Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks199 from public data
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks5,701
This work proposes a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections, and proposes a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels.
- Residual Dense Network for Image Super-Resolution4,163
This paper proposes residual dense block (RDB) to extract abundant local features via dense connected convolutional layers and uses global feature fusion in RDB to jointly and adaptively learn global hierarchical features in a holistic way.
- Siamese Box Adaptive Network for Visual Tracking991
SiamBAN views the visual tracking problem as a parallel classification and regression problem, and thus directly classifies objects and regresses their bounding boxes in a unified FCN, making SiamB Ban more flexible and general.
- Residual Dense Network for Image Restoration895
This work proposes residual dense block (RDB) to extract abundant local features via densely connected convolutional layers and proposes local feature fusion in RDB to adaptively learn more effective features from preceding and current local features and stabilize the training of wider network.
- A Comprehensive Survey of Vision-Based Human Action Recognition Methods499
This survey paper provides a comprehensive overview of recent approaches in human action recognition research, including progress in hand-designed action features in RGB and depth data, current deep learning-based action feature representation methods, advances in human–object interaction recognition methods, and the current prominent research topic of action detection methods.
- 313
- Deep Network Cascade for Image Super-resolution264
Experiments on image super-resolution demonstrate that the proposed DNC can gradually upscale a low-resolution image with the increase of network layers and achieve more promising results in visual quality as well as quantitative performance.
- Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers230
This work proposes an adaptive tracker with spatio-temporal transformers (named AQA-Track), which adopts simple autoregressive queries to effectively learn spatio-temporal information without many hand-designed components, and designs a novel attention mechanism for the interaction of existing queries to generate a new query in current frame.
- 206
- 172
- 152
- What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation150
A new unsupervised semantic transfer model including two complementary modules for endoscopic lesions segmentation, which can alternatively determine where and how to explore transferable domain-invariant knowledge between labeled source lesions dataset and unlabeled target diseases dataset is developed.
- Toward Unified Token Learning for Vision-Language Tracking136
A simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task, and the design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling.
- Learning to Filter: Siamese Relation Network for Robust Tracking134
A novel Siamese relation network is proposed, which introduces two efficient modules, i.e. Relation Detector (RD) and Refinement Module (RM), which performs in a meta-learning way to obtain a learning ability to filter the distractors from the background while RM aims to effectively integrate the proposed RD into theSiamese framework to generate accurate tracking result.
- 130
- The Ninth Visual Object Tracking VOT2021 Challenge Results127
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative; results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years.
- Learning Modality-Consistency Feature Templates: A Robust RGB-Infrared Tracking System123
A new tracking system, which aims to combine the information from RGB and infrared modalities for object tracking, based on the proposed machine learning model that can alleviate the modality discrepancy issue under the proposed modality consistency constraint.
- 113
- 107
- CNNTracker: Online discriminative object tracking via deep convolutional neural network104
A deep learning architecture to learn the most discriminative features dynamically via a convolutional neural network (CNN) to enhance the discrim inative ability of the appearance model in three-fold is proposed.
- 104
- Trajectory Privacy Preservation Based on a Fog Structure for Cloud Location Services97
A fog structure to store partial important data with the dummy anonymity technology to ensure physical control, which can be considered as absolutely trust is proposed.
- 95
- 92
- 87
- 87
- 80
- 72
- Representative Task Self-Selection for Flexible Clustered Lifelong Learning68
This work proposes a novel incremental clustered lifelong learning framework with two knowledge libraries: feature learning library and model knowledge library, called Flexible Clustered Lifelong Learning (FCL3), and evaluates the proposed framework by analyzing several multitask data sets.
- Visualizing and Understanding Patch Interactions in Vision Transformer67
This work proposes a novel explainable visualization approach to analyze and interpret the crucial attention interactions among patches for ViT, and introduces a quantification indicator to measure the impact of patch interaction and verify such quantification on attention window design and indiscriminative patches removal.
- 65
- Towards Universal Modal Tracking With Online Dense Temporal Token Learning63
This work proposes a universal video-level modality-awareness tracking model with online dense temporal token learning (called UM-ODTrack), designed to support various tracking tasks, utilizing the same model architecture and parameters, and introduces two simple yet effective online dense temporal token association mechanisms.
- Perceptual Hashing With Complementary Color Wavelet Transform and Compressed Sensing for Reduced-Reference Image Quality Assessment61
Experimental results demonstrate that the proposed hashing is superior to some state-of-the-art algorithms in terms of classification and RR IQA application.
