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
- Gregory S. ChirikjianSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works218 from public data
- Deep Modular Co-Attention Networks for Visual Question Answering1,023
A deep Modular Co-Attention Network (MCAN) that consists of Modular co-attention layers cascaded in depth that significantly outperforms the previous state-of-the-art models and is quantitatively and qualitatively evaluated on the benchmark VQA-v2 dataset.
- ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering793
This work introduces ActivityNet-QA, a fully annotated and large scale VideoQA dataset, which consists of 58,000 QA pairs on 5,800 complex web videos derived from the popular ActivityNet dataset and explores various video representation strategies to improve videoQA performance.
- Multi-modal Factorized Bilinear Pooling with Co-attention Learning for Visual Question Answering758
A Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multi- modal features, which results in superior performance for VQA compared with other bilinear pooling approaches.
- Beyond Bilinear: Generalized Multimodal Factorized High-Order Pooling for Visual Question Answering532
A DNN architecture is designed to integrate all these aforementioned modules into a unified model for achieving superior VQA performance and an ensemble of the authors' MFH models achieve the state-of-the-art performance on the large-scale VQ a data sets and win the runner-up in V QA Challenge 2017.
- Multimodal Transformer With Multi-View Visual Representation for Image Captioning468
Inspired by the success of the Transformer model in machine translation, this work extends it to a Multimodal Transformer (MT) model for image captioning that significantly outperforms the previous state-of-the-art methods.
- Prompting Large Language Models with Answer Heuristics for Knowledge-Based Visual Question Answering211
- Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding150
This paper introduces the diversity and discrimination simultaneously when generating proposals, and in doing so proposes Diversified and Discriminative Proposal Networks model (DDPN), a high performance baseline model for visual grounding and evaluates it on four benchmark datasets.
- Discriminative coupled dictionary hashing for fast cross-media retrieval150
The experiments show that the DCDH and MV-DCDH outperform the state-of-the-art methods significantly on cross-media retrieval and conjecture that a balanced representation is crucial in cross- media retrieval.
- 130
- UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training114
UC2, the first machine translation-augmented framework for cross-lingual cross-modal representation learning, is introduced, to tackle the scarcity problem of multilingual captions for image datasets and facilitate the learning of a joint embedding space of images and all languages of interest.
- Deep Multimodal Neural Architecture Search114
The obtained MMnasNet significantly outperforms existing state-of-the-art approaches across three multimodal learning tasks (over five datasets), including visual question answering, image-text matching, and visual grounding.
- 114
- Strategy and Policy Learning for Non-Task-Oriented Conversational Systems103
A set of generic conversational strategies to handle possible sys-tem breakdowns in non-task-oriented dialog systems and three metrics, which consider both the lo-cal and global quality of the conversation, to evaluate conversation quality are proposed.
- Paraphrase Augmented Task-Oriented Dialog Generation92
A paraphrase augmented response generation (PARG) framework that jointly trains a paraphrase model and a response generation model to improve the dialog generation performance and design a method to automatically construct paraphrase training data set based on dialog state and dialog act labels.
- A Visual Attention Grounding Neural Model for Multimodal Machine Translation87
A novel multimodal machine translation model that utilizes parallel visual and textual information and jointly optimizes the learning of a shared visual-language embedding and a translator that achieves competitive state-of-the-art results on the Multi30K and the Ambiguous COCO datasets.
- Matching and reconstruction of brachytherapy seeds using the Hungarian algorithm (MARSHAL)81
Matching rate and reconstruction accuracy were found to be sufficient for prostate brachytherapy and the algorithm is sufficiently generic to be used for establishing correspondences across any choice of features in different imaging modalities.
- Zero-Shot Dialogue State Tracking via Cross-Task Transfer77
This work proposes TransferQA, a transferable generative QA model that seamlessly combines extractive QA and multi-choice QA via a text-to-text transformer framework, and tracks both categorical slots and non-categorical slots in DST.
- ENHANCING THE PERFORMANCE OF74
Recommendations for the use of Behavioural Markers recommendations for performance measurement in a range of organisational settings, especially in high reliability industries such as nuclear power, rail and maritime transport, and medicine.
