Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Zhongwei ZhangSuggested from co-authorship
- King Ngi NganSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works409 from public data
- 1,147
- 860
- 486
- 323
- VisDrone-DET2020: The Vision Meets Drone Object Detection in Image Challenge Results259
Based on the selected 29 robust detection methods, the experimental results comprehensively are discussed, which shows the effectiveness of ensemble learning and data augmentation in drone captured object detection.
- Multimodal medical image fusion based on IHS and PCA258
Visual and quantitative analysis show that the proposed algorithm significantly improves the fusion quality; compared to fusion methods including PCA, Brovey, discrete wavelet transform (DWT).
- 225
- Key-Word-Aware Network for Referring Expression Image Segmentation200
A key-word-aware network, which contains a query attention model and a key-words-aware visual context model, which outperforms state-of-the-art methods on two referring expression image segmentation databases.
- Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm188
A greedy heuristic dynamic programming iteration algorithm is developed to solve the zero-sum game problems, which can be used to solves the Hamilton-Jacobi-Isaacs equation associated with H"~ optimal regulation control problems.
- 165
- 161
- 145
- 145
- VisDrone-DET2018: The Vision Meets Drone Object Detection in Image Challenge Results133
A large-scale drone-based dataset, including 8, 599 images with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc, is released, to narrow the gap between current object detection performance and the real-world requirements.
- 114
- CL-MAPF: Multi-Agent Path Finding for Car-Like robots with kinematic and spatiotemporal constraints111
This paper proposes a novel hierarchical search-based solver called Car-like Conflict-Based Search to address the Multi-Agent Path Finding for Car-Like robots problem, and introduces a new algorithm called Spatiotemporal Hybrid-State A* as the single-agent path planner to generate path satisfying both kinematic and spatiotem temporal constraints.
- 111
- Saliency model-based face segmentation and tracking in head-and-shoulder video sequences98
A novel face segmentation algorithm based on facial saliency map (FSM) for head-and-shoulder type video application that is capable of segmenting the face area quite effectively.
- 96
- 96
- 92
- 89
- 88
- 86
- 81
- 77
- 77
- A2RMNet: Adaptively Aspect Ratio Multi-Scale Network for Object Detection in Remote Sensing Images76
A novel end-to-end Adaptively Aspect Ratio Multi-Scale Network (A 2 RMNet) is proposed to solve the problem of easy to miss or incorrectly locate objects due to the various sizes and aspect ratios of objects.
- Subjective and Objective De-Raining Quality Assessment Towards Authentic Rain Image75
A de-raining quality assessment (DQA) database is created and a bi-directional feature embedding network (B-FEN) which integrates the features of global perception and local difference together is proposed which significantly outperforms many existing universal blind image quality assessment models.
- 75
- 73
- 73
- 72
- 67
- 67
- 65
- 64
- 64
- 62
- 61
- Towards Continual Egocentric Activity Recognition: A Multi-Modal Egocentric Activity Dataset for Continual Learning59
A multi-modal egocentric activity dataset for continual activity learning named UESTC-MMEA-CL is proposed and the results of egocentric activity recognition of three modalities separately and jointly on a base network architecture are reported.
- 59
- 56
- 55
- 54
- Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyond49
The proposed PGMA-Net can solve bbox-level and cross-domain FSS, co-segmentation, zero-shot segmentation (ZSS) tasks, leading an any-shot segmentation framework capable of accommodating diverse weak or pixel annotations.
- 49
- Global and local semantics-preserving based deep hashing for cross-modal retrieval49
A large margin is enforced between similar hash codes and dissimilar hash codes from an inter-modal view to learn discriminative hash codes, which can well preserve local semantic structure and the global semantic structure can be preserved into the hash codes.
- 49
- 49
- 47
- 47
- No reference image quality assessment metric via multi-domain structural information and piecewise regression47
This paper develops a new local image representation which extracts the structural image information from both the spatial-frequency and spatial domains and develops an efficient piecewise regression method to capture the local distribution of the feature space.