- Mining flickr landmarks by modeling reconstruction sparsity60
The main idea is to regard the landmark mining problem as a process to find photos whose visual signatures can be reconstructed using other photos of this landmark region with a minimal coding length, and a sparse reconstruction scheme offers a general perspective to mine the representative photos.
- 56
- 54
- Projection & Probability-Driven Black-Box Attack54
This paper proposes Projection & Probability-driven Black-box Attack (PPBA), a method to tackle the problem of generating adversarial examples in a black-box setting by reducing the solution space and providing better optimization.
- Exploring Decoupled Spatio-Temporal Consistency Learning and Self-Prompting Evolution for Self-Supervised Tracking51
This work designs an effective weak-to-strong self-supervised training framework that aims to narrow the feature distribution gap between labeled and unlabeled frames, and enables SSTrack++ to not only learn a generalizable tracking representation in a low-annotation self-supervised manner, but also makes it possible to simulate realistic appearance and motion variations of target instances in real-world scenarios.
- Escherichia Coli DNA N-4-Methycytosine Site Prediction Accuracy Improved by Light Gradient Boosting Machine Feature Selection Technology51
A t-distributed stochastic neighbor embedding analysis confirmed that the prediction performance enhancement of iEC4mC-SVM was due to the light gradient boosting machine feature selection.
- 49
- 49
- 46
- 44
- A Survey on Human Pose Estimation44
While the focus of this study is on approaches using depth and RGB image data, it also discusses human pose estimation methods based on object detection and action recognition and gives some analysis advice to researchers.
- 44
- Long-Range Feature Propagating for Natural Image Matting41
This work proposes Long-Range Feature Propagating Network (LFPNet), which learns the long-range context features outside the reception fields for alpha matte estimation and presents Center-Surround Pyramid Pooling (CSPP) that explicitly propagates the context features from the surrounding context image patch to the inner center image patch.
- Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy39
This work proposes a two-task tracking framework (named DMTrack), which utilizes two core components to achieve distractor-aware fast tracking via Dynamic convolutions (d-convs) and Multiple object tracking (MOT) philosophy, and constructs a lightweight one-shot detector using a novel dynamic convolutions generation method.
- Structured and Sparse Annotations for Image Emotion Distribution Learning37
A convolutional neural network based framework called Structured and Sparse annotations for image emotion Distribution Learning (SSDL) to tackle two challenges: structured and sparse annotations for predicting emotion distribution and sparse regularization for handling sparse annotations.
- 36
- 35
- Unifying Dual-Attention and Siamese Transformer Network for Full-Reference Image Quality Assessment35
The proposed UniDASTN outperforms some state-of-the-art FR-IQA methods on the LIVE, CSIQ, TID2013, and PIPAL databases and can offer stable training and thus enables the proposed UnidASTN to effectively learn visual perceptual image quality.
- 35
- Conditional GAN based individual and global motion fusion for multiple object tracking in UAV videos35
A Conditional Generative Adversarial Networks (GAN) based model is proposed to predict complex motions in UAV videos and robust motion prediction and improved MOT performance are achieved compared with state-of-the-art methods.
- Dynamic Updates for Language Adaptation in Visual-Language Tracking34
A novel vision-language tracking framework, named DUTrack, which captures the latest state of the target by dynamically updating multimodal references to maintain consistency and achieves new state-of-the-art performance on five mainstream vision-language and two vision-only tracking benchmarks.
- 3D object tracking via image sets and depth-based occlusion detection34
A novel 3D object tracking method using image sets and depth-based occlusion detection, in which each training and testing example contains a set of image instances of an object and covers large variations in the object?s appearance.
- 33
- 32
- 31
- Kernel correlation filters for visual tracking with adaptive fusion of heterogeneous cues29
This paper proposes a correlation filter-based tracker by adaptively fusing the heterogeneous cues to effectively handle the scale variation and the drifting problem, and successfully tracked the targets in about 90% videos and outperformed the state-of-the-art trackers.
- MambaLCT: Boosting Tracking via Long-term Context State Space Model28
The advantage of MambaLCT is its ability to continuously extend the length of the context, capturing complete target change cues, which enhances the stability and robustness of the tracker, and enhances the model's ability to perceive targets in complex scenarios.