- SPRNet: Single-Pixel Reconstruction for One-Stage Instance Segmentation72
This article proposes a one-stage framework, single-pixel reconstruction net (SPRNet), which performs efficient instance segmentation by introducing a single- pixel reconstruction ( SPR) branch to off-the-shelf one- stage detectors.
- 64
- ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration63
A new VLP method called ROSITA is introduced, which integrates the cross- and intra-modal knowledge in a unified scene graph to enhance the semantic alignments and introduces a novel structural knowledge masking (SKM) strategy to use the scene graph structure as a priori to perform masked language (region) modeling.
- Open-Ended Long-form Video Question Answering via Adaptive Hierarchical Reinforced Networks61
This paper proposes the adaptive hierarchical encoder network to learn the joint representation of the long-form video contents according to the question with adaptive video segmentation and develops the reinforced decodernetwork to generate the natural language answer for open-ended video question answering.
- A robotic library system for an off-site shelving facility61
An autonomous mobile robotic library system has been developed to retrieve items from bookshelves and carry them to scanning stations located in the off-site shelving facility in order to achieve real-time browsing of printed materials.
- ALICE: Active Learning with Contrastive Natural Language Explanations56
This work proposes Active Learning with Contrastive Explanations (ALICE), an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning and outperform baseline models that are trained with 40-100% more training data.
- Learning Conversational Systems that Interleave Task and Non-Task Content51
Experiments with human users indicate that a system that interleaves social and task content achieves a better task success rate and is also rated as more engaging compared to a pure task-oriented system.
- 50
- 48
- Comprehensive evaluations of a prototype full field-of-view photon counting CT system through phantom studies46
Both qualitative and quantitative evaluations show that PCCT, under the tested conditions, has superior imaging performance with lower noise and improved spatial resolution compared to conventional energy integrating detector (EID)-CT.
- Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog41
A multimodal hierarchical reinforcement learning framework that dynamically integrates vision and language for task-oriented visual dialog and a new technique, state adaptation, to integrate context awareness in the dialog state representation are proposed.
- ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding40
ArtiMuse, an innovative MLLM-based IAA model with Joint Scoring and Expert-Level Understanding capabilities, and ArtiMuse-10K, the first expert-curated image aesthetic dataset, each annotated by professional experts with 8-dimensional attributes analysis and a holistic score are presented.
- TickTock: A Non-Goal-Oriented Multimodal Dialog System with Engagement Awareness40
Tick, a conversational agent designed to engage humans on topics of its choosing and to carry on an interaction for as long as possible, is described and non-language cues are investigated to create a more robust engagement model based on multiple human communication channels.
- Cross-Media Hashing with Neural Networks40
This work proposes a cross-media hashing approach based on multi-modal neural networks that achieves superior cross- media retrieval performance compared with the state-of-the-art methods.
- Imp: Highly Capable Large Multimodal Models for Mobile Devices38
This paper conducts a systematic study for lightweight LMMs from the aspects of model architecture, training strategy, and training data, and obtains Imp—a family of highly capable LMMs at the 2B, 3B, and 4B scales.
- Unsupervised Vision-and-Language Pretraining via Retrieval-based Multi-Granular Alignment38
This paper proposes a novel unsupervised V + L pre-training curriculum for non-parallel texts and images and constructs a weakly aligned imagetext corpus via a retrieval-based approach, then applies a set of multi-granular alignment pre- training tasks to bridge the gap between the two modalities.
- Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation37
This work proposes an automatic evaluation model CMADE (Comparison Model for Automatic Dialog Evaluation) that automatically cleans self-reported user ratings as it trains on them and first uses a self-supervised method to learn better dialog feature representation, and uses KNN and Shapley to remove confusing samples.
- Prophet: Prompting Large Language Models With Complementary Answer Heuristics for Knowledge-Based Visual Question Answering36
This paper presents Prophet—a conceptually simple, flexible, and general framework designed to prompt LLM with answer heuristics for knowledge-based VQA, which significantly outperforms existing state-of-the-art methods on four challenging knowledge-based VQA datasets.
- Incremental Coordination: Attention-Centric Speech Production in a Physically Situated Conversational Agent35
A model that considers the demands and availability of listeners’ attention at the onset and throughout the production of system utterances, and that incrementally coordinates speech synthesis with the listener’s gaze is introduced.
