Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks342 from public data
- 509
- 340
- 336
- 209
- Hyperspectral Image Classification in the Presence of Noisy Labels203
Experimental studies show that the RLPA can reduce the level of noisy label and demonstrates the advantages of the proposed method over four major classifiers with a significant margin—the gains in terms of the average overall accuracy, average accuracy, and kappa are impressive.
- 192
- Physical Adversarial Attack Meets Computer Vision: A Decade Survey169
A comprehensive overview of physical adversarial attacks is presented and a proposed evaluation metric, hiPAA, comprises six perspectives: Effectiveness, Stealthiness, Robustness, Practicability, Aesthetics, and Economics.
- 161
- 155
- 149
- 144
- Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes139
This paper proposes a Semantic Guidance and Evaluation Network (SGE-Net) to iteratively update the structural priors and the inpainted image in an interplay framework of semantics extraction and image inpainting, which utilizes semantic segmentation map as guidance in each scale of inPainting.
- 129
- Cascaded SR-GAN for Scale-Adaptive Low Resolution Person Re-identification123
A unified formulation, a Cascaded Super-Resolution GAN (CSR-GAN) framework is proposed, which requires a network not only synthesizing high-resolution images with different upscaling factors, but also extracting discriminative image feature for judging person’s identity.
- Image Inpainting Guided by Coherence Priors of Semantics and Textures118
A multi-scale joint optimization framework is adopted to first model the coherence priors and then accordingly interleaving optimize image inpainting and semantic segmentation in a coarse-to-fine manner and two coherence losses are proposed to constrain the consistency between the semantics and the inpainted image in terms of the overall structure and detailed textures.
- Batch mode active sampling based on marginal probability distribution matching114
A novel criterion is proposed which achieves good generalization performance of a classifier by specifically selecting a set of query samples that minimizes the difference in distribution between the labeled and the unlabeled data, after annotation.
- 109
- Magic ELF: Image Deraining Meets Association Learning and Transformer102
This paper aims to unify CNN and Transformer to take advantage of their learning merits for image deraining, and introduces degradation prior to help background recovery and presents the association refinement deraining scheme.
- 97
- 88
- Learning Sparse and Identity-Preserved Hidden Attributes for Person Re-Identification82
This work proposes to incrementally generate Deep Hidden Attribute (DHA) based on baseline deep network for newly uncovered annotations based on an auto-encoder model that can be plugged into any deep network to mine latent information in an unsupervised manner.
- Classroom Learning Status Assessment Based on Deep Learning78
A deep learning-based student classroom behavior recognition method, which extracts the key information of the human skeleton from student behavior images and combines a 10-layer deep convolutional neural network (CNN-10) to recognize students’ classroom behavior.
- 77
- Identifying Influenza Viruses with Resequencing Microarrays76
Resequencing microarrays rapidly identify influenza viruses and provide real-time information about circulating and novel viruses that pose a threat to human health.
- MIMR-DGSA: Unsupervised hyperspectral band selection based on information theory and a modified discrete gravitational search algorithm75
A MIMR-DGSA algorithm for band selection is proposed by following the Maximum-Information-Minimum-Redundancy (MIMR) criterion that maximises the information carried by individual features of a subset and minimises redundant information between them.
- Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding72
A unified framework to disentangle the style factor and the fog factor separately, and then the dual-factor from images in different domains is devised, which achieves the state-of-the-art performance on three benchmarks and shows generalization ability in rainy and snowy scenes.
- Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification69
This paper provides a comprehensive review of state-of-the-art Hetero-ReID methods that address the challenge of inter-modality discrepancies and compares the representative approaches from two perspectives, i.e., the application scenario and the learning pipeline.
- Context-Enhanced Stereo Transformer68
This work constructs their stereo depth estimation model, Context Enhanced Stereo Transformer (CSTR), by plugging CEP into the state-of-the-art stereo depth estimating method Stereotransformer, and finds CSTR outperforms prior approaches by a large margin.
- Degrade Is Upgrade: Learning Degradation for Low-Light Image Enhancement68
A novel two-step generation network for degradation learning and content refinement, which is not only superior to one-step methods, but also capable of synthesizing sufficient paired samples to benefit the model training.
- 65
- DAWN: Direction-aware Attention Wavelet Network for Image Deraining61
A novel Direction-aware Attention Wavelet Network (DAWN) for rain streaks removal that delivers significant performance gains on nine datasets across image deraining and object detection tasks, exceeding the state-of-the-art method MPRNet by 0.88 dB in PSNR on the Test1200 dataset.
- Equidistance constrained metric learning for person re-identification61
An algorithm for learning a Mahalanobis distance for person re-identification that outperforms the state-of-the-art methods on CUHK01, CUHK03, Market1501 and DukeMTMC-reID datasets, and achieves very competitive performance on the widely used VIPeR dataset.
- 60
- Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval58
This paper investigates an extremely challenging task: given a ground-view image of a landmark, it aims to achieve cross-view geo-localization by searching out its corresponding satellite-view images, and proposes a Peer Learning and Cross Diffusion (PLCD) framework.
- 57
- 57
- Ranking Optimization for Person Re-identification via Similarity and Dissimilarity56
This paper proposes to use both similarity and dissimilarity cues in a ranking optimization framework for person re-identification, based on the phenomenon that the true match should not only be similar to theStrong similar samples of the probe but also dissimilar to the strong dissimilar samples.
- Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer52
This paper introduces an iterative self-supervised learning scheme with regression-detection bi-knowledge transfer in the target and formulate the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge distillation between the two models.
- Rainy WCity: A Real Rainfall Dataset with Diverse Conditions for Semantic Driving Scene Understanding50
A real, comprehensive, and well-annotated scene understanding dataset under rainy weather, named Rainy WCity is pioneer, which covers various rain patterns and their bring-in negative visual effects and an unsupervised contrastive learning network for real image deraining and the final rainy scene semantic segmentation via multi-task joint optimization is designed.
- 47
- 47
- Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning46
A one-stage based Cycle-projected Mutual learning network (CycMu-Net) for ST-VSR is proposed, which makes full use of spatial-temporal correlations via the mutual learning between S-V SR and T-vSR, to exploit the mutual information among them via iterative up-and-down projections.