- Online Non-Negative Multi-Modality Feature Template Learning for RGB-Assisted Infrared Tracking28
An infrared tracking framework in which information from RGB-modality will be exploited to assist the infrared object tracking, and an online non-negative feature template learning model is designed in order to deal with the contaminated features caused by large appearance variations.
- Robust infrared target tracking based on particle filter with embedded saliency detection28
Experimental results on AMCOM FLIR sequences and comparisons with the state-of-the-art methods demonstrate that the proposed tracking method is robust to appearance changes as well as drastic abrupt motions.
- 26
- 26
- 25
- 25
- Robust tracking via patch-based appearance model and local background estimation25
This paper presents a local spatial co-occurrence based background modeling approach to automatically estimate the local context background model of an interested object captured from a single camera, which may be stationary or moving.
- 23
- 22
- Hearing like Seeing20
A novel adversarial deep semantic matching network for efficient voice-face interactions and associations is presented, which can well learn the correspondence between voices and faces for various cross-modal matching and retrieval tasks.
- Extracting Target Detection Knowledge Based on Spatiotemporal Information in Wireless Sensor Networks20
A more realistic signal model is utilized and a probabilistic detection algorithm in which all sensors' local measurement values are fully used is proposed, which makes the most of spatiotemporal information to obtain the final decision.
- 20
- 19
- 19
- 18
- 18
- 18
- 17
- Structured partial least squares for simultaneous object tracking and segmentation17
This paper proposes a novel method to address this limitation by incorporating structured labeling information in the partial least square analysis algorithms for simultaneous object tracking and segmentation, which allows for novel structured labeling constraints to be placed directly on the tracked objects to provide useful contour constraint to alleviate the drifting problem.
- 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.
- 16
- 16
- 16
- Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking14
A decoupled spatio-temporal consistency training framework is proposed to learn rich target information across timestamps through global spatial localization and local temporal association, which allows for the simulation of appearance and motion variations of instances in real-world scenarios.
- 14
- Background subtraction driven seeds selection for moving objects segmentation and matting14
This paper proposes a new automatic way to integrate a background subtraction (BGS) and an alpha matting technique via a heuristic seeds selection scheme, and demonstrates the efficiency and effectiveness of this method.
- 14
- Real-time video dehazing via incremental transmission learning and spatial-temporally coherent regularization13
The experimental results show that the proposed video dehazing approach is able to well preserve the spatial-temporal coherence, runs sufficiently fast, and also performs favorably compared to the state-of-the-art methods.
- Maximizing real-time streaming services based on a multi-servers networking framework13
A novel multi-server based framework is proposed that multiple servers collaborate with each other to form a virtual server, and provide high-quality services such as real-time streams delivery and storage, and an algorithm is proposed to implement backups and maximize streaming flows simultaneously.
- 12
- 12
- 12
- 12
- DRNet: Towards fast, accurate and practical dish recognition12
This paper proposes a practical two-stage dish recognition framework (DRNet) that yields a tradeoff between speed and accuracy while adapting to the variation in class numbers.
- LRDNN: Local-refining based Deep Neural Network for Person Re-Identification with Attribute Discerning12
A Local-refining based Deep Neural Network (LRDNN) is proposed to aggregate pose estimation and attribute recognition to improve the re-ID performance and diminish the negative affect from unstable pose estimation.
- Localization-Aware Meta Tracker Guided With Adversarial Features12
This paper designs a novel intersection over union guided method to effectively balance the problem of classification and localization accuracy and creatively use adversarial features during offline training phase to improve the robustness of the classifier.
- Online learning 3D context for robust visual tracking12
A3D context-based object tracking method that learns a set of 3D context key-points, which have spatial–temporal co-occurrence correlations with the tracked object, for collaborative tracking in binocular video data is proposed.
- 11
- Unambiguous Object Tracking by Exploiting Target Cues11
UTrack is proposed, a simple and effective algorithm for unambiguous object tracking that uses the refined template to obtain more detailed information about the target and better understand which pixels belong to the target.
- End-to-End Human Instance Matting11
A novel End-to-End Human Instance Matting (E2E-HIM) framework for simultaneous multiple instance matting in a more efficient manner and a large-scale human instance matting dataset comprising over 100,000 human images with instance alpha matte labels is constructed.
- Local Spatial Co-occurrence for Background Subtraction via Adaptive Binned Kernel Estimation11
A nonparametric background subtraction method that uses the local spatial co-occurrence correlations between neighboring pixels to robustly and efficiently detect moving objects in dynamic scenes is presented.