- 34
- Assembling the Jigsaw: How Multiple Open Standards Are Synergistically Combined in the HALEF Multimodal Dialog System33
This chapter examines how an open-source, modular, multimodal dialog system—HALEF—can be seamlessly assembled, much like a jigsaw puzzle, by putting together multiple distributed components that are compliant with the W3C recommendations or other open industry standards.
- C-arm Calibration – Is it Really Necessary?32
Results corroborated the theory in that mis-calibration in the focal spot by as much as 50 mm still allows for tracking with an accuracy of 0.5 mm in translation and 0.65 degrees in rotation, and such mis-calibration does not impose any additional error on the reconstruction of small objects.
- Comprehensive Distance-Preserving Autoencoders for Cross-Modal Retrieval31
Compared with eight state-of-the-art cross-modal retrieval methods, the experimental results demonstrate that the CDPAE outperforms all the unsupervised methods and performs competitively with the supervised methods.
- 30
- 30
- An Open-Source Dialog System with Real-Time Engagement Tracking for Job Interview Training Applications27
A dialog system that tracks and reacts to a user’s state, such as engagement, in real time with positive feedback strategies designed to re-engage the user in the job interview process and suggests that users speak more while interacting with the engagement-coordinated version of the system as compared to a non- coordinated version.
- Automatic Prediction of Friendship via Multi-model Dyadic Features27
A new computational model used to model friendship status in a dyad using a set of automatically harvested verbal and nonverbal features from videos of the interaction of students in a peer tutoring study is proposed, based on a group sparse model with L2,1 norm which is designed to accommodate the sparse and noisy properties of the multi-channel features.
- 26
- 25
- LayoutDIT: Layout-Aware End-to-End Document Image Translation with Multi-Step Conductive Decoder24
This work proposes a novel Layout -aware end-to-end DIT with multi-step conductive decoder that out-performs state-of-the-art methods with better parameter efficiency and extensive experiments show that LayoutDIT has a good generalization in diverse and complex layout scenes.
- 24
- ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos24
ANetQA is presented, a large-scale benchmark that supports fine-grained compositional reasoning over the challenging untrimmed videos from ActivityNet and is an order of magnitude larger than AGQA with a similar number of videos.
- 22
- Conformational Statistics of Semiflexible Macromolecular Chains with Internal Joints22
This paper describes the general structure of semi-flexible macromolecular chains as inextensible elastic chains with one or more internal joints which have limited ranges of rotation, and proposes a method to compute the probability density functions of the end-to-end pose of these macromolescular chains.
- Accelerated masked transformer for dense video captioning21
An improved Accelerated Masked Transformer (AMT) model is devised that enjoys the dual-benefit of effectiveness and efficiency and achieves competitive performance on two benchmark datasets ActivityNet-Caption and YouCookII with significant speed improvement.
- 21
- User-Click-Data-Based Fine-Grained Image Recognition via Weakly Supervised Metric Learning20
This work presents a novel fine-grained image recognition framework using user click data, which can bridge the semantic gap in distinguishing categories that are similar in visual, and proposes a weakly-supervised metric and template leaning with smooth assumption and click prior method.
- 18
- 18
- Cross-Lingual Cross-Platform Rumor Verification Pivoting on Multimedia Content16
A new features set, cross-lingual cross-platform features that leverage the semantic similarity between the rumors and the external information are introduced that achieve the state-of-the-art rumor verification results.
- 16
- 16
- 15
- MARN: Multi-level Attentional Reconstruction Networks for Weakly Supervised Video Temporal Grounding14
- 14
- Bootstrapping Development of a Cloud‐Based Spoken Dialog System in the Educational Domain From Scratch Using Crowdsourced Data14
A crowdsourcing-based framework to iteratively and rapidly bootstrap a dialog system from scratch for a new domain and illustrates the usefulness of this framework using four different prototype dialog items with applications in the educational domain.
- 3D Question Answering with Scene Graph Reasoning13
This paper proposes a novel graph-based 3DQA method termed 3DGraphQA, which leverages scene graph reasoning to enhance the ability to handle complex reasoning tasks in 3DQA and offers stronger interpretability.