- 45
- Automated detection and identification of white-backed planthoppers in paddy fields using image processing45
A new three-layer detection method was proposed to detect and identify white-backed planthoppers (WBPHs, Sogatella furcifera (Horvath) and their developmental stages using image processing.
- Coupled-View Based Ranking Optimization for Person Re-identification45
A coupled-view based ranking optimization method through cross KNN rank aggregation and graph-based re-ranking to revise the original ranking lists based on the core assumption that the images of the same person should share the similar visual appearance in both global and local views.
- What’s Wrong with the Murals at the Mogao Grottoes: A Near-Infrared Hyperspectral Imaging Method44
Evaluating the degree of flaking in the Mogao Grottoes by automatically analyzing hyperspectral images that were scanned at the site shows the effectiveness of the method, and better results are obtained using DBNs when the training data contain a significant amount of striping noise.
- 41
- 40
- 39
- Rank-in-Rank Loss for Person Re-identification38
Extensive experimental results indicate that the proposed Differentiable Retrieval-Sort Loss (DRSL) can improve the performance of the state-of-the-art re-ID models, thus demonstrating its effectiveness and superiority in the re- ID task.
- 38
- Camera Network Based Person Re-identification by Leveraging Spatial-Temporal Constraint and Multiple Cameras Relations38
Quantitative experiments conducted on TMin and CamNeT datasets have shown that the proposed probabilistic method achieves a better performance to the novel CNPR problem.
- Specific Person Retrieval via Incomplete Text Description38
A specific attribute completion is conducted to enrich the original text query and generate a more expressive attribute vector and a pairwise-based metric learning is introduced for completed attribute vectors.
- Modal-aware Visual Prompting for Incomplete Multi-modal Brain Tumor Segmentation37
This work introduces a novel incomplete multi-modal segmentation framework called Modal-aware Visual Prompting (MAVP), which draws inspiration from the widely used pre-training and prompt adjustment protocol employed in natural language processing (NLP), and utilizes embeddings as the prompts generated by a modality state classifier that focuses on the missing modality states.
- Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion37
A novel Target-Domain driven pseudo label Diffusion (TDo-Dif) scheme that employs superpixels and optical flows to identify the spatial similarity and temporal correspondence of the sequential image data, and diffuses the confident but sparse pseudo labels within a superpixel or a temporal corresponding pair linked by the flow.
- Instance-Level Heterogeneous Domain Adaptation for Limited-Labeled Sketch-to-Photo Retrieval37
Experiments show that the proposed Instance-level Heterogeneous Domain Adaptation framework has set a new state of the art on three sketch-to-photo image retrieval benchmarks without extra annotations, which opens the door to train more effective models on limited-labeled heterogeneous image retrieval tasks.
- Point to Rectangle Matching for Image Text Retrieval36
This work proposes a Point to Rectangle Matching mechanism, which actually is a geometric representation learning method for image-text retrieval, and intuitive insight is that the representations of different modalities could be extended to rectangles, then a set of points inside a rectangle embedding could be semantically related to many candidate correspondences.
- 36
- DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting35
This work proposes a Domain-agnostically Aligned Optimal Transport (DAOT) strategy that aligns domain-agnostic factors between domains and demonstrates that the proposed method has strong generalizability across diverse datasets.
- Mining on Heterogeneous Manifolds for Zero-Shot Cross-Modal Image Retrieval35
This work proposes a bi-directional random walk scheme to mining more reliable relationships between images by traversing heterogeneous manifolds in the feature space of each modality to alleviate the interference caused by noisy similarities in the cross-modal feature space.
- Fine-Grained Fragment Diffusion for Cross Domain Crowd Counting34
A cross- domain Fine-Grained Fragment Diffusion model (FGFD) is proposed that explores feature-level fine-grained similarities of crowd distributions between different fragments to bridge the cross-domain gap (content-level coarse- grained dissimilarities).
- 34
- Multi-Scale Fast Fourier Transform Based Attention Network for Remote-Sensing Image Super-Resolution33
This work proposes a multiscale fast Fourier transform (FFT) based attention network (MSFFTAN), which employs a multiinput U-shape structure as backbone for accurate RSSR and carefully design an FFT-based residual block consisting of an image domain branch and a Fourier domain branch to extract local details and global structures simultaneously.
- The 3rd Anti-UAV Workshop & Challenge: Methods and Results32
A brief summary of the 3rd Anti-UAV Workshop&Challenge is provided including brief introductions to the top three methods in each track including brief introduction to the bottom three methods.
- When Pedestrian Detection Meets Nighttime Surveillance: A New Benchmark32
This paper builds a novel pedestrian detection dataset from the nighttime surveillance aspect, and compares the performances of state-of-the-art pedestrian detectors and reveals that the methods cannot solve all the challenging problems of NightSurveillance.
- Benchmarking Deep Networks for Predicting Residue-Specific Quality of Individual Protein Models in CASP1132
Four novel single-model methods based on stacked denoising autoencoders (SdAs) and support vector machines (SVMs) with better performance than most of the six other CASP11 methods in distinguishing the reliably modeled residues from the unreliable measured by ROC analysis are developed.
- 31
- Video-Based Person Re-Identification via Self Paced Weighting31
A novel video-based person re-id method via self paced weighting (SPW) is proposed, which proposes a self paced outlier detection method to evaluate the noise degree of video sub sequences and a weighted multi-pair distance metric learning approach is adopted to measure the distance of two person image sequences.
- Region-Based Interactive Ranking Optimization for Person Re-identification31
This paper proposes a region-based interactive ranking optimization method, to improve the original query result by labeling locally similar and dissimilar image regions in the person re-identification problem, and proves that the ranking optimization algorithm is both an effective and efficient method.
- Ensemble Super-Resolution With a Reference Dataset30
This paper presents a simple but effective single image SR method based on ensemble learning, which can produce a better performance than that could be obtained from any of SR methods to be ensembled (or called component super-resolvers).
- 29
- 29
- DANet: Image Deraining via Dynamic Association Learning28
This work proposes a dynamic associated network (DANet) to achieve the association learning between rain streak removal and background recovery, and introduces the parametric association constraint for enhancing the compatibility of deraining model with background reconstruction.