- 10
- 10
- 10
- 9
- Explicit Context Reasoning with Supervision for Visual Tracking8
RSTrack is proposed, which explicitly models and supervises context reasoning via three core mechanisms, and achieves state-of-the-art performance on multiple benchmark datasets while maintaining real-time running speeds.
- RGB+2D skeleton: local hand-crafted and 3D convolution feature coding for action recognition8
A new RGB video and 2D skeleton-based action recognition method including local joint trajectory volume representation and feature coding, which shows that skeleton joint-based features result in a more compact and effective action representation approach than other approaches.
- Semi-supervised discrete hashing for efficient cross-modal retrieval8
The proposed SSDH approach utilizes the relaxed hash representations to characterize each modality, and learns the semi-supervised semantic-preserving regularization to correlate the semantic consistency between the heterogeneous modalities.
- 8
- An effective unconstrained correlation filter and its kernelization for face recognition8
A non- linear extension of UOOTF based on the kernel technique allows for higher flexibility of the decision boundary due to a wider range of non-linearity properties and to handle non-linearly separable distributions between different classes.
- Local Histogram of Figure/Ground Segmentations for Dynamic Background Subtraction8
A novel feature, local histogram of figure/ground segmentations, is proposed for robust and efficient background subtraction (BGS) in dynamic scenes (e.g., waving trees, ripples in water, illumination changes, camera jitters, etc.).
- 7
- Robust Individual-Cell/Object Tracking via PCANet Deep Network in Biomedicine and Computer Vision7
This paper proposes a robust feature learning method for constructing discriminative appearance models without large-scale pretraining, and develops a novel algorithm to represent a target by composing of a PCA-based filter bank layer, a nonlinear layer, and a patch-based pooling layer.
- Multi-surface analysis for human action recognition in video7
This paper proposes a novel multi-surface video analysis strategy that combines three-surface motion feature (3SMF), which is extracted from the motion history image in three different video surfaces: horizontal–vertical, horizontal- and vertical-time surface.
- 6
- A Hierarchical Heterogeneous Graph Attention Network for Emotion-Cause Pair Extraction6
A novel hierarchical heterogeneous graph attention network to model global semantic relations among nodes and introduces all types of semantic elements involved in the ECPE, not just clauses or clause pairs.
- Robust Long-Term Tracking via Localizing Occluders6
This work proposes a novel occluder-aware representation learning framework, which works on the principle that discriminates the non-noumenal part from a target based on the general knowledge of this category, and designs a local occluders detection module (LODM) to localize the occludes.
- 6
- Efficient Audio-Visual Speaker Recognition via Deep Heterogeneous Feature Fusion6
This paper exploits a dual-branch deep convolutional neural networks (CNN) learning framework to extract and fuse the high-level semantic features of face and audio data and embeds the fused features into a bidirectional Long Short-Term Memory (LSTM) networks to produce recognition result.
- Automatic facial flaw detection and retouching via discriminative structure tensor6
This study proposes an efficient approach to automatically detect and retouch the facial flaws by using discriminative structure tensor and proposes a structure Tensor-based inpainting algorithm to retouched the detected flaws.
- Sparse Representation-Based Semi-Supervised Regression for People Counting6
A sparse representation-based semi-supervised regression method is proposed to count people in images with limited data and has a low mean square error and mean absolute error compared with those of state-of-the-art people-counting benchmarks.
- Jointly Feature Learning and Selection for Robust Tracking via a Gating Mechanism6
This work proposes a novel visual tracking method via a point-wise gated convolutional deep network (CPGDN) that jointly performs the feature learning and feature selection in a unified framework and combines an edge box-based object proposal method to further improve the tracking accuracy.
- Network in network based weakly supervised learning for visual tracking6
This work designs a simple yet effective method to transfer the mid-level features learned from NIN on the source tasks with large scale training data to the tracking tasks with limited training data and uses a heuristic schema to judge whether updating the object appearance model or not.
- 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.
- 6
- Texture and Motion Pattern Fusion for Background Subtraction6
A novel background subtraction algorithm, which takes both texture and motion information into account, and combines the texture pattern- based and motion pattern-based background model.