- 13
- 13
- 12
- 12
- Hashing with List-Wise learning to rank12
In this paper, the hashing problem is considered from the perspective of optimizing a list-wise learning to rank problem and an approach called List-Wise supervised Hashing (LWH) is proposed, which obtains a significant improvement over the state-of-the-art hashing approaches due to both structural large margin and list- Wise ranking pursuing in a supervised manner.
- 12
- 11
- Building Task-Oriented Visual Dialog Systems Through Alternative Optimization Between Dialog Policy and Language Generation11
This paper proposes a novel framework that alternatively trains a RL policy for image guessing and a supervised seq2seq model to improve dialog generation quality and achieves the state-of-the-art performance in both task completion and dialog quality.
- 11
- Multimodal HALEF: An Open-Source Modular Web-Based Multimodal Dialog Framework11
An open-source web-based multimodal dialog framework that integrates video conferencing and telephony abilities into the existing HALEF cloud-based dialog framework via the FreeSWITCH video telephony server is presented.
- 11
- White matter structural connectivity as a biomarker for detecting juvenile myoclonic epilepsy by transferred deep convolutional neural networks with varying transfer rates10
Through detection of the abnormal white matter changes, the white matter structural connectivity can be used as a useful biomarker for detecting JME, which helps to characterize the pathophysiology of epilepsy.
- User Engagement Study with Virtual Agents Under Different Cultural Contexts10
Two versions of a virtual agent targeting American and Chinese cultures are implemented and it is found that users from different culture context express engagement differently.
- A sampling method based on URL clustering for fast web accessibility evaluation10
This work proposes a novel page sampling method based on URL clustering for web accessibility evaluation, namely URLSamp, which uses only the URL information for stratified page sampling and can efficiently scale to large websites.
- CXRAgent: Director-Orchestrated Multi-Stage Reasoning for Chest X-Ray Interpretation9
CXRAgent is proposed, a director-orchestrated, multi-stage agent for CXR interpretation, where a central director coordinates the following stages: 1) Tool Invocation: The agent strategically orchestrates a set of CXR-analysis tools, grounding diagnostic outputs with visual evidence to support reliable downstream diagnosis.
- Effective Video Summarization by Extracting Parameter-Free Motion Attention9
The Parameter-free Motion Attention Module (PMAM) is proposed to exploit the crucial motion clues potentially contained in adjacent video frames, using a multi-head attention architecture, and the Multi-feature Motion Attention Network (MMAN) is introduced, integrating the PMAM with local and global multi-head attention based on object-centric and scene-centric video representations.
- Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation9
This work investigates knowledge distillation based life-long learning methods for Multilingual Neural Machine Translation and proposes a multilingual distillation method to make the new model (student) jointly learn multilingual output from old model (teacher) and new task.
- 9
- Intra- and Inter-modal Multilinear Pooling with Multitask Learning for Video Grounding9
This work proposes a simple yet effective multi-task learning framework to simultaneously predict the action label, alignment score and refined location in an end-to-end manner and demonstrates the superiority of the proposed approach over existing state-of-the-art methods.
- 9
- 9
- 9
- 9
- 9
- 8
- MMCNav: MLLM-empowered Multi-agent Collaboration for Outdoor Visual Language Navigation8
Inspired by the classical perception-cognition-action feedback loop in cognitive neuroscience, a multi-agent collaborative outdoor navigation system that significantly enhances the capability to accomplish outdoor navigation tasks by extending a single agent into multiple cooperative agents is presented.
- Characterization of diffusion magnetic resonance imaging revealing relationships between white matter disconnection and behavioral disturbances in mild cognitive impairment: a systematic review8
This review summarized the correspondence between white matter disconnections and behavioral disturbances such as cognition and affection, which provides a theoretical basis for the future diagnosis and treatment of AD.
- A Student-Teacher Architecture for Dialog Domain Adaptation Under the Meta-Learning Setting8
An efficient domain adaptive task-oriented dialog system model, which incorporates a meta-teacher model to emphasize the different impacts between generated tokens with respect to the context, is proposed.
- Image Ranking via Attribute Boosted Hypergraph8
In this paper, hypergraph is used to integrate the visual attributes with low-level features of images and a ranking algorithm is performed on the hypergraph to boost the result of image ranking.