- 28
- CCS-GAN: a semi-supervised generative adversarial network for image classification28
A novel CCS-GAN model for semi-supervised image classification, which aims to improve its classification ability by utilizing the cluster structure of unlabeled images and ’bad’ generated images and adopts an enhanced feature matching approach to encourage its generator to produce adversarial images from the low-density regions of real distribution.
- 27
- Visible-Infrared Person Re-Identification: A Comprehensive Survey and a New Setting27
This paper provides a complete overview of current VI-ReID approaches that employ deep learning algorithms, and compares ReID with VI- re-identification in three aspects, including data composition, challenges, and performance.
- 27
- FedPFT: Federated Proxy Fine-Tuning of Foundation Models26
This paper proposes Feder- ated Proxy Fine-Tuning (FedPFT), a novel method enhancing FMs adaptation in downstream tasks through FL by two key modules, facilitating comprehensive FM fine-tuning across all layers by emphasizing those crucial neurons.
- An Aggregation-Induced Emission Material Labeling Antigen-Based Lateral Flow Immunoassay Strip for Rapid Detection of Escherichia coli O157:H726
A lateral flow immunoassay strip based on aggregation-induced emission material labeling antigen as a fluorescent probe for the rapid detection of E. coli O157:H7 is reported, which has good specificity and stability and might be valuable in monitoring food pathogens for rapid detection.
- Application of Quantum—Markov Open System Models to Human Cognition and Decision26
The purpose of this article is to formulate open system models that have good potential to make important advancements in cognitive science and address some of the constraints required for achieving this goal.
- 25
- Development of an antigen-capture ELISA for the detection of equine influenza virus nucleoprotein25
An antigen-capture enzyme-linked immunosorbent assay (AC-ELISA) was developed for the detection of the equine influenza virus (EIV), employing monoclonal and polyclonal antibodies against the H3N8 nucleoprotein (NP).
- 24
- 24
- Learning to Attack Real-World Models for Person Re-identification via Virtual-Guided Meta-Learning24
This study argues that learning powerful attackers with high universality that works well on unseen domains is an important step in promoting the robustness of re-ID systems and introduces a novel universal attack algorithm called ``MetaAttack'' for person re- ID.
- 24
- Incremental Deep Hidden Attribute Learning24
This work proposes a new person representation with hidden attributes by mining latent information from visual feature in an unsupervised manner using an auto-encoder model plugged-in to the deep learning network to compose a Deep Hidden Attribute Network (DHA-Net).
- Research on a cloud image forecasting approach for solar power forecasting24
A cloud image forecasting approach to provide a means that can track the cloud deformation process and then forecast the cloud shape and position in a future sky image using linear extrapolation.
- Striking a Balance: Unsupervised Cross-Domain Crowd Counting via Knowledge Diffusion22
A Self-awareness Knowledge Diffusion method (SaKnD) that leverages the self-knowledge without establishing cross-domain knowledge relationships, which aims to balance the knowledge bias between general and domain-specific knowledge.
- Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval22
A non-local (NL) fusion module that gathers sketches from different witnesses for the same identity is proposed and an AttrAlign module utilizes attributes as an implicit mask to align cross-domain features.
- You Only Align Once: Bidirectional Interaction for Spatial-Temporal Video Super-Resolution21
An effective yet efficient recurrent network with bidirectional interaction for ST-VSR, where only one alignment and fusion is needed, and a Hybrid Fusion Module (HFM) is designed to aggregate and distill information to refine spatial information and reconstruct high-quality video frames.
- 21
- 21
- 20
- Correlation Discrepancy Insight Network for Video Re-identification20
A novel correlation discrepancy insight network for video-based person ReID is proposed, which consists of an unsupervised correlation insight model for video purification and a discrepancy description network (DDN) for person representation that outperforms several state-of-the-art methods.
- Learning to rank tags20
A novel semi-supervised learning framework to rank image tags is presented, which learns a ranking projection with theoretic guarantee from visual words distribution to the relevant tags distribution, and then uses it for ranking new image tags.
- 19
- A Survey of Dataset Refinement for Problems in Computer Vision Datasets19
This survey provides a comprehensive and structured overview of recent advances in dataset refinement for problematic computer vision datasets and classifies the dataset refinement algorithms into three categories based on the refinement process: data sampling, data subset selection, and active learning.
- Collaborative Fraud Detection: How Collaboration Impacts Fraud Detection19
A significant positive correlation between the increase of collaborative fraud and the degraded detection performance of traditional techniques is found, implying that those fraudsters that are difficult to detect with traditional methods are often collaborative in their fraudulent behavior.
- Beyond the Parts: Learning Coarse-to-Fine Adaptive Alignment Representation for Person Search19
A Coarse-to-Fine Adaptive Alignment Representation (CFA2R) network for learning multiple granular features in misaligned person search in the coarse- to-fine perspective is proposed and a Part-Attentional Progressive Module (PAPM) is designed to guide the network to focus on informative body parts and positive accessorial regions.
- Sparsity-Based Occlusion Handling Method for Person Re-identification19
A sparsity-based patch matching method using a sparse representation model to determine the occlusion state of each image patch, which is further utilized to adjust the weight of patch pairs in the feature matching process.
- Progressive Spatial-temporal Collaborative Network for Video Frame Interpolation18
This work develops a content-guided motion module (CGMM) and a motion-guided content module (MGCM) for individual content and motion representation, and develops a novel progressive spatial-temporal Collaborative network (Prost-Net) for video frame interpolation.
- Unsupervised Video Person Re-Identification via Noise and Hard Frame Aware Clustering18
Experiments conducted on two video-based datasets demonstrate the effectiveness of the proposed NHAC under the unsupervised re-ID setting.
- 17
- Reference-Guided Texture and Structure Inference for Image Inpainting17
Both quantitative and qualitative evaluations demonstrate the superiority of the method over the state-of-the-art methods in terms of completing complex holes.
- Consistency-Constancy Bi-Knowledge Learning for Pedestrian Detection in Night Surveillance17
A consistency-constancy bi-knowledge learning (CCBL) for pedestrian detection in night surveillance is proposed, which is able to simultaneously achieve the night pedestrian detection's useful knowledge, coming from day and night surveillance.