- 5
- 5
- 5
- 5
- 5
- 5
- Combined Improved Dirichlet Models and Deep Learning Models for Road Extraction from Remote Sensing Images5
An improved DMM is proposed which embeds superpixel strategy and sparse representation into DMM and can achieve better results than other compared state-of-the-art image segmentation methods, but the processing speed and accuracy of DMM are also improved.
- Identification of Anti-cancer Peptides Based on Multi-classifier System5
A multi-classifier system, which combining multiple machine learning models, to predict anti-cancer peptides, which shows that the overall prediction rate of each individual learner is above 80% and the overall accuracy can reach 95.93%, which is better than the existing prediction model.
- Probability‐based method for boosting human action recognition using scene context5
This study model a scene as a mid-level `middle layer' in order to bridge action descriptors and action categories via a scene topic model, in which hybrid visual descriptors, including spatial-temporal action features and scene descriptors are first extracted from a video sequence.
- 5
- 4
- Motion-Aware Object Tracking via Motion and Geometry-Aware Cues4
A motion-aware spatio-temporal framework that enhances motion perception by explicitly matching motion patterns and modeling inter-frame motion relationships and embeds geometric cues into the search region features, which strengthens spatial perception, reduces ambiguity under occlusion, and improves foreground-background separation.
- Vision-language discriminative fusion network for object tracking4
A multimodal discriminative fusion module is proposed, which innovatively adopts a cross-utilization strategy, combining multimodal discriminative attention (MDA) with multi-head attention (MDA) with multi-head attention, and is committed to exploring the consistency among multimodal relevant vectors.
- 4
- 4
- Convolutional Deep Belief Networks for Single-Cell/Object Tracking in Computational Biology and Computer Vision4
Deep architecture to dynamically learn the most discriminative features from data for both single-cell and object tracking in computational biology and computer vision is proposed and a simple yet effective method to transfer features learned on the source tasks for generic purpose to the object tracking tasks using only limited amount of training data is designed.
- 4
- Detecting Targets Based on a Realistic Detection and Decision Model in Wireless Sensor Networks4
This work utilizes a realistic signal model and a probabilistic decision model to describe the sensing process of sensors as well as to make the final decision and proposes a realistic decision algorithm in which local signal measurements of sensors are converted to corresponding local detection probabilities in order to make a rational final decision.
- A Novel Unconstrained Correlation Filter and Its Application in Face Recognition4
A novel unconstrained correlation filter called Unconstrained Optimal Origin Tradeoff Filter (UOOTF) is presented and applied to face recognition, which increases the overall performance for unseen patterns by removing the hard constraints on the outputs during the filter design.
- 4
- Aware Distillation for Robust Vision-Language Tracking Under Linguistic Sparsity3
A knowledge distillation framework employing a knowledge-rich teacher model and a lightweight student model to establish modality correlations between vision and language, enabling efficient modeling between visual information and language descriptions, and simulating language-deficient conditions during training and contrastive learning to enhance model adaptability.
- 3
- 3
- Robust feature learning for online discriminative tracking without large-scale pre-training3
This paper designs a PCA filter bank-based convolutional neural network architecture to learn robust features online with a few positive and negative samples in the high-dimensional feature space and uses a simple soft-thresholding method to produce sparse features that are more robust to target appearance variations.
- 2
- 2
- 2
- Coded Caching for Combination Networks with Multiaccess2
Theoretical and numerical analysis shows that the direct scheme and the hybrid scheme have a smaller transmission load for each relay compared with the naive scheme and have much lower subpacketizationCompared with the ZY scheme.
- Medical Image Segmentation Based on Spatially Constrained Inverted Beta-Liouville Mixture Models2
A variational Bayes inference algorithm is developed to learn the proposed model, such that model parameters can be efficiently estimated in closed form and the spatial relationship among nearby pixels is imposed into the model by using generalized means.
- 2
- Automatic Character Motion Style Transfer via Autoencoder Generative Model and Spatio-Temporal Correlation Mining2
This paper presents an efficient approach to automatically transfer motion style by using autoencoder generative model and spatio-temporal correlation mining, which allows users to transform an input motion into a new style while preserving its original content.
- 2
- 2
- MUTrack: A Memory-Aware Unified Representation Framework for Visual Tracking1
This work designs a unified memory bank that stores and manages long-term memory for maintaining long-term identity consistency, and short-term memory for adapting to instantaneous appearance changes, and introduces a perception interaction module that dynamically fuses these memory types through deep and bidirectional interactions.