- 47
- 46
- Towards human-like and transhuman perception in AI 2.0: a review46
This paper briefly review the state-of-the-art advances across different areas of perception, including visual perception, auditory perception, speech perception, and perceptual information processing and learning engines and envision several R&D trends in intelligent perception for the forthcoming era of AI 2.0.
- 43
- Video Segmentation and Its Applications43
The objective of Video Segmentation and Its Applications is to present the latest advances in video segmentation and analysis techniques while covering the theoretical approaches, real applications and methods being developed in the computer vision and video analysis community.
- A multi-index assessment method for evaluating coverage effectiveness of remote sensing satellite42
A multi-index assessment method based on index weight using entropy weight method and analytic hierarchy process is proposed and designs and experimental results show that the established coverage characteristic model and the proposed assessment method are effective and right.
- 42
- 42
- Language-Aware Fine-Grained Object Representation for Referring Expression Comprehension41
This work proposes a language-aware deformable convolution model (LDC) that adaptively samples a set of key points based on the image and language to represent objects and designs a bidirectional interaction model (BIM) that leverages a modified co-attention mechanism to build cross-modalbidirectional interactions to further improve the language and object representations.
- 41
- Exploring space–frequency co-occurrences via local quantized patterns for texture representation41
This paper proposes to explore space-frequency co-occurrences via local quantized patterns for texture representation via global thresholding, and achieves the best classification results compared with state-of-the-art approaches investigated.
- 40
- 40
- Parametric Deformable Exponential Linear Units for deep neural networks39
A Parametric Deformable Exponential Linear Unit (PDELU) is proposed and theoretically verify its effectiveness for improving the convergence speed of learning procedure and by means of flexible map shape, it could push the mean value of activation responses closer to zero, which ensures the steepest descent in training a deep neural network.
- 38
- A New Local Transformation Module for Few-Shot Segmentation38
A new transformation module based on local cues, where the relationship of the local features is used for transformation is proposed, which can be used to replace the transformation module in the existing few-shot segmentation frameworks.
- 38
- 38
- 37
- Discriminative deep metric learning for asymmetric discrete hashing37
A novel discriminative deep metric learning approach for asymmetric discrete hashing (ADMH) approach for supervised hashing learning and extensive experiments show that the proposed asymmetric deep hashing method outperforms the existing hashing methods.
- 36
- 35
- 35
- Cosegmentation of multiple image groups35
Experimental results demonstrate that the proposed multi-group cosegmentation framework is able to discover more accurate object priors and outperform state-of-the-art single-group image cose segmentation methods.
- 35
- Global salient information maximization for saliency detection35
A new method for saliency detection is proposed based on the defined features of the salient object, which achieves better results than the state of the art methods and can be applied for graph based salient object segmentation.
- 34
- 34
- Saliency detection using joint spatial-color constraint and multi-scale segmentation34
Experimental results show that the proposed method outperforms the state-of-the-art methods on salient region detection as well as human fixation prediction.
- Microbial community structures and important taxa across oxygen gradients in the Andaman Sea and eastern Bay of Bengal epipelagic waters33
Several microbial taxa, including the Thioglobaceae, Nitrospinaceae, SAR202, SAR406, WPS-2, UBA10353, and Woeseiaceae, may be involved in nitrogen and/or sulfur cycling, while also contributing to oxygen consumption in these waters.
- 32
- WaveLBP based hierarchical features for image classification32
Experimental results show that the proposed WaveLBP based image description achieves competitive classification accuracies for three different visual recognition tasks.
- 31
- Synthesis and bioevaluation of diaryl urea derivatives as potential antitumor agents for the treatment of human colorectal cancer31
A series of diaryl urea derivatives has been designed and synthesized based on clinical candidate gedatolisib (6aa), and most of the newly synthesized derivatives showed kinase inhibitory and antiproliferative activities within nanomolar and submicromolar level, respectively.
- 30
- 30
- 29
- 29
- Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning28
This paper proposes a Non-Homogeneous Haze Removal Network (NHRN) via artificial scene prior and bidimensional graph reasoning and demonstrates that the method achieves superior performance over many state-of-the-art algorithms for both the single image dehazing and hazy image understanding tasks.