- Low-altitude protection technology of anti-UAVs based on multisource detection information fusion17
An architecture of intelligent anti-UAVs low-altitude defense system based on multisensor information fusion is proposed, which combines radar and photoelectric information and shows better performance in range, accuracy, and success rate of surveillance.
- 16
- 16
- 16
- 16
- 15
- 15
- 15
- 14
- Location Predicts You: Location Prediction via Bi-direction Speculation and Dual-level Association14
This work proposes a novel Bi-direction Speculation and Dual-level Association method (BSDA), which considers both users' interests in POIs and POIs' appeal to users, and develops the cross-user and cross-POI association to alleviate the data sparsity by similar users and POI to enrich the candidates.
- 14
- Mix-Modality Person Re-Identification: A New and Practical Paradigm13
A Mix-Modality Person Re-Identification (MM-ReID) task is proposed, the influence of modality mixing ratio on performance is explored, and mix-modality test sets for existing datasets are constructed according to the new mix-modality testing paradigm.
- 13
- UniParser: Multi-Human Parsing With Unified Correlation Representation Learning13
By unifying instance-level and category-level output, UniParser circumvents manually designed post-processing techniques and surpasses state-of-the-art methods, achieving 49.3% AP on MHPv2.0 and 60.4% AP on CIHP.
- 13
- 13
- Store and Fetch Immediately: Everything Is All You Need for Space-Time Video Super-resolution13
An immediate storeand-fetch network to promote long-range correlation learning, where the stored information from the past and future can be refetched to help the representation of the current frame.
- Unsupervised Vehicle Search in the Wild13
A new vehicle search dataset is established and an unsupervised framework on this benchmark dataset is designed to generate pseudo labels for further training existing vehicle re-ID or person search models to advance the research of vehicle search.
- Dynamic weighted histogram equalization for contrast enhancement using for Cancer Progression Detection in medical imaging13
The purpose of this research is to devise an intelligently robust framework based on the image data collected during several phases of Ultrasound (US) cancer image by automating the real-time image enhancement, segmentation, classification and progression the widely spreading of cancer disease at initial stages.
- Statistical Inference of Gaussian-Laplace Distribution for Person Verification13
Experiments conducted on a metric learning method by exploiting Gaussian-Laplace distribution statistical inference show its superiority in terms of effectiveness and efficiency as compared with the state-of-the-art approaches, no matter the appearance description is handcrafted or deep learned.
- 12
- Moiré Backdoor Attack (MBA): A Novel Trigger for Pedestrian Detectors in the Physical World12
It is demonstrated that individuals wearing such clothes can effectively evade detection by the backdoored model while wearing regular clothes does not trigger the attack, ensuring the attack remains covert.
- 12
- 12
- Dual-View Ranking with Hardness Assessment for Zero-Shot Learning12
A novel DuAl-view RanKing (DARK) loss for zeroshot learning simultaneously ranking labels for an image by point-to-point metric and ranking images for a label by pointto-set metric is proposed, which is capable of better modeling the relationship between images and classes.
- 11
- Heterophilic Graph Invariant Learning for Out-of-Distribution of Fraud Detection11
The Heterophilic Graph Invariant Learning Framework (HGIF), a novel approach to bolster the OOD generalization of GFD, is introduced, setting a new benchmark for GFD in OOD scenarios.
- Vertex points are not enough: Monocular 3D object detection via intra- and inter-plane constraints11
A novel 3D monocular object detection method to improve the accuracy of detection objects with large differences in deformation by introducing the geometric constraints of the object 3D bounding box plane.
- Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning11
This paper first discover the relationship between micro-behavior and hidden intentions and use graph structure to reason about hidden intentions, and constructed a seminal dataset containing a hidden intention annotation of a typical theft scenario for HID.
- Don't Ignore Alienation and Marginalization: Correlating Fraud Detection11
COFRAUD is proposed, a correlation-aware fraud detection model, which innovatively incorporates synergistic camouflage into fraud detection and captures the correlation among multi-relation fraudulent behaviors.
- 11
- Vehicle Re-Identification with Spatio-Temporal Model Leveraging by Pose View Embedding11
A two-branch framework for vehicle Re-ID is designed, including a Keypoint-based Pose Embedding Visual (KPEV) model and a Key pointed Pose-Guided Spatio-Temporal (KPGST) model, which is integrated into the framework and the results of KPEV and KPGST are fused based on a Bayesian network.
- Beyond fixed time and space: next POI recommendation via multi-grained context and correlation11
This work proposes a novel model for the next POI recommendation via multi-granularity context and correlation, which explores effective spatial-temporal contexts to learn mobility patterns locally and globally by introducing hierarchical regions and slots.
- Effective and Efficient: Toward Open-world Instance Re-identification11
This tutorial would be useful for multimedia content analysis and system-level multimedia retrieval, especially for an effective and efficient open-world ReID system for the practical, large-scale, and open-set domain.
- 11
- 10
- NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval10
This work directly mitigate hubness during training and introduces NeighborRetr, a novel method that effectively balances the learning of hubs and adaptively adjusts the relations of various kinds of neighbors, achieving state-of-the-art results on multiple cross-modal retrieval benchmarks.
- 10
- Efficient virtual data search for annotation‐free vehicle reidentification10
This paper presents a novel data sampling strategy from both semantic and feature levels to perform an effective data search and is among the first attempts to search effective virtual data to perform annotation‐free vehicle re‐ID.
- Progressive Domain Adaptation for Robot Vision Person Re-identification10
This paper demonstrates a guiding robot with person followers system, which recognizes the follower using a person re-identification technology, and first adopts existing face recognition and person tracking methods to generate person tracklets with different IDs.
- 9
- Informative Classes Matter: Towards Unsupervised Domain Adaptive Nighttime Semantic Segmentation9
An Online Informative Class Sampling (OICS) strategy to adaptively mine informative classes from the target nighttime domain according to the corresponding spectrogram mean and the class frequency via the authors' Informative Mixture of Experts framework, which outperforms state-of-the-art UDA-NSS methods by large margins on three widely-used benchmarks.
- 9
- 9
- OPTICS-based Unsupervised Method for Flaking Degree Evaluation on the Murals in Mogao Grottoes9
An unsupervised method to accurately predict the degree of mural flaking diseases in Mogao Grottoes using hyperspectral images and the results show the effectiveness of the proposed method.