- 1
- UBATrack: Spatio-Temporal State Space Model for General Multi-Modal Tracking1
This work introduces a novel multi-modal tracking framework based on a mamba-style state space model, termed UBATrack, which outperforms state-of-the-art methods on RGB-T, RGB-D, and RGB-E tracking benchmarks, and enhances multi-modal representation capacity across multiple feature dimensions to improve tracking robustness.
- 1
- Learning to Track Instance from Single Nature Language Description1
This work introduces a novel self-supervised VL tracker that is capable of tracking any referred object by a language description, and proposes an efficient Dynamic Token Aggregation Module, which treats each visual token unequally.
- An Efficient Token Compression Framework for Visual Object Tracking1
This work proposes a compress-then-interact tracking framework, ETCTrack, that learns to efficiently compress template tokens from historical template frames into a robust target representation, moving beyond handcrafted rules.
- Boosting Self-Supervised Tracking with Contextual Prompts and Noise Learning1
This work proposes a novel self-supervised tracking framework, named Tracker, which introduces a dual-modal context association mechanism that jointly leverages fine-grained semantic prompts and contextual noise to drive the model toward learning robust tracking representations.
- Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-Tuning and Modality Fusion Prompt Generation1
This work proposes an efficient Visual Fourier Prompt Tracking (named VFPTrack) method to learn modality-related prompts via Fast Fourier Transform (FFT) that generates bidirectional interaction prompts through multi-modal feature fusion.
- 1
- Robust Tracking via Unifying Pretrain-Finetuning and Visual Prompt Tuning1
A novel partial finetuning paradigm for visual tracking via unifying pretrain-finetuning and visual prompt tuning (named UPVPT), which can not only efficiently learn knowledge from the tracking task but also reuse the prior knowledge learned by the pre-trained model for effectively handling various challenges in tracking task.
- 1
- 1
- Efficient Cross-modal Retrieval via Discriminative Deep Correspondence Model1
This paper proposes a discriminative deep correspondence model that attempts to seamlessly combine the correspondence autoencoder (Corr-AE) and supervised correspondence neural networks (Super- Corr-NN) for cross-modal matching.
- A Sparse Representation Algorithm for Effective Photograph Retrieval1
Experimental results demonstrate that if the similarity vector in photograph retrieval is sparse, feature extraction is no longer critical and the proposed method has better retrieval accuracy.
- Coarse-to-fine visual tracking with PSR and scale driven expert-switching1
A coarse-to-fine tracker which integrates a kernelized correlation filter (KCF) based tracker with detection proposal and a multi-expert based tracker via a simple yet effective Peak to Sidelobe Ratio (PSR) and scale driven schema is proposed.
- 1
- Higher order partial least squares for object tracking: A 4D-tracking method1
This paper proposes a novel 4D object tracking method via the higher order partial least squares (HOPLS) which is a generalized multi-linear regression method and uses HOPLS to adaptively learn low-dimensional discriminative feature subspace for object representation.
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- Dual-branch Distilled Transformer for Efficient Asymmetric UAV Tracking–
EATrack is an efficient and asymmetric UAV tracking framework centered around a teacher-guided dual-branch distillation strategy that enhances the feature expressiveness of the lightweight student model and introduces a fine-grained target-aware distillation strategy that selectively transfers the teacher's target modeling capacity to the student.
- –
- –
- –
- –
- –
- –
- –
- –
- Co-Inference Discriminative Tracking Through Multi-Task Siamese Network–
A multi-stage co-inference tracker via a multi-task Siamese network, in which a complicated tracking task is divided into three complementary sub-tasks, that can avoid the pitfalls of purely single components and get reliably observations to improve its adaptive power.
- Efficient Human Motion Transition via Hybrid Deep Neural Network and Reliable Motion Graph Mining–
A hybrid deep learning framework that allows for flexible and efficient human motion transition from motion capture (mocap) data, which optimally satisfies the diverse user-specified paths is proposed.
- A Semantic Mapping Method based on Ontology Structure Graph–
A semantic mapping method based on ontology structure graph is put forward to solve the problem of semantic clash between enterprise models and the formalization of semantic mapping rules is presented to support semantic mapping process from enterprise model to ontology.
- –
- A New Method Based on Wavelet Transform for Taking Instantaneous EEG–
The experiment shows that this method based on wavelet transform of taking instantaneous EEG is convenient and efficient to test instantaneous EEG and take the parameters.
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.