Quant is comparable to or even surpass the FP counterpart, establishing a new state of the art for QAT.
- Robust learning for ridge-penalized quasi-GLMs under non-identical distributions–
A novel log-truncated minimization estimator and a corresponding stochastic gradient descent algorithm for quasi-generalized linear models and its practical effectiveness is demonstrated through a real-data analysis of the German health care demand dataset using robust negative binomial regression.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Guided Convolutional Network–
A new deep model, termed Guided Convolutional Networks (GCNs), is proposed using low-level handcrafted features to guide the training process of the DCNNs, which can be used in the following vision tasks.
- Face Liveness Detection Benchmark based on Stereo Matching–
A face liveness detection benchmark is established and maintained, wherein 400 images pairs captured with binocular camera are made openly available for research purposes, and a set of optimal parameters for the classification is given which provides a reference for further research.
- –
- –
- –
- –
- Compressed Sensing Ensemble Classifier for Human Detection–
Experimental results on INRIA and SDL databases show that the performance of CSEC is better than two most popular classifiers SVM and AdaBoost, as well as a most recent method CLML.
- –
- –
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 2026-10-14. 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.