- Automated surrogate-assisted particle swarm optimizer with an adaptive parental guidance strategy for expensive engineering optimization problems8
Results demonstrate that AutoSAPSO significantly outperforms state-of-the-art approaches regarding convergence accuracy and robustness, confirming its potential as a general-purpose optimization tool for expensive engineering optimization problems.
- Devil is in Details: Locality-Aware 3D Abdominal CT Volume Generation for Self-Supervised Organ Segmentation8
The Locality-Aware Diffusion (Lad) is introduced, a novel method tailored for exquisite 3D abdominal CT volume generation that design a locality loss to refine crucial anatomical regions and devise a condition extractor to integrate abdominal priori into generation, thereby enabling the generation of large quantities of high-quality abdominal CT volumes essential for SSL tasks without the need for additional data such as labels or radiology reports.
- ELMA: Energy-Based Learning for Multi-Agent Activity Forecasting8
This paper puts forth a novel Energy-based Learning approach for Multi-Agent activity forecasting (ELMA) to estimate this complex model via maximum log-likelihood estimation and proves that ELMA outperforms recent leading studies by an obvious margin.
- 8
- 8
- DeepDirect: Learning Directions of Social Ties with Edge-Based Network Embedding (Extended Abstract)8
- An Edge Detection Method Based on Mathematical Morphology8
The experimental results showed that the proposed novel method of edge detection has better anti-noise effect and the edge extracted is quite smooth.
- Clothing Purification with Causality Meets Vision-Language Pretraining Models7
The Causality-based Purification (CaPu) model constructs a clothing indication pipeline that leverages the unique strengths of multiple VLP models to efficiently capture clothing semantics and achieves state-of-the-art performance.
- 7
- FasterPest: A Multi-Task Classification Model for Rice Pest Recognition7
A multi-task classification model based on the FasterViT network that can identify rice pest species and leaf conditions simultaneously and incorporates a feature fusion module that effectively integrates the base model’s features and the classification heads’ output features using attention mechanisms.
- 7
- 7
- Gaussian-modulated continuous-variable quantum key distribution based on untrusted entanglement source7
Experimental results show that the proposed Gaussian-modulated continuous-variable quantum key distribution scheme can generate secure quantum keys even if the Gaussian entanglement source is untrusted, and the two optical amplifiers can effectively improve the quantum efficiency of the detector at the receiver.
- 7
- 7
- 7
- Universally Unfiltered and Unseen: Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards6
This paper proposes Universally Unfiltered and Unseen (U3)-Attack, a multimodal jailbreak attack method against T2I safeguards that optimizes an adversarial patch on the image background to universally bypass safety checkers and optimizes a safe paraphrase set from a sensitive word to universally bypass prompt filters while eliminating redundant computations.
- A New Dataset and Benchmark for Grounding Multimodal Misinformation6
The task of Grounding Multimodal Misinformation (GroundMM), which verifies multimodal content and localizes misleading segments across modalities, is introduced and the first real-world dataset for this task is presented, featuring a taxonomy of misinformation types, fine-grained annotations across text, speech, and visuals, and validation with Snopes evidence and annotator reasoning.
- Unified Category and Style Generalization for Instance-Level Sketch Retrieval6
The Dual-Attentive Prompt (DAP) method is proposed, which unifies category generalization and style adaptation into a single, interpretable framework and ensures robust generalization of unseen categories while mitigating the impact of subjective style variations.
- 6
- Context-aware target texture perturbation attack for concealed object detection6
A novel adversarial attack method, context-aware target texture perturbation, specifically designed to fool COD models, which is effectiveness in reducing COD model performance by up to 40% while preserving the visual quality of original images is demonstrated.
- 6
- Disentangled Representation Learning and Enhancement Network for Single Image De-Raining6
A disentangled representation learning and enhancement network (DRLE-Net) is presented to address the challenging single image de-raining problems, i.e., raindrop and rain streak removal and is demonstrated to produce significantly better results than state-of-the-art models.
- Feature Selection via Transferring Knowledge Across Different Classes6
A cross-class knowledge transfer feature selection framework which transfers the cross- class knowledge from the source domain to guide target domain feature selection and high-level descriptions are used as the bridge for knowledge transfer is proposed.
- Uniportal complete video-assisted thoracoscopic surgery lobectomy with partial pulmonary arterioplasty for lung cancer with calcified lymph node.6
A uniportal cVATS left upper lobectomy with partial pulmonary arterioplasty for lung cancer with calcified lymph nodes is described and two-stage maneuvering for left upper lobe (LUL) bronchus is applied to reduce the risk of bleeding.
- Spread Spectrum-Based Multi-bit Watermarking for Free-View Video6
Experimental results show that the watermark in FTV not only can be resistant to common signal processing but also can be detected from the virtual view generated for an arbitrary view.
- 5
- 5
- 5
- The Parables of the Mustard Seed and the Yeast: Extremely Low-Budget, High-Performance Nighttime Semantic Segmentation5
A new task focusing on exploring the potential of training strategy and framework design with limited annotation to achieve high-performance NSS, and an innovative Fragmentation Synergy Active Domain Adaptation framework (FS-ADA), which progressively broadcasts the limited annotation to the unlabeled regions, achieving high performance with a minimal annotation budget.
- 5
- 5
- Assess and Guide: Multi-modal Fake News Detection via Decision Uncertainty5
This work distinguishes among uni-modal information sources through accurate estimation of their decision uncertainty, employing this uncertainty as a confidence measure and indicator of information imbalance to guide feature fusion.
- Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection5
A novel prototype-based knowledge filtering method to estimate the transferability of cross-domain samples and optimize the shared feature space by aligning the cross- domain image representations simultaneously on domain level with early alignment and class level with supervised contrastive learning, which endows model training and knowledge transfer with stronger robustness.
- Towards Causality Inference for Very Important Person Localization5
A causal inference framework is established that unpacks the causes of previous methods and derives a new principled solution for VIPLoc, which treats the scene as confounding factor, allowing the ever-elusive confounding effects to be eliminated and the essential determinants to be uncovered.
- An Interactive Design for Visualizable Person Re-Identification5
It is demonstrated that a system offering these visual representations can effectively expedite and improve a person re-identification analysis and make it a much user-friendly experience.