- Hybrid human detection and recognition in surveillance27
An Overlapping Local Phase Feature (OLPF) is introduced to describe the face region, which can improve the robustness to pose change and blurring and is resistant to face detection error caused by imperfect localization or misalignment.
- 27
- 26
- 26
- Remember and Reuse25
A dynamic Remember and Reuse (R&R) network, which efficiently performs the cross-task BIQA based on a novel relevance-aware incremental learning strategy and significantly outperforms many state-of-the-art methods.
- 25
- SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting24
A new end-to-end scene text spotting framework termed SwinTextSpotter v2 is proposed, which seeks to find a better synergy between text detection and recognition and enhances the relationship between two tasks using novel Recognition Conversion and Recognition Alignment modules.
- 24
- 24
- 24
- A New Deep Segmentation Quality Assessment Network for Refining Bounding Box Based Segmentation24
This paper uses the proposed blind SQA network to refine the traditional bounding box-based segmentation results, with the idea of selecting parameters that are adaptive to each image, and a two-step refinement method is proposed.
- 24
- 23
- 23
- 22
- CODAN: Counting-driven Attention Network for Vehicle Detection in Congested Scenes22
The impressive results indicate that vehicle detection and counting can be mutually supportive, which is an important and meaningful finding.
- Optimization of integer wavelet transforms based on difference correlation structures22
A novel lifting integer wavelet transform based on difference correlation structure (DCCS-LIWT) is proposed that produces better results than the other well-known integer transforms for the lossless image compression.
- Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment21
A scalable incremental learning framework that could sequentially conduct BIQA across multiple evaluation tasks with limited memory capacity is proposed and a scalable memory unit is developed by gradually and selectively pruning unimportant neurons from previously settled parameter subsets to suppress the unrestrained expansion of memory capacity in sequential tasks learning.
- Manifold-ranking embedded order preserving hashing for image semantic retrieval21
A novel unsupervised hashing approach, namely Manifold-Ranking Embedded Order Preserving Hashing (MREOPH), which introduces a manifold ranking loss and an order preserving loss to solve the issue of global topological structure preserving.
- 21
- 21
- 21
- Cross-Modal Cognitive Consensus Guided Audio–Visual Segmentation20
A Cross-modal Cognitive Consensus guided Network (C3N) is proposed to align the audio-visual semantics from the global dimension and progressively inject them into the local regions via an attention mechanism.
- Design, Synthesis, Formulation, and Bioevaluation of Trisubstituted Triazines as Highly Selective mTOR Inhibitors for the Treatment of Human Breast Cancer20
A structure-based drug design strategy is used to discover a highly potent and kinase-selective mTOR inhibitor 24 (PT-88), which demonstrated an mTOR inhibitory IC50 value of 1.2 nM without obvious inhibition against another 195 kinases from the kinase profiling screening.
- 20
- Trends and Developments in the Detection of Pathogens in Central Nervous System Infections: A Bibliometric Study20
Exploring more advanced laboratory assays to improve the diagnostic accuracy of pathogens is essential for CNS infection research, and metagenomic next-generation sequencing is emerging as a novel useful unbiased approach for diagnosing infectious diseases of the CNS.
- 20
- 20
- 20
- 19
- 19
- 19
- 19
- 19
- Object Segmentation from Long Video Sequences19
This paper proposes a framework to segment the objects in relative video shots, while discarding the irrelative video shots and introduces a new long video segmentation dataset which corresponds to the pixel-wise ground truth.
- 19
- Fast and efficient method for block edge classification18
A fast and efficient method to classify block edge using difference properties from three coefficients in the non-normalised Haar transform (NHT) domain is presented and significantly reduces the number of computational operations in the edge models determination.
- 18
- 17
- Two-layer average-to-peak ratio based saliency detection17
Experimental results show that the proposed method outperforms the state-of-the-art methods and achieves the good performance on the visual saliency detection task.
- 16
- 16
- 16
- 16
- Hybrid-loss supervision for deep neural network16
A Hybrid-loss supervision (HLS) framework is proposed in order to obtain smoother and more spatially consistent features with shared FC layers and can significantly boost the efficiency of existing convolution networks for both image classification task and object detection task without increasing network parameters and computational complexity.
- 16
- 15
- 15
- 15
- 15
- 15
- 15
- Multi-Stage LLM Fine-Tuning with a Continual Learning Setting14
This work proposes a new learning paradigm designed specifically for multi-stage continuous learning that includes a preference-based learning bias to identify potential knowledge conflicts, as well as a self-distillation-based data augmentation strategy to expand and enrich the training corpus, thereby improving the integration of knowledge-compatible information.
- 14
- 14
- 14
- 14
- 14
- On Multiple Image Group Cosegmentation14
Experimental results show that the proposed multi-group cosegmentation framework is able to discover more accurate object priors and significantly outperform state-of-the-art single-group image cose segmentation methods.
- 14
- 14
- Bridging the Gap Between End-to-End and Two-Step Text Spotting13
Bridging Text Spotting is introduced, a novel approach that resolves the error accumulation and suboptimal performance issues in two-step methods while retaining modularity and introduces a Bridge that connects the locked detector and recognizer through a zero-initialized neural network.
- 13
- 13
- 13
- 13
- 13
- An efficient intra-mode selection algorithm for H.264 based on edge classification and rate-distortion estimation13
Experimental results show that this fast intra-mode selection scheme can lessen the encoding time significantly with little loss of bit-rate and visual quality.
- A novel PDE-based rate-distortion model for rate control13
A novel rate-distortion (R-D) model for rate control of video coding is presented that achieves better buffer status, higher control accuracy, and stabler and more consistent picture quality compared with the well-known MPEG-4 Q2 rate-control scheme.
- 12
- Design, synthesis and bioevaluation of PI3Kα-selective inhibitors as potential colorectal cancer drugs12
A detailed structure-activity relationship (SAR) study has identified the optimal compound 18a bearing a quinoxaline scaffold, which had a higher plasma exposure, higher maximum concentration and shorter elimination time compared to 8a and showed better isoform-selective profiles over other PI3Ks.
- 12
- 12
- RefCrowd: Grounding the Target in Crowd with Referring Expressions12
A Fine-grained Multi-modal Attribute Contrastive Network (FMAC) to deal with REF in crowd understanding, which outperforms existing state-of-the-art (SoTA) methods on the authors' RefCrowd dataset and existing REF datasets, and implements an end-to-end REF toolbox for the deeper research in multi- modal domain.
- Model reduction-based initialization methods for solving the Poisson-Nernst-Plank equations in three-dimensional ion channel simulations12
Numerical tests on two highly charged channel protein systems demonstrate that three initialization methods can effectively reduce the number of Gummel iteration steps and/or the total CPU time in the solution of the PNP equations, and especially do not need the continuation approach anymore.
- Interactive object segmentation in two phases12
This paper presents a coarse-to-fine method from region-level segmentation to pixel- level segmentation, and uses the coarse segmentation result to aid the construction of the energy function in the pixel-level segmentsation.
- A novel attention model and its application in video analysis12
An adaptive threshold choice is given for extracting video attention regions automatically, and attention curve of videos based on the definition of frame attention is given, which can describe the attention variation of viewers when video is showing.
- 11
- Smaller But Better: Unifying Layout Generation with Smaller Large Language Models11
The proposed LGGPT is an LLM-based model tailored for unified layout generation that beats prior 7B or 175B models even in the most extensive and challenging unified scenario, and underscores the necessity of employing LLMs for unified layout generation.
- 11
- Continual Egocentric Activity Recognition With Foreseeable-Generalized Visual–IMU Representations11
This work proposes a motivational optimization scheme to address the limited generalization caused by the modal imbalance, enabling foreseeable generalization in a visual–IMU multimodal network and introduces a robust representation estimation technique and pseudo representation (PR) generation strategy for continual learning.
- 11
- 11
- 11
- 11
- 11
- 11
- Segmenting focused objects based on the Amplitude Decomposition Model11
An inherent model of the low depth-of-field (DOF) images is presented, referred as the Amplitude Decomposition Model, which turns out to be useful for the detection and segmentation of focused objects in the low DOF images.