- Error-correcting output hashing in fast similarity search8
This paper proposes a new method called Error-correcting Output Hashing (ECOH) which meets all the above three requirements and experimental results on real world data sets demonstrate the effectiveness and efficiency of the proposed approach.
- Development of prognostic models for advanced multiple hepatocellular carcinoma based on Cox regression, deep learning and machine learning algorithms7
Of the ML models, GBM model could predict the prognosis of advanced MHCC patients most accurately, and the Kaplan–Meier survival analysis demonstrated that the newly developed risk stratification system could well differentiate the prognosis of patients.
- 7
- 7
- 7
- Pipeline 3D Modeling Based on High-Definition Rendering Intelligent Calculation7
A new deep learning-based high-definition rendering solution for the pipeline image, which consists of three subnetworks: pipeline image feature modeling module, feature model alignment module, and pipeline image re-rendering module, which is proposed for pipeline image style conversion.
- Question-relationship guided graph attention network for visual question answer7
This paper proposes introducing a method of question-relationship guided graph attention network (QRGAT) to study a new representation of the visual features of an image through the guidance of a question and the explicit, internal relationships of objects.
- 7
- Large field of view beaconless laser nutation tracking sensor based on a micro-electro-mechanical system mirror7
A laser nutation tracking sensor for beaconless laser communication, which uses a micro-electro-mechanical system (MEMS) mirror to achieve high-efficiency and large-amplitude nutation at its resonant frequency, and derives a new formula for the case of incompletely detectable optical power in the nutation cycle.
- 7
- A Multimodal Dialog System for Language Assessment: Current State and Future Directions7
A multimodal dialog system for English language assessment using a modular cloud-based architecture adhering to open industry standards and multiple modules heavily exploit machine learning techniques.
- 7
- 7
- Application of deconvolutional networks for feature interpretability in epilepsy detection6
A novel convolutional neural network model, combining SE (Squeeze-and-Excitation) modules, was proposed on top of the Fully Convolutional Network, which showed superior advancement, stability, and reliability compared to the other methods.
- Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering6
This work presents the bilaterally slimmable Transformer (BST), a general framework that can be seamlessly integrated into arbitrary Transformer-based VQA models to train a single model once and obtain various slimmed submodels of different widths and depths.
- 6
- Attention and Engagement Aware Multimodal Conversational Systems6
This work aims to design and implement a multimodal dialog system to coordinate with users' engagement and attention on the fly via techniques such as adaptive conversational strategies and incremental speech production.
- Modified radon-Fourier transform for reflective tomography laser radar imaging6
The computer simulation result demonstrates the effectiveness of this modified algorithm to reconstruct image in reflective tomography using the diffuse reflection model (lamberts body).
- 6
- Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts5
A Diversified Layout benchmark for Chinese Street View Text Retrieval (DL-CSVTR), which is specifically designed to evaluate retrieval performance across various text layouts, including vertical, cross-line, and partial alignments, is established.
- The interpretable deep learning framework and validation for seizure detection in pediatric electroencephalography: An improved accuracy and performance analysis5
An interpretable deep learning framework is proposed and a fully convolutional network with squeeze-and-excitation modules (SE-FCN) is designed to enhance spatial sensitivity and retain temporal resolution and a transformer-based model is developed to capture temporal and channel-wise dependencies via self-attention.
- 5
- Distributed Estimation of Principal Support Vector Machines for Sufficient Dimension Reduction5
A naive and a refined distributed estimation algorithms for fast implementation when the sample size is large, which provides rigorous statistical guarantees for their application to large-scale datasets and hence is more advantageous when memory limitations exist on distributed machines.
- Parameter-Efficient Transfer Learning for Audio-Visual-Language Tasks5
This paper introduces a novel Long Short-Term Trimodal Adapter (LSTTA) approach for video understanding tasks involving audio, visual, and language modalities and shows the effectiveness of LSTTA over existing state-of-the-art methods.
- 5
- 5
- 5
- 5
- Impact of an Energy Normalization Transform on the Performance of the LF-ASD Brain Computer Interface5
An energy normalization transform is presented as a method to reduce system errors in the LF-ASD brain-computer interface and can increase class separation between the active and idle EEG data and desensitize the system to the signal amplitude variability.