- Precise Geometric Correction and Robust Mosaicking for Airborne Lightweight Optical Butting Infrared Imaging System5
A robust mosaicking method combination of as-projective-as-possible warps and similarity transformation, which uses multiple images to generate a wide viewing field panorama that weakens the “ghosting,” shape distortion, and area distortion.
- Perceptually learning multi-view sparse representation for scene categorization5
A perceptual multi-view sparse learning (PMSL) framework to distinguish sceneries from different categories is proposed and the superiority of this method over well-known shallow/deep recognition models is demonstrated.
- Person Re-identification Using Data-Driven Metric Adaptation5
This paper proposes a data-driven metric adaptation method that re-exploits the training data with cross-view consistency to adaptively adjust the metric.
- IMAGE QUALITY FEEDBACK-BASED ADAPTIVE VIDEO DEFINITION IMPROVEMENT FOR THE SPACE MANIPULATION TASK5
A novel video definition enhancement technique for space manipulation task is presented by considering both the feedback of the image quality (IQ) and the correction of the visual fatigue factor simultaneously.
- Study on Multiclass Text Categorization Method Based on Improved Support Vector Machine5
This paper puts forward a method of multiclass text categorization based on an improved support vector machine with binary tree and the pre-extracting support vectors and circulated iterative algorithm that possesses much higher computation efficiency.
- 4
- 4
- PrefAce: Face-Centric Pretraining with Self-Structure Aware Distillation4
A novel self-supervised face-centric pretraining framework, called PrefAce, which learns transferable video facial representation without labels, that can transfer across various facial analysis tasks, e.g., Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization.
- MORE'24 Multimedia Object Re-ID: Advancements, Challenges, and Opportunities4
A spectrum of topics related to object re-id are covered, including but not limited to deep metric learning, multi-view data generation, video-based object re-id, cross-domain object re-id and real-world applications.
- Cross-Illumination Video Anomaly Detection Benchmark4
Experimental results show that the designed benchmark framework for the cross-illumination video anomaly detection task outperforms existing methods regarding detection accuracy and is more robust.
- Data-driven product ranking: A hybrid ranking approach4
The usefulness and applicability of the proposed decision support framework is proved in two aspects: the comparison of whether the preference of decision makers is considered, and the comparison with the existing ranking methods.
- 4
- 4
- 4
- 4
- 4
- 4
- Multi-color space learning for image segmentation based on a support vector machine4
This method reduced the segmentation time and improved the image segmentation performance, and used Region Circularity and Boundary Center Deviation as evaluation indicators to analyze the performance of the algorithm.
- 4
- 4
- 4
- SAR Image Segmentation Based On Markov Random Field Model4
The result shows that this algorithm can efficiently reduce the influence of speckle noise, and segment the image into three parts of target, shadow and background.
- Behave Your Motion: Habit-preserved Cross-category Animal Motion Transfer3
This work proposes a novel habit-preserved motion transfer framework for cross-category animal motion that introduces a habit-preservation module with category-specific habit encoder, allowing it to learn motion priors that capture distinctive habitual characteristics in animals.
- SegTraj: A Segmented-Trajectory-Aware Spatio-Temporal Graph Convolutional Network for Social Group Detection3
A Segmented-Trajectory-Aware Spatio-Temporal Graph Convolutional Network (SegTraj) is proposed, which uniformly models explicit and implicit interactions through a spatio-temporal graph, and fuses individual trajectories with contextual neighborhood information for fine-grained representation of group relationships.
- 3
- Leader is Guided: Interactive Motion Generation via Lead-Follow Paradigm and Trajectory Guidance3
Inspired by role allocation in partner dancing, the decompose complex interactive motion tasks into a Lead-Follow paradigm and shows that the proposed approach, by more effectively using trajectory, outperforms existing methods in both realism and accuracy.
- Predicting the Unseen: A Novel Dataset for Hidden Intention Localization in Pre-abnormal Analysis3
A novel video dataset specifically for Temporal Intention Localization (TIL), aimed at identifying hidden abnormal intention in densely populated and complex environments, and develops the Intention-Action Fusion module, an creative approach integrating dynamic feature fusion across 11 behavioral subcategories, significantly enhancing the model's ability to discern nuanced intention.
- Local Features Meet Stochastic Anonymization: Revolutionizing Privacy-Preserving Face Recognition for Black-Box Models3
This work adopts an adversarial learning-based approach with irreversible stochastic injection to ensure the stochastic nature of the anonymization of face recognition, outperforming existing methods in both privacy protection and anti-reconstruction capabilities.
- 3
- 3
- 3
- 3
- 3
- Dual-focus: person search from Coarse-Grained Focus to Fine-Grained Focus3
Inspired by the observation that the police first narrowed the scope to a small group of people similar to the suspect, and then located the target, this work proposes a Dual-Focus framework consisting of Coarse-Grained Focus (search for similar people) and Fine-Graining Focus (find the target).
- Unlabeled data driven cost-sensitive inverse projection sparse representation-based classification with 1/2 regularization3
An improved SRC model is constructed to achieve effective and stable representation and recognition results and the cost-sensitive strategy is integrated into the model’s classification criteria to improve the imbalance of class distribution adaptively.
- Salient Time Slice Pruning and Boosting for Person-Scene Instance Search in TV Series3
This paper extends the focus from time point (single video shot) to time slice (multiple consecutive video shots) in the time-line, and evaluates the importance of salient time slices to boost the aggregation results.
- Improved Simple Linear Iterative Clustering Algorithm Using HSL Color Space3
This work proposed an improved method based on SLIC to address the problem of undersegmentation of superpixel segmentation, and showed that the improved algorithm has better accuracy and efficiency.
- 3
- 3
- 3
- Person Re-Identification via Multiple Coarse-to-Fine Deep Metrics3
This paper proposes a coarse-to-fine deep metric learning method equipped with multiple different Stacked Auto-Encoder (SAE) networks and classification networks that simulate the information processing of the brain’s visual system to recognize the character of objects.
- 3
- Person Re-identification via Attribute Confidence and Saliency3
A novel person re-identification method that epitomizes the diversities of different attributes as two folds: the attribute confidence which denotes the descriptive power, and the attribute saliency which expresses the discriminative power is proposed.
- The ACM Multimedia 2025 Grand Challenge of Truthful and Responsible Multimodal Learning2
This work establishes benchmarks that support responsible multimodal AI in diverse real-world applications and focuses on detecting hallucinated elements in AI-generated image captions, such as fabricated objects or attributes.
- S2ML: Spatio-Spectral Mutual Learning for Depth Completion2
This work proposes a Spatio-Spectral Mutual Learning framework (S2ML) to harmonize the advantages of both spatial and frequency domains for depth completion, and considers the distinct properties of amplitude and phase spectra and devise a dedicated spectral fusion module.
- SPAN: Continuous Modeling of Suspicion Progression for Temporal Intention Localization2
This paper reconceptualizes hidden intention modeling by shifting from discrete classification to continuous regression and proposes Suspicion Progression Analysis Network (SPAN), which capture the fluctuations and progression of hidden intentions over time and formalizes a suspicion score formula that models continuous changes while accounting for temporal characteristics.
- From Language to Instance: Generative Visual Prompting for Zero-shot Camouflaged Object Detection2
LiP is the first framework that utilize text-to-image generative model to construct instance-level visual prompts in COD task, and is the first framework that utilize text-to-image generative model to construct instance-level visual prompts in COD task.
- Pixel-REfocused Navigated Tri-margin for Semi-supervised Action Detection2
This paper proposes an effective pipeline called Pixel-Refocused Navigated Tri-margin (PRENT), which adaptively leverages class-explicit knowledge to manage uncertain boundaries within latent buffer regions within semi-supervised action detection.
- 2
- 2
- 2
- 2
- 2
- Multimedia Content Understanding in Harsh Environments2
This tutorial introduces some multimedia enhancement methods, presents recent advances in 2D and 3D visual scene understanding, shows strategies to estimate the prediction uncertainty, provides a brief summary, and shows some typical applications.
- Improving Generalization of Metric Learning via Listwise Self-distillation2
This work proposes a simple yet effective regularization, namely Listwise Self-Distillation (LSD), which progressively distills a model's own knowledge to adaptively assign a more appropriate distance target to each sample pair in a batch.
- 2
- FrequentNet : A New Deep Learning Baseline for Image Classification.2
This paper generalizes the idea from the method called "PCANet" to achieve a new baseline deep learning model for image classification that uses basis vectors in discrete Fourier analysis and wavelets analysis as the authors' filter vectors.
- Zero-shot Feature Selection via Exploiting Semantic Knowledge.2
This paper uses class-semantic descriptions (i.e., attributes) which provide additional semantic information about unseen concepts as supervision to address the problem of Zero-Shot Feature Selection, and proposes a novel loss function (named center-characteristic loss) which encourages the selected features to capture the central characteristics of seen concepts.
- 2
- 2
- Adaptive Margin Nearest Neighbor for Person Re-Identification2
An Adaptive Margin Nearest Neighbor (AMNN) method is proposed, which aims to take unequal treatment to each samples impostors by pushing them to adaptive variable margins away, and is confirmed the superiority of the proposed method.
- 2
- 2
- Web Surface Defect Segmentation Based on Stationary Wavelet Transform2
A novel approach based on stationary wavelet transform for the segmentation of web surface defect and makes full use of available information in each sub-band images to obtain better output results when compared with ordinary image enhancement.
- 2
- Pedestrian detection by multispectral fusion2
A Multi-spectral fusion approach to perform accurate pedestrian segmentation under varying operational parameters is presented, which combines the " best" detection results from the visible images and the "best" from the thermal images.
- 1
- 1
- 1
- 1
- 1
- Hammer and Anvil: Toward a Theory of Backdoors in Federated Learning1
This work devise a new adaptive adversary that surpasses existing adversaries in capabilities, yielding attacks that only require one or two malicious clients out of 20 to break existing state-of-the-art defenses.
- Beyond the Individual: Introducing Group Intention Forecasting with SHOT Dataset1
The concept of group intention, which represents shared goals emerging through the actions of multiple individuals, and Group Intention Forecasting (GIF), a novel task that forecasts when group intentions will occur by analyzing individual actions and interactions before the collective goal becomes apparent are introduced.
- 1
- 1
- 1
- 1
- Localization of Image Splicing Under Segment Anything Model With Integrated Compression and Edge Artifacts1
Leveraging SAM’s object understanding ability, the proposed Segment Anything Model with Integrated Compression and Edge artifacts (SAM-ICE) for the localization of image splicing is proposed, addressing limitations by fusing forged edge features and compression artifact features.
- 1
- 1
- 1
- Statistical Thinking and New Forms of Contemporary Art under the Background of Big Data1
This paper mainly studies the influence and change of the development of big data on the contemporary art world, how they change, integrate and develop, and evaluates the value of statistical thinking under the background ofbig data and the new form of contemporary art.
- 1
- 1
- Single Sea Surface Image Dehazing via Multi-scale Concatenated Attention Network1
A novel Multi-scale Concatenated Attention Network (MCA-Net) is proposed, which uses the concatenation operation to connect multi-scale residual blocks (MRB), while introducing the channel attention mechanism for guiding the hazy region feature extracting.
- Multi-scene Representation Learning with Neural Radiance Fields1
A multi-scene representation model that can learn the representation of complex scenes and reconstruct them in high resolution given novel viewing directions is proposed and outperforms previous model on both reconstruction precision and scenes generation ability from Novel viewing directions.
- 1
- 1
- 1
- 1
- 1
- 1
- User-Driven Sports Video Customization System for Mobile Devices1
A user-driven sports video customization system, aiming to provide interesting video clips for mobile users according to their personalized preferences, and the proposed extended-hidden Markov model extended-HMM is proved to be able to recognize the clock time precisely.
- Research on Modulation Recognition of the MPSK Signals Based on Statistical Analysis1
The blind identification method based on Wavelet Transform (WT) and Phase Clustering and the phase mutation phase difference by using WT will be discussed on the problem of how to identify the PSK subclass signal in the situation of non-cooperative communication.
- 1
- 1
- 1
- Image restoration method based on neural network combining with optimization algorithms1
At Last, blurred image which needs restoring could be restored by the trained evolving neural network, and this method has a satisfying restoration effect both in visual impression and quantitative analysis.