- Automatic body segmentation with graph cut and self-adaptive initialization level set (SAILS)11
An automatic human body detector is designed to provide hard constraints on the object and background for segmentation, and a coarse-to-fine segmentation strategy is employed to deal with the situation of partly detected object.
- 10
- 10
- 10
- Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptation10
A knowability-based labeling scheme which can be divided into two steps: knowability-guided detection of known and unknown samples based on the intrinsic structure of the neighborhoods of samples, and label refinement based on neighborhood consistency to relabel the target samples.
- 10
- ELM_Kernel and Wavelet Packet Decomposition Based EEG Classification Algorithm10
A novel classification algorithm is proposed based on the characteristic of electroencephalogram (EEG) signals that outperforms state-of-the-art algorithms such as ELM, BP and SVM in terms of both training time and classification accuracy.
- Boosting Scene Parsing Performance via Reliable Scale Prediction10
A novel fully-supervised Scale Prediction Model is proposed, which learns parsing scales by the strong scale supervision, which is automatically generated from the scene parsing ground truth without any extra manually annotation, and a Scale Parsing Net (SPNet) is designed, which segments each object on the scale predicted by the Scale Prediction model.
- 10
- 9
- 9
- 9
- A New Few-shot Segmentation Network Based on Class Representation9
A new class representation based few-shot segmentation framework, which firstly generates class activation map of unseen class based on the knowledge of existing classes, and then uses the map as foreground probability map to extract the foregrounds from query image.
- 9
- 9
- 9
- Image/Video Segmentation: Current Status, Trends, and Challenges9
This chapter has several objectives: to survey the current status of research activities including graph-based, density estimator- based, and temporal-based segmentation algorithms, and to discuss recent developments while providing a comprehensive introduction to the fields of image/video segmentation.
- 9
- A Robust, Efficient, and Fast Global Motion Estimation Method from MPEG Compressed Video9
First, the moving background of the current frame is extracted using predictive error dcimage, and a new global motion detecting method based on a 6-parameters camera motion analysis is proposed in this paper.
- 9
- Learning With Noisy Low-Cost MOS for Image Quality Assessment via Dual-Bias Calibration8
This paper considers the LC-MOS as the noisy observation of LA-MOS and enforce the IQA model learned from LC-MOS to approach the unbiased estimation of LA-MOS, which is the first exploration of robust IQA model learning from noisy low-cost labels.
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- Cognition Transferring and Decoupling for Text-Supervised Egocentric Semantic Segmentation7
A Cognition Transferring and Decoupling Network (CTDN) is proposed that first learns the egocentric wearer-object relations via correlating the image and text and a Cognition Transferring Module (CTM) is developed to distill the cognitive knowledge from the large-scale pre-trained model to the authors' model for recognizing egocentric objects with various semantics.
- 7
- 7
- 7
- Callicarpnoids A–C, structurally intriguing ent-Clerodane diterpenoid dimers with cytotoxicity against MCF-7 and HCT-116 cell lines from Callicarpa arborea Roxb7
Callicarpnoids A-C (1-3), three new ent-clerodane diterpenoid dimers formed via a [4 + 2] hetero Diels-Alder cycloaddition, appeared as a third example of this type of dimers, were isolated from the stems of Callicarpa arborea Roxb by comprehensive spectroscopic analysis.
- Category boundary re-decision by component labels to improve generation of class activation map7
This work proposes to use a set of lower-level labels, called component labels, to refine the classification boundary and provide more supervision to force the classification network to learn more local features of the target.
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- SegCTC: Offline Handwritten Chinese Text Recognition via Better Fusion Between Explicit and Implicit Segmentation6
A new method is proposed, SegCTC, which better integrates these two approaches into a unified to be a more powerful recognizer and designed a hybrid Segmentation-based and Segmentation-free Feature Fusion Module (S ² FFM) to better fuse the features of both explicit and implicit segmentation-based recognition branches.
- Constituents from leaves of Macaranga hemsleyana6
The isolated compounds established taxonomic classification of M. hemsleyana in Euphorbiaceae family and one new compound, identified as (2Z)-3-[4-(β-D-glucopyranosyloxy)-2′-hydroxy-5′-methoxyphenyl]-2-propenoic acid was a new glycoside.