- 5
- A Malicious URL Detection Framework Based on Custom Hybrid Spatial Sequence Attention and Logic Constraint Neural Network4
A novel detection framework, HSSLC-CharGRU (Hybrid Spatial–Sequential Attention Logically constrained neural network CharGRU), which balances high efficiency and accuracy while enhancing the generalization capability of detection frameworks.
- 4
- AI Safety Subproblems for Software Engineering Researchers4
The problem of long-term AI Safety from a Software Engineering (SE) research viewpoint, and the challenge of avoiding harms from AI as systems meet or exceed human capabilities, including software engineering capabilities (and approach AGI /"HLMI").
- Delegate-based Utility Preserving Synthesis for Pedestrian Image Anonymization4
A new delegate-based utility preserving synthesis (DUPS) approach for pedestrian image anonymization that can not only achieve superior anonymization performance against deep pedestrian recognizers, but also can obtain a better tradeoff between privacy protection and utility preservation compared with state-of-the-art methods.
- 4
- Application of Hybrid Ant Colony Algorithm in Urban Traffic Path Planning4
To plan the urban traffic path using the ant colony algorithm, the composition and functional division of the mobile robot are analyzed and the results showed that the artificial potential field method and the A* algorithm improved the performance of theAnt colony algorithm.
- Joint decision and Naive Bayes learning for detection of space multi-target4
Experimental results indicate that the proposed JD-NB algorithm not only possesses a high recognition rate of better than 90% for the target block, but also effectively overcomes the disturbance of the smear block.
- Nonholonomic Motion Planning Using Diffusion of Workspace Density Functions4
A trajectory planning algorithm for nonholonomic mobile robots which operate in an environment with obstacles that generates evolving probability density functions that describe all attainable positions and orientations of the robot at a given value of time.
- 3
- Indoor WiFi fingerprint localization based on dual population PSO of stacked autoencoder and multi label classification3
A deep neural network (DNN) framework that integrates a Stacked Autoencoder (SAE) for feature extraction and a multi-label classification strategy for accurate localization using received signal strength (RSS) data is proposed that outperforms traditional PSO and recent algorithms like the Sparrow Search Algorithm, achieving the global optimum in four cases.
- 3
- 3
- 3
- DialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs3
This work proposes DialogStitch, a novel framework to seamlessly ‘stitch’ multiple conversations and highlight these desirable traits in a taskoriented dialog, and demonstrates its benefits in two settings: multimodal, imagegrounded conversations, and task-oriented dialogs fused with chit-chat conversations.
- 3
- End‐to‐end visual grounding via region proposal networks and bilinear pooling3
An end-to-end approach to tackle the visual grounding problem, which uses a region proposal network to generate object proposals and the corresponding visual features simultaneously, and multi-modal factorised bilinear pooling model to fuse the multi- modal features effectively.
- Control analysis of acquirement and locking in inter-satellite laser communications3
Simulation results provide the suited condition parameters for both fine pointing system and coarse pointing system, which is very helpful to the subsequent point and tracking processes.
- 3
- Design of 2*6 optical hybrid in inter-satellite coherent laser communications3
This work presents a design of a 2*6 optical hybrid, which demodulates the incoming signal by mixing it with the local oscillator and captures the interference pattern from the wide beams, and then the pattern is processed and analyzed by the computer.
- 2
- 2
- 2
- 2
- Performance of polar codes with low complexity cyclic redundancy check aided bit‐flipping for successive cancellation list decoding over power line channels2
Experimental results demonstrate that the proposed decoder outperforms the traditional CRC‐aided SCL decoder in terms of decoding performance and complexity, and the suggested polar codes‐based OFDM‐based PLC system can reduce the bit error rate of the system in the presence of impulsive noise.
- 2
- 2
- SIHG4SR: Side Information Heterogeneous Graph for Session Recommender2
SIHG4SR outperforms the state-of-art baselines, getting an MRR score 0.20762 and ranked 4th position on final leaderboard(team name ”MooreWins”).
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- Generative object separation in X-ray images1
This work proposes a novel method for separating overlapping objects in X-ray images from the perspective of image inpainting by using a vision transformer to construct a generative adversarial network (GAN) model that requires a hand-created trimap as input.
- 1
- 1
- 1
- 1
- ETL Transformation Function Modeling Approach Based on Model Transformation1
This paper proposes a modeling method of ETL transformation function based on model transformation, combining the semantics of relational metamodel which are accurately represented by the description logic SHIQ with the relational algebra representation method, to model the ETl transformation function from the relational schema data source to the multidimensional data warehouse.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Chroma Backdoor: A Stealthy Backdoor Attack Based on High-Frequency Wavelet Injection in the UV Channels–
HCBA (high-frequency chroma backdoor attack), a novel backdoor attack method based on high-frequency injection in the UV chroma channels, achieves outstanding performance in terms of both stealthiness and evasion of existing defense mechanisms while maintaining a high attack success rate.
- –
- GTS_Forecaster: a novel deep learning based geodetic time series forecasting toolbox with python–
GTS Forecaster, an open-source Python package for geodetic time series forecasting, integrates advanced deep learning models -- including kernel attention networks (KAN), graph neural network-based gated recurrent units (GNNGRU), and time-aware graph neural networks (TimeGNN) -- to effectively model nonlinear spatial-temporal patterns.
- –
- –
- –
- Fine-Grained Underwater Visual Object Tracking via Long-Term Template Refinement–
This paper proposes to adapt the methodology for underwater tracking by performing a long-term template refinement to achieve fine-grained spatial template matching and long-range temporal dependency for use with a Siamese tracking network.
- DiSCo: Disentangled Attribute Manipulation Retrieval via Semantic Reconstruction and Consistency Regularization–
DiSCo is proposed, a novel disentangled attribute manipulation retrieval framework via semantic reconstruction and consistency regularization that achieves superior retrieval accuracy over state-of-the-arts while maintaining high-fidelity editing.
- Gradient learning of symmetric positive-definite matrix regression–
This paper focuses on the gradient learning in a regression setting where the response is a symmetric positive-definite (SPD) matrix and the predictor is a Euclidean vector and calculates the gradients by solving a linear system under the assumption that the gradient function resides in a reproducing kernel Hilbert space.
- –
- –
- –
- –
- –
- Automated right coronary artery localizer using deep learning for optimal cardiac phase selection–
Results based on real clinical data with a heart rate of 74 beats per minute have shown the proposed algorithm can efficiently localize the RCA for arbitrary cardiac phase, and accurately determine the optimal RCA reconstruction with minimal motion artifacts.
- –
- –
- –
- –
- –
- 3D scanning coherent lidar demonstration using frequency modulated continuous wave–
A coherent lidar system that produces 3D information of target by use of circularly scanning system that uses the frequency modulated continuous laser wave as optical source and has advantage of background noise resistance over traditional direct detection system is proposed.
- –
- –
- –
- –
- –
- –
- –
- The Appliance of Data Warehouse in Heterogeneous Database Integration–
It is a good solution that heterogeneous databases are made integrity by using data warehouse technology and the concept of data transform rule set was presented and used in extracting data processing.
- –
- LuSH: A Generic High-Dimensional Index Framework–
A generic high-dimensional index framework named LuSH, which means Lucenebased SH, uses SH as high- dimensional index and Lucene, the well-known open source inverted index, as underlying index file to speedup retrieval efficiency.
- –
- –
- –
- Design and development of control software in the experiment system of synthetic aperture laser imaging radar–
A control software experiment system of synthetic aperture imaging ladar that can operate the laser, stepper motor and oscillograph successfully is developed based on multithreading parallel mechanism of Labview8.6 and SCPI protocol.
- –
- –
- On parametric approach of aerial robots' visual navigation–
This approach paves the way for segmenting the image into distinct parts, which can be realized by deploying a Bayesian classifier on the picture cell level, which is considerably more robust to noises.
- A Bending Beam-Based Path Planning Method Suitable for Mobile Robots in Sensor Network Environments–
The proposed bending beam method may substantially reduce the time complexity of the sensor-based motion planning for mobile robots in dynamic environments, with the assistance from sensor networks.
- Assessment of body fat based on potential function clustering segmentation of computed tomography images–
An effective multi-thresholds image segmentation method based on potential function clustering is used to deal with multiple peaks in the grayness histogram of a CT image.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.