- 1
- –
- –
- An Amplified Luminescent Proximity Homogeneous Assay-Implemented CRISPR/Cas13a System for Noncoding RNA Detection–
The Alpha-CRISPR RNA detection system developed in this study integrates AlphaLISA technology with the CRISPR-Cas13a system, achieving significantly enhanced detection sensitivity, demonstrating substantial application potential in fundamental medical research and clinical diagnostics.
- –
- –
- –
- –
- Latent Watermarking: Secure Cryptographic Hashing in Flow-Matching for AI Content Authentication–
This approach addresses the limitations of prior techniques, overcoming inversion-induced distortion while enabling efficient embedding and decoding of meaningful authentication messages without pretraining or fine-tuning.
- –
- MIS '24: 1st ACM Multimedia Workshop on Multi-modal Misinformation Governance in the Era of Foundation Models–
This workshop brings together researchers and practitioners to discuss key topics in multi-modal misinformation governance, including new datasets, evaluation techniques, ethical considerations, methodological progress, case studies, and future research directions.
- Research and application of initial phase angle calibration technology for smart grids based on cloud platform–
This study achieves accurate verification and management of the initial phase angle of the power supply network by adopting a new structure of power frequency initial phase angle high-voltage signal collector, a cloud platform-based data resource maintenance system, and the construction of base station networks.
- –
- NNVISR: Bring Neural Network Video Interpolation and Super Resolution into Video Processing Framework–
NNVISR fills the gap between video enhancement neural networks and video processing pipelines, by accepting any network that enhances a group of frames, and handling all other network agnostic details during video processing.
- Camouflaged Object Segmentation Based on Dense Multi-Scale Transformer–
A camouflaged object segmentation method called dense multi-scale Transformer, which consists of two main modules: two-branch separable dense multi-scale feature extraction module and fast attention-induced cross-level interaction fusion module, to make deep self-attentive transform networks reach their full potential in the task of camouflaged object segmentation.
- –
- A Direct Modeling Method for 3D CAD Models Preserving Columnar Features–
This paper proposes a direct modeling method for CAD models that preserves columnar body features based on boundary representation (B-Rep), propagates editing operations within the columnar body features, and modifies associated geometric elements while maintaining the topology.
- –
- –
- Hi-Geo-Ti: A Visual Analytic Design for Pedestrian Trajectories Using Hierarchical Geographical Timelines–
Taking the transmission process of Covid-19 as case study, by combining with ReID technology, the assistance of proposed visualization system in the fight against the epidemic is demonstrated and user surveys are conducted to verify the effectiveness of proposed design.
- –
- –
- –
- –
- –
- –
- –
- –
- Supervised Discovery of Unknown Unknowns through Test Sample Mining (Student Abstract)–
This method seeks to reduce the structural mismatch between the training model and that of the target space in a supervised way, and simplifies the solution, as it does not rely on budgeted queries to an Oracle whose outcomes inform adjustments to training.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Stay Onbig-data Collaborative Management system with–
Racteristics of the data collection and analysis ability with BIG-DATA can effectively enhance the emergency handling Ciency, and provide effective support to handle emergencies event in marine.
- Test of Relative Translucency for Four All-Ceramic Core Material after Veneering Ceramic–
There is no significant difference between Empress II and Colored Zirconia in the relative translucency of 4 veneered and glazed all-ceramic systems core material, but Vita In-Ceram Alumina has significant difference.
- –
- Analysis of Packaging Standards for Sanitary Ceramics–
In this paper, some annotation and analysis have been done about JC/T694-2008 "sanitary ceramics packaging" on packaging materials, packaging forms, reference standards, vocabulary of terms and technical requirements.
- –
- Research on Rule-Based Reasoning Methods Oriented on Information Resource Ontology–
This paper extracts reasoning rules from semantic relationship of audit information, and presents Smallest Connected Subgraph Generation Algorithm, Connected Componets Generation Al algorithm and Connectedcomponets Matching Rules Algorithm; these three algorithms are in solving problems in the process of reasoning, implement the reasoning function.
- Evolutionary model for military forces system of systems based on topological weighed networks–
Through simulation, this paper draws the conclusion that military forces SoSs has the character of self-similarity which is reflected with the power law, also has a fractal structure.
- A kind of Image Compression Method Using BP Neural Network in Wavelet Domain–
A new image compression method which combined lifting wavelet transformation and BP neural network was proposed which not only had high compression ratio but also improved the PSNR.
- A Method of Data Mining of Customer Knowledge Management–
The paper defines the steps of implementing data mining,ognizes and summarizes the existent problems, and validates the feasibility that data mining can be used in the customer knowledge management, through a practice of excavation cluster analysis in a case.
- Medical Image Segmentation Method Based on Texture Character and GRBF Network–
The emulational results show that the image segmentation method based on texture character and generalized radial basis function neural networks is an effective medical image segmentsation method.
- The Development of Shoe Style CAD Based on Surface-Trimming on 3D Lasts–
In this work, to implement shoe design based on 3D lasts which made up of parametric surfaces, a CAD prototype system for shoe styles with further-development method is developed.
- On-line Glass Medicine Bottle Dimension Detection Technique Based on Image Manipulation–
An on-line medicine bottle dimension detection system that can ensure good quality when it is used on line and is developed by developing a detection system based on arithmetic.
- [An algorithm based on deformable contour models for medical image segmentation].–
A new medical image segmentation algorithm is provided, which integrates Fuzzy C-Means (FCM) Clustering technique and deformable contour model, which joins the external constrain of the deformable model and drives the deformables towards the contour ideal edge of the object.
- –
- –
- AN ALGORITHM FOR COMPLETE EUCLIDEAN DISTANCE TRANFORMATION BASED ON CONTOUR TRACING–
The results show that the algorithm is self-adaptive, runs fast, takes few mem-ory spaces, and applies to the practice conveniently.
- CONTOUR TRACING AND COMPUTING THE EULER NUMBER OF BINARY IMAGES REPRESENTED BY LINEAR QUADTREE–
The crack based contour tracing algorithm is extended to binary images represented by linear quadtrees, and an algorithm for tracing contours on that kind of images is presented.
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 2026-10-12. 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.