- Multi-stage Tag Guidance Network in Video Caption6
This work proposes a tag guidance module to learn a representation which can better build the interaction in cross-modal between visual content and textual sentences and was ranked third place in Pre-training for Video Captioning Challenge.
- Class Activation Map Generation by Multiple Level Class Grouping and Orthogonal Constraint6
This paper tries to capture the semantic relationships between classes to form different semantic levels of classification models, and hierarchical clustering based on class relationships is used to form hierarchical clusters results, where the clustering levels are treated as semantic levels to form the classification models.
- Store classification using Text-Exemplar-Similarity and Hypotheses-Weighted-CNN6
This work introduces two features: Text-Exemplar-Similarity and Hypotheses-Weighted-CNN to efficiently distinguish different stores and builds a new 9-class store dataset composed of photos and images from the internet.
- 6
- Framework for GMPLS and PCE Control of G.709 Optical Transport Networks6
This document provides a framework to allow the development of protocol extensions to support Generalized Multi-Protocol Label Switching and Path Computation Element control of Optical Transport Networks as specified in ITU-T Recommendation G.709 as published in 2012.
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- Learning Offset Probability Distribution for Accurate Object Detection5
A distance-aware offset bin classification network optimized with multiple binary cross entropy losses to learn various offset probability distribution, including single label distribution and distance-aware label distribution is proposed.
- Dual UMIs and Dual Barcodes With Minimal PCR Amplification Removes Artifacts and Acquires Accurate Antibody Repertoire5
A novel approach named DUMPArts, which improves the accuracy of antibody repertoires by labeling each sample with dual barcodes and each molecule with dual unique molecular identifiers via minimal PCR amplification to remove artifacts, is developed.
- 5
- Multi-Scale Shape Adaptive Network for Raindrop Detection and Removal from a Single Image5
This paper establishes a large-scale dataset named RaindropCityscapes, which includes 11,583 pairs of raindrop and raindrop-free images, covering a wide variety of raindrops and background scenarios, and proposes a two-branch Multi-scale Shape Adaptive Network (MSANet) to detect and remove diverse raindrops.
- 5
- 5
- A fast calibration method for autonomous landing of UAV with ground-based multisensory fusion system5
- 5
- 5
- 5
- 5
- 5
- MSA-UNet3+: Multi-Scale Attention UNet3+ with New Supervised Prototypical Contrastive Loss for Coronary DSA Image Segmentation4
A Supervised Prototypical Contrastive Loss (SPCL) that combines supervised and prototypical contrastive learning to enhance coronary DSA image segmentation is proposed and implemented within MSA-UNet3+, a Multi-Scale Attention-Enhanced UNet3+ architecture.
- 4
- Unsupervised Ego- and Exo-centric Dense Procedural Activity Captioning via Gaze Consensus Adaptation4
A Gaze Consensus-guided Ego-Exo Adaptation Network (GCEAN) that injects the gaze information into the learned representations for the fine-grained Ego-Exo alignment and adopts hierarchical gaze-guided consistency losses to construct gaze consensus for the explicit temporal and spatial adaptation between the source and target views.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Realized volatility forecasting based on rolling SW-SVR method: evidence from CSI 300 index4
The empirical evidences from the high frequency data of CSI 300 index show that this new method, named rolling SW-SVR method, has stronger out-of-sample forecasting ability than the OLS and SVR methods.
- 4
- 4
- Guest Editorial Introduction to the Special Section on Intelligent Visual Content Analysis and Understanding4
Development in end-to-end differentiable learning and multimodality methods, targeting on making full use of various visual data sources, contribute to the innovations of two core modules for a typical intelligent vision system, i.e., image and video description and recognition.
- 4
- 4
- Special issue on recent advances in saliency models, applications and evaluations4
New datasets, metrics, benchmarks and behavioral studies are expected to comprehensively evaluate and fairly compare the performance of state-of-the-art saliency models, as well as to shape the future research directions.
- Mode dependent down-sampling and interpolation scheme for high efficiency video coding4
A mode dependent down-sampling and interpolation scheme is proposed to improve the coding efficiency of the intra prediction module by minimizing the spatial prediction distance.
- 3
- 3
- 3
- 3
- 3
- 3
- Torque identification based on LMS adaptive delay inverse system method3
The adaptive delayed inverse model was used to identify the time-domain torque by analyzing the angular acceleration response data of the working state and it is proved by the experiment that the method is also feasible to the shaft system with disk coupling.
- 3
- Hierarchical class grouping with orthogonal constraint for class activation map generation3
Experimental results on the PASCAL VOC 2012 dataset show the superior performance of the proposed CAM generation method, which attributes such incompleteness extraction to the finite discriminative cues within a single classification model.
- 3
- Salient Object Detection and Segmentation via Ultra-Contrast3
This paper proposes a salient object detection principle from existing contrast based methods: dissimilarity produces contrast, while contrast leads to saliency, and proposes a generalized framework to detect complex salient objects.
- 3
- GIP: Generic Image Prior for No Reference Image Quality Assessment3
A novel parametric image representation which is derived from the generic image prior (GIP), which utilizes the classic fields of experts model to capture the prior distribution of an image with respect to a random field, which is learned from a great deal of natural images.
- 3
- 3
- 3
- Research on Student Learning Behavior Analysis and Precision Teaching Driven by Big Data2
This study constructs various learning behavior analysis models, revealing students' learning habits and personalized needs, thereby providing teachers with robust evidence for instructional interventions and proposing precise teaching strategies, including personalized learning path planning, dynamic resource recommendations, and real-time feedback mechanisms, further enhancing teaching efficiency and learning outcomes.
- 2
- On the Adversarial Robustness of Learning-Based Image Compression Against Rate-Distortion Attacks2
This paper considers the arbitrary nature of the attack direction and the uncontrollable compression ratio faced by adversaries, and presents two practical rate-distortion attack paradigms, i.e., Specific-ratio Rate-Distortion Attack (SRDA) and Agnostic-ratio Rate-Distortion Attack (ARDA), and is the first to conduct joint rate-distortion attacks on LIC algorithms.
- 2
- 2
- 2
- 2
- 2
- 2
- Two new compounds from Verbena bonariensis2
The cytotoxicity of some of the compounds against MCF-7, HCT-116, MDA-MB-231, and SW620 human cancer cell lines were evaluated, in which compound 4 showed negligible cytotoxic activity.
- 2
- Block Fast FIR Algorithm and Circuit Design2
A 128 order configurable FIR filter circuit with 16 order as a block based on fast fir algorithm (FFA), block FFA (BFFA) is proposed, and the analysis of experimental data shows that the 16 bit integer FIR filter performance reaches 881.78Gop/s.
- 2
- 2
- 2
- 2
- Improving object proposals with top-down cues2
This paper proposes a novel method to improve the ranking of object proposals by combining bottom-up cues with top-down information of objectivity, and achieves better performance compared with the state-of-art on the Pascal VOC2007 dataset.
- Feature discovering for image classification via wavelet-like pattern decomposition2
A feature discovering method incorporated with a wavelet-like pattern decomposition strategy to address the image classification problem and shows the effectiveness of proposed method is verified on the challenging public datasets.
- 2
- 2
- 2
- 2
- Predictive functional control (PFC) and its application in chlorinated polyethylene process2
The main principle and the characteristic of Predictive Functional Control (PFC) strategy are presented and the corresponding control system aid design software APC-PFC is introduced and the control performance is improved obviously.
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- [Acute respiratory distress syndrome caused by severe respiratory infectious diseases: clinical significance and solution of maintaining artificial airway closure].1
This review summarizes the research status in related fields to provide a reference for corresponding solutions and programs on the temporary sealing of airway lines and ventilator system.
- 1
- 1
- Your Demands Deserve More Bits: Referring Semantic Image Compression at Ultra-low Bitrate1
This work proposes a novel Referring Semantic Image Compression framework, which achieves flexible customized compression according to user demands, which better balance the local fidelity, global realism, semantic alignment, and bit overhead.
- 1
- MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning1
This work proposes a method to Mitigate Catastrophic Forgetting in class-incremental learning for multimodal Video Captioning (MCF-VC), and designs Fine-grained Sensitivity Selection based on the Mask of Linear's Parameters and Fisher Sensitivity to pick useful knowledge from old tasks.
- 1
- Slightly Shift New Classes to Remember Old Classes for Video Class-Incremental Learning1
SNRO is a video class-incremental learning approach, which slightly shifts the features of new classes to remember old classes, and contains Examples Sparse and Early Break, which stores more examples under the same memory consumption.
- 1
- 1
- 1
- No Re-Train, More Gain: Upgrading Backbones with Diffusion model for Pixel-Wise and Weakly-Supervised Few-Shot Segmentation1
DiffUp, a novel FSS method that conceptualizes the FSS task as a conditional generative problem using a diffusion process, and incorporates an uncertainty-aware information fusion module that harmonizing the variability across zero-shot, one-shot and many-shot scenarios.
- 1
- 1
- 1
- 1
- 1
- 1
- A multi-scale language embedding network for proposal-free referring expression comprehension1
This paper proposes a multi-scale language embedding network for REC, which adopts the proposal-free structure, which directly feeds fused visual-language features into a detection head to predict the bounding box of the target.
- 1
- 1
- Research on Approximate Fitting Method of Activation Function Based on Gradient Equalization in Deep Learning1
An approximate fitting method of activation function based on gradient bisection is proposed and can fit the activation function curve well, which means the storage capacity can be reduced by one time compared with the traditional approximatefitting method.
- 1
- ECMO Therapy for Critically Ill Coronavirus Disease 2019 Patients in Wuhan, China: A Retrospective Multicenter Cohort Study1
Despite the high mortality, ECMO was associated with improved outcomes relative to IMV-only therapy in critically ill COVID-19 patients, and tracheotomy could facilitate weaning from ECMO.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Innovative Applications and Practical Research of Artificial Intelligence Technology in Basic Computer Course Teaching–
The research shows that the effective application of artificial intelligence technology not only helps to enhance the learning experience but also fosters students' autonomous learning and innovation capabilities.
- –
- –
- –
- –
- –
- DFR: A Decompose-Fuse-Reconstruct Framework for Multi-Modal Few-Shot Segmentation–
A novel framework that addresses the fundamental challenge of effectively utilizing multi-modal guidance in few-shot segmentation (FSS), and leverages the Segment Anything Model to systematically integrate visual, textual, and audio modalities for enhanced semantic understanding.
- –
- –
- –
- –
- –
- –
- –
- Two New Prenylated Flavonoids from the Leaves of Macaranga pustulata–
Two new flavonoids, 8,2′-diprenyl-3,5,7,5′-tetrahydroxyflavone and 8-(1-methoxy-2,3-dihydroxy-3-methylbutyl)naringenin, were isolated from the leaves of Macaranga pustulata and showed weak cytotoxicity against HCT-116.
- –
- Design and Implementation of Child Missing Registration and Mutual Aid Mini Program Based on Java–
In the age of information technology, people can make better use of this mini program to participate in the search for missing children and improve the success rate of search operations, bringing positive impacts to families and society.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Detecting Aging Substation Transformers by Audio Signal with Deep Neural Network–
A practical detection system for indoor substation transformers based on the analysis of audio signal is designed, which use computer technology instead of manpower to efficiently monitor the transformers working states in real-time to avoid unforeseeable outages and minimize planned downtimes.
- Design of inter-stations H∞ decoupling controller in VSC-HVDC system–
The electromagnetic transient simulation is carried out to verify that the H∞ decoupling controller between stations can be effectively weakened the interaction between two converter stations and improves the dynamic performance and robust stability of the system.
- –
- Error Bounds of Adaptive Dynamic Programming Algorithms–
This chapter develops an iterative ADP algorithm by using Q-function which depends on the state and action to solve the nonlinear optimal control problems and shows that the iterative approximate value function converges to a finite neighborhood of the optimal value function under some mild conditions.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- MRF based construction of statistical operator and its application–
It is proved that many detail coefficients being zero in the smooth gray-level variation areas can be achieved under the conditional probability density function in MRF model, which shows that this operator is suitable for the task of image compression, especially for lossless coding applications.
- –
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 2026-10-15. 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.