Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks196 from public data
- 211
- Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching199
This work presents Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks and demonstrates impressive generalization performance across various segmentation tasks, all without training.
- Improved Algorithms for the Feedback Vertex Set Problems160
Improved parameterized algorithms for the Feedback Vertex Set problem on both unweighted and weighted graphs are presented, both of which run in time O(5kkn2).
- TeachText: CrossModal Generalized Distillation for Text-Video Retrieval158
This work proposes a novel generalized distillation method, TeachText, which leverages complementary cues from multiple text encoders to provide an enhanced supervisory signal to the retrieval model and extends the method to video side modalities and shows that it can effectively reduce the number of used modalities at test time without compromising performance.
- Cross Modal Retrieval with Querybank Normalisation149
This work formulates a simple but effective framework called Querybank Normalisation (QB-NORM) that re-normalises query similarities to account for hubs in the embedding space, and shows that QB- NORM improves retrieval performance without requiring retraining.
- 139
- 131
- Weakly Supervised Video Moment Localization with Contrastive Negative Sample Mining125
A novel weakly supervised solution to video moment localization by introducing Contrastive Negative sample Mining (CNM), which uses a learnable Gaussian mask to generate positive samples, highlighting the video frames most related to the query, and considers other frames of the video and the whole video as easy and hard negative samples respectively.
- Amplifying Key Cues for Human-Object-Interaction Detection102
Two methods to amplify key cues in the image and a method to combine these and other cues when considering the interaction between a human and an object, which exceeds prior HOI methods across standard benchmarks by a considerable margin.
- Synthetically Supervised Feature Learning for Scene Text Recognition84
This work designs a multi-task network with an encoder-discriminator-generator architecture to guide the feature of the original image toward that of the clean image, and significantly outperforms the state-of-the-art methods on standard scene text recognition benchmarks in the lexicon-free category.
- 73
- Understanding and Mitigating Overfitting in Prompt Tuning for Vision-Language Models71
Subspace Prompt Tuning (Sub PT) is proposed to project the gradients in back-propagation onto the low-rank subspace spanned by the early-stage gradient flow eigenvectors during the entire training process and successfully eliminate the overfitting problem.
- Comparing HMM, maximum entropy, and conditional random fields for disfluency detection71
Overall it is found that that the conditional modeling approaches (Maxent and CRF) provide benefit over the HMM approach and provide a more principled way to model correlated features.
- 70
- Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation67
This work proposes an innovative framework, RMR_DSE that leverages a recall optimization mechanism to selectively memorize important parameters of previous tasks via regularization, and uses a domain drift estimation algorithm to compensate the drift between different do-mains in the embedding space.
- Fused GRU with semantic-temporal attention for video captioning56
This work proposes an end-to-end pipeline named Fused GRU with Semantic-Temporal Attention (STA-FG), which can explicitly incorporate the high-level visual concepts to the generation of semantic-temporal attention for video captioning.
- Recognizing Unseen Attribute-Object Pair with Generative Model55
This paper proposes a generative model with the encoder-decoder mechanism that bridges visual and linguistic information in a unified end-to-end network that presents the impressive potential to find an intrinsic attribute-object feature representation.
- Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training52
This work explores multi-modal correlations derived from large-scale image-text data to facilitate generalisable VMR and proposes a generic method, referred to as Visual-Dynamic Injection (VDI), to empower the model's understanding of video moments.
- 51
- Measuring and Reducing LLM Hallucination without Gold-Standard Answers50
This work proposes Factualness Evaluations via Weighting LLMs (FEWL), an innovative hallucination metric that is specifically designed for the scenario when gold-standard answers are absent and leverages the answers from off-the-shelf LLMs that serve as a proxy of gold-standard answers.
- 50
- DIURNAL VARIATION IN THE P300 COMPONENT OF HUMAN COGNITIVE EVENT-RELATED POTENTIAL47
The results suggest the existence of diurnal variation in human cognitive functions and the P300 latency was correlated positively with subjectively rated sleepiness and negatively correlated withsubjectively rated attention level.
- Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation46
A novel Uncertainty-induced Transferability Representation (UTR), which leverages uncertainty as the tool to analyse the channel-wise transferability of the source encoder in the absence of the sources data and target labels, and a novel Calibrated Adaption Framework for SFUDA.
- 44
- 42
- Exploring the Potential of Large Foundation Models for Open-Vocabulary HOI Detection39
A novel end-to-end open vocabulary HOI detection framework with conditional multi-level decoding and fine-grained semantic enhancement (CMD-SE), harnessing the potential of Visual-Language Models (VLMs) by leveraging large language models such as GPT models.
- 39
- Twitter summarization with social-temporal context30
This paper provides a methodology to model temporal context globally and locally, and proposes a novel unsupervised summarization framework with social-temporal context for Twitter data, to assess the proposed framework and demonstrate the importance of social- Temporal context in Twitter summarization.
- 30
- 30
- Diurnal variations in alpha power density and subjective sleepiness while performing repeated vigilance tasks30
Diurnal variations in EEG activity and subjectively rated sleepiness while performing repeated vigilance tasks were examined and the diurnal variation was found in alpha power while performing vigilance tasks.
- Zero-Shot Video Moment Retrieval from Frozen Vision-Language Models29
This work proposes a zero-shot method for adapting generalisable visual-textual priors from arbitrary VLM to facilitate moment-text alignment, without the need for accessing the VMR data, and devise a conditional feature refinement module to generate boundary-aware visual features conditioned on text queries to enable better moment boundary understanding.
- Generating Structured Pseudo Labels for Noise-resistant Zero-shot Video Sentence Localization28
A Structure-based Pseudo Label generation (SPL) is proposed, which first generate free-form interpretable pseudo queries before constructing query-dependent event proposals by modeling the event temporal structure.
- Mind-the-Gap! Unsupervised Domain Adaptation for Text-Video Retrieval28
This work proposes Concept-Aware-Pseudo-Query (CAPQ), a method for learning discriminative and transferable features that bridge these cross-domain discrepancies to enable effective target domain retrieval using source domain supervision.
- 27
- Phrase-Level Temporal Relationship Mining for Temporal Sentence Localization27
A phrase-level Temporal Relationship Mining (TRM) framework employing the temporal relationship relevant to the phrase and the whole sentence to have a better understanding of each semantic entity in the sentence.
- FaceChain-ImagineID: Freely Crafting High-Fidelity Diverse Talking Faces from Disentangled Audio25
This paper abstracts the process of people hearing speech, extracting meaningful cues, and creating vari-ous dynamically audio-consistent talking faces, termed Lis-tening and Imagining, into the task of high-fidelity diverse talking faces generation from a single audio, and intro-duce the Controllable Coherent Frame generation.
- LEBP -- Language Expectation & Binding Policy: A Two-Stream Framework for Embodied Vision-and-Language Interaction Task Learning Agents23
The LEBP contains a language expectation module to generate an expectation describing how to perform tasks by understanding the language instruction and uses the binding policy module to bind sub-steps in expectation to actual actions to specific scenarios.
- Respiration and Activity Detection Based on Passive Radio Sensing in Home Environments23
A deep learning enabled passive radio sensing method that can monitor human respiration and daily activities through leveraging unplanned and ever-present wireless bursts in the ISM frequency band, and can be employed as an additional data input within healthcare informatics.
- Cross Interaction Network for Natural Language Guided Video Moment Retrieval22
The proposed cross-attention method achieves superior performance compared to complex state of the art methods, in particular surpassing the SOTA on high IoU metrics (R@1, IoU=0.7) by 3.52% absolute (11.09% relative) on the Charades-STA dataset.
- 22
- 22
- EKF–GPR-Based Fingerprint Renovation for Subset-Based Indoor Localization with Adjusted Cosine Similarity22
A Fingerprint Renovation System (FRS) based on crowdsourcing is described, which avoids the use of manual labour to obtain the up-to-date fingerprint status and the proposed subset algorithm can bring less computation.
- 21
- Level of interest sensing in spoken dialog using multi-level fusion of acoustic and lexical evidence20
It is found that even though the word error rate is quite high, there is still performance gain by incorporating lexical information obtained from ASR output, and various combinations improve system performance.
- DiverGen: Improving Instance Segmentation by Learning Wider Data Distribution with More Diverse Generative Data19
It is argued that generative data can expand the data distribution that the model can learn, thus mitigating overfitting, and it is found that the diversity of generative data is crucial for improving model performance and enhance it through various strategies, including category diversity, prompt diversity, and generative model diversity.
- 19
- 18
- 18
- 18
- Near-surface pedestrian detection method based on deep learning for UAVs in low illumination environments16
The experimental results demonstrate that the YOLOv3 model is successfully transferred to the target dataset and the performance of the proposed detection model using the fused images for transfer training is the best among the different methods.
- VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator16
VISITRON is a multi-modal Transformer-based navigator better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN), and its ability to identify when to interact leads to a natural generalization of the game-play mode introduced by Roman et al. (2020).
- Speech Sentiment and Customer Satisfaction Estimation in Socialbot Conversations16
Insight is provided into open domain social conversations between real users and socialbots, and the use of both acoustic and lexical information for understanding the relationship between CSAT and sentiment scores is explored.
- 16
- Evaluating Factors Impacting the Accuracy of Forced Alignments in a Multimodal Corpus16
A number of factors that may contribute to highly accurate forced alignments to support the rapid production of these multimodal corpora including the acoustic model, the match between the speech used for training the system and that to be force aligned, the amount of data used to train the ASR system, the availability of speaker adaptation, and the duration of alignment segments are investigated.
- 15
- SpecEval: Evaluating Code Comprehension in Large Language Models via Program Specifications15
Inspired by the idea that specifications can act as a comprehensive articulation of program behaviors concerning all possible execution traces, SpecEval is proposed, a novel black-box evaluation framework to evaluate code comprehension in LLMs via program specifications.
- 15
- BiT-MamSleep: Bidirectional Temporal Mamba for EEG Sleep Staging14
BiT-MamSleep, a novel architecture that integrates the Triple-Resolution CNN for efficient multi-scale feature extraction with the Bidirectional Mamba mechanism, which models both short- and long-term temporal dependencies through bidirectional processing of EEG data, significantly outperforms state-of-the-art methods.
- 14
- Bayesian data fusion approaches to predicting spatial tracks: Application to marine mammals14
These two Bayesian approaches to combine accurate but sparse direct observations with another set of high-resolution but biased calculated observations are extended to estimate the path of a moving or evolving object and applied in a case study of tracking northern fur seals.
- ESIQA: Perceptual Quality Assessment of Vision-Pro-based Egocentric Spatial Images13
The Egocentric Spatial Images Quality Assessment Database (ESIQAD) is established, the first IQA database dedicated for egocentric spatial images as far as the authors know, and a novel mamba2-based multi-stage feature fusion model, termed ESIQAnet, which predicts the perceptual quality of egocentric spatial images under the three display modes.
- Advancing 3D Scene Understanding with MV-ScanQA Multi-View Reasoning Evaluation and TripAlign Pre-training Dataset13
This work introduces MV-ScanQA, a novel 3D question answering dataset where 68% of questions explicitly require integrating information from multiple views (compared to less than 7% in existing datasets), thereby rigorously testing multi-view compositional reasoning, and develops LEGO, a baseline method for the multi-view reasoning challenge in MV-ScanQA.
- 13
- 13
- Restoration of mobility through mobile health: the digital health code as a technology of governance13
This paper explores how this social biotechnology reconstructs the notion of health, how it restores mobility and in doing so how it strikes a balance between biosecurity and capital accumulation in post-pandemic societies.
- Using Relevant Public Posts to Enhance News Article Summarization13
Using public posts following a new article to improve automatic summary generation for the news article is explored and it is shown that relevant public posts provide useful information and can be effectively leveraged to improve news article summarization results.
- 13
- Transformer-based Graph Neural Networks for Battery Range Prediction in AIoT Battery-Swap Services12
This paper proposes a novel structural Transformer-based model, referred to as the SEB-Transformer, designed specifically for predicting the battery range of SEBs, conceptualized as a dynamic heterogeneous graph that encapsulates the interactions between users and bicycles, providing a comprehensive framework for analysis.
- On speaker-specific prosodic models for automatic dialog act segmentation of multi-party meetings12
It is concluded that features beyond pauses are useful for dialog act segmentation in natural conversation, and that for some speakers, speaker-specific training yields further gains.
- 11
- Speaker adaptation of language models for automatic dialog act segmentation of meetings11
This paper explores speaker adaptation of hidden event language models (LMs) for DA segmentation using the ICSI Meeting Corpus and finds the speaker-adapted LM yields statistically significant improvement over the baseline LM for both test conditions.
- 11
- TryOn-Adapter: Efficient Fine-Grained Clothing Identity Adaptation for High-Fidelity Virtual Try-On10
This work decouple clothing identity into fine-grained factors: style for color and category information, texture for high-frequency details, and structure for smooth spatial adaptive transformation and introduces the training-free T-RePaint strategy to further enhance clothing identity preservation while maintaining the realistic try-on effect during the inference.
- Active Object Detection with Knowledge Aggregation and Distillation from Large Models10
A knowledge distillation approach that encourages the student decoder to mimic the detection capabilities of the teacher decoder using the oracle query by replicating its predictions and attention and achieves state-of-the-art performance on four datasets.
- Burned area detection from a single satellite image using an adaptive thresholds algorithm10
A maximum curvature segmentation method to capture the adaptative thresholds for adaptive detection of burned areas and can provide real-time burned information for wildfire management systems.
- 10
- ResVG: Enhancing Relation and Semantic Understanding in Multiple Instances for Visual Grounding9
The proposed ReSVG model significantly improves the model's ability to comprehend both object semantics and spatial relations, leading to enhanced performance in visual grounding tasks, particularly in scenarios with multiple-instance distractions.
- 9
- A User Adaptive Model for Followee Recommendation on Twitter9
This paper designs an adaptive layer to dynamically leverage the contribution of topology and content to recommending followees, which changes the situation where the contribution weights are usually predefined.
- Coupled Directional Level Set for MR Image Segmentation9
A coupled directional level set model is proposed to segment the outer and inner boundaries simultaneously by exploiting the directional gradient, region information and thickness prior of the bladder wall.
- Distributed Range-Free Localization Algorithm for 3D Wireless Sensor Networks under Irregular Radio Propagation Model9
The 3D-DRL scheme eliminates the requirement for specific positioning hardware, avoids the need for any interaction between the individual unknown nodes, and is independent of node densities and network topologies.
- 9
- Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement8
A Training-Free Prompt, Image, and Guidance Enhancement (TPIGE) framework that bridges the semantic gap between the video description and the reference image and design sampling guidance that enhance identity preservation and video quality, achieving performance gains at minimal cost is introduced.
- 8
- Cosalpure: Learning Concept from Group Images for Robust Co-Saliency Detection8
A novel robustness enhancement framework is proposed by first learning the concept of the co-salient ob-jects based on the input group images and then leveraging this concept to purify adversarial perturbations, which are subsequently fed to CoSODs for robustness enhancement.
- RelScene: A Benchmark and baseline for Spatial Relations in text-driven 3D Scene Generation8
This paper conducts a dataset and benchmark for assessing spatial relations in text-driven 3D scene generation, which contains a comprehensive collection of 3D scenes, including textual descriptions, annotating object spatial relations, and providing both template and free-form natural language descriptions.
- An anchor-based convolutional network for the near-surface camouflaged personnel detection of UAVs8
A novel anchor-based method is proposed to detect the camouflaged personnel and demonstrates that the mean average precision of the proposed method can reach 85%, and the recall can reach 83% on the developed dataset.
- Phrase-level Prediction for Video Temporal Localization8
This paper builds a contrastive mechanism to restrain phrase-level localization without fine-grained phrase boundary annotation required in training, and proposes a clustering-based batch sampler to ensure that contrastive learning can be conducted efficiently.
- Eliminate Aspect Angle Variations for Human Activity Recognition using Unsupervised Deep Adaptation Network8
This paper aims to eliminate the aspect angle variations by learning aspect angle invariant and meanwhile discriminative features in the bi-static radar geometry using the unlabeled test data.
- AI Mathematician: Towards Fully Automated Frontier Mathematical Research7
This work proposes AI Mathematician (AIM) framework, which harnesses the reasoning strength of LRMs to support frontier mathematical research and highlights the potential of LRMs in mathematical discovery and suggests that LRM-based agent systems could significantly accelerate mathematical research in the future.
- Zero-Shot Cyclic Peptide Design via Composable Geometric Constraints7
CP-Composer is proposed, a novel generative framework that enables zero-shot cyclic peptide generation via composable geometric constraints and decomposes complex cyclization patterns into unit constraints, which are incorporated into a diffusion model through geometric conditioning on nodes and edges.
- Incorporating Pre-Training Data Matters in Unsupervised Domain Adaptation7
This study redefines UDA as a three-domain problem, i.e., source domain, target domain, and pre-training data domain, and proposes a novel framework, named TriDA, which maintains the pre-trained knowledge and improves the error bound by incorporating pre-training data into adaptation for both vanilla UDA and source-free UDA scenarios.
- Delving into the Continuous Domain Adaptation7
This work proposes a novel alternating training strategy to reduce discrepancies among multiple domains meanwhile generalize to unseen target domains, and proposes a continuity constraint when estimating the cross-domain divergence measurement.
- Generative Video Diffusion for Unseen Novel Semantic Video Moment Retrieval6
A hybrid selection mechanism is introduced that integrates three quantitative metrics to selectively incorporate synthetic video moments (novel video hypotheses) as enlarged additions to the original source training data, whilst minimising potential detrimental noise or unnecessary repetitions in the novel synthetic videos harmful to VMR learning.
- ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos6
The first Egocentric Spatial Video Quality Assessment Database (ESVQAD) is introduced, and a novel multi-dimensional binocular feature fusion model, termed ESVQAnet, is proposed, which integrates binocular spatial, motion, and semantic features to predict the overall perceptual quality.
- 6
- 6
- 6
- 6
- 6
- Factor analyzed Gaussian mixture models for speaker identification6
By FA modeled the data covariance, a relative gain of 39.6% over GMM baseline can be seen at the same amount of training data, and various tying strategies are studied too.
- InteractMove: Text-Controlled Human-Object Interaction Generation in 3D Scenes with Movable Objects5
This paper uses 3D visual grounding models to identify the interaction object, and proposes a hand-object joint affordance learning to predict contact regions for different hand joints and object parts, enabling accurate grasping and manipulation of diverse objects.
- Implicit Regression in Subspace for High-Sensitivity CEST Imaging5
By modeling spatial variant z-spectrums into low-dimensional subspace, IRIS is introduced, which is an unsupervised denoising algorithm utilizing the excellent property of implicit neural representation for continuous mapping that surpasses other CEST denoising methods regarding both qualitative and quantitative performance.
- 5
- 5
- 4
- Weakly and Single-Frame Supervised Temporal Sentence Grounding With Gaussian-Based Contrastive Proposal Learning4
This paper uses multiple learnable asymmetric Gaussian functions to generate both positive and negative proposals within the same video and proposes a controllable, easy-to-hard negative proposal mining strategy to collect negative samples within the same video, which enables CPL to distinguish highly confusing scenes.
- Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo4
A novel Source-Free Unsupervised Transferability Estimation (SUTE) is proposed, which enables assessing and comparing transferability across multiple source models with different architectures under domain shift, without requiring target labels and source data.
- 4
- 4
- Research on 3D Localization of Indoor UAV Based on Wasserstein GAN and Pseudo Fingerprint Map4
An innovative 3D localization method for indoor UAVs using a Wasserstein generative adversarial network (WGAN) and a pseudo fingerprint map (PFM) is proposed, demonstrating significant improvements in localization precision.
- Femtosecond laser ablation power level identification based on the ablated spot image4
A preliminary segmentation strategy for spot mark image based on the K-means clustering is proposed and the recognition model of laser power level based on SVM is constructed.
- Inter-procedural stacked register allocation for itanium® like architecture4
This work introduces the stacked register quota assignment problem based on the observation that reducing stacked register usage in some procedures could reduce the total memory access time of spilling registers, and proposes a new inter-procedural algorithm to solve the problem by allocating stacked registers across procedures based on a quantitative cost model.
- Interact-Custom: Customized Human Object Interaction Image Generation3
A two-stage model Interact-Custom is designed, which firstly explicitly model the spatial configuration by generating a foreground mask depicting the interaction behavior, then under the guidance of this mask, the target human object interacting while preserving their identities features.
- Risk-sensitive Reinforcement Learning Based on Convex Scoring Functions3
A reinforcement learning framework under a broad class of risk objectives, characterized by convex scoring functions, and an auxiliary variable sampling method inspired by the alternating minimization algorithm, which is convergent under certain conditions is proposed.
- Learn 3D VQA Better with Active Selection and Reannotation3
This paper proposes a multi-turn interactive active learning strategy that selects data based on models' semantic uncertainty to form a solid knowledge foundation more effectively and actively requests reannotation from an oracle to resolve potentially misleading labels.
- Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Data3
A realistic patient generation framework, Patient-Zero, which requires no real medical records and enables the generation of contextually diverse patient records while maintaining strict medical coherence, supported by adaptive dialogue strategies and real-time clinical plausibility verification.
- Investigating Domain Gaps for Indoor 3D Object Detection3
This paper considers the task of adapting indoor 3D object detectors from one dataset to another, presenting a comprehensive benchmark with ScanNet, SUN RGB-D and 3D Front datasets, as well as the authors' newly proposed large-scale datasets ProcTHOR-OD and ProcFront generated by a 3D simulator.
- Decoding nature’s melody: significance and challenges of machine learning in assessing bird diversity via soundscape analysis3
This review comprehensively and cohesively examines two predominant approaches in soundscape analysis: soundscape component recognition and acoustic indices methods, and surveys representative research within each category, outlining their respective strengths and limitations.
- 3
- Clinical evaluation of SonicFill bulk resin technique in the restoration of proximal deep caries of primary molars: a two-year randomized controlled trial3
The SonicFill resin technique has proven to be a viable and time-efficient option for the restoration of primary molars with deep proximal caries and has been a viable and time-efficient option for deep proximal restorations in primary molars.
- 3
- 3
- Risk-Averse Matchings over Uncertain Graph Databases3
This work introduces a novel formulation for finding matchings with maximum expected reward and bounded risk under a general model of uncertain weighted (hyper)graphs that generalizes probabilistic models used in prior work, and captures both continuous and discrete probability distributions.
- 3
- Online Allocation and Pricing with Economies of Scale3
This work considers the problem of offline and online allocation of goods that have economies of scale, or decreasing marginal cost per item for the seller, and shows that if customers have $$\{0,1\}$$ valuations over items, and the goal of the allocator is to give each customer an item he or she values, it can efficiently produce such an allocation with cost at most a constant factor greater than the minimum.
- Pessimistic Verification for Open Ended Math Questions2
This work proposes pessimistic verification, a paradigm of agentic workflows that rejects a solution if any of multiple parallel verifiers identifies a flaw, and introduces progressive pessimistic verification, which employs fine-grained proof decomposition to significantly enhance verification accuracy and efficiency.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Trilateration Based Joint Anchor Optimization Selection Mechanism2
Comprehensive simulations have been executed, demonstrating that the proposed theorem for distributing positioning reference points and the JAOS mechanism can effectively cater to the requirements of realtime positioning of mobile entities in the ubiquitous computing environment.
- 2
- 2
- 2
- Localization Algorithm for Mobile Nodes in Wireless Sensor Networks Based on Discrete-Time H∞ Filtering and Dynamic Node Model2
A discrete-time H∞ filtering and dynamic node model based algorithm that not only can achieve highly reliability but also the better localization accuracy under stochastic uncertainty wireless sensor network (WSN) conditions compared with the classic mobile MCL and MCB mobile schemes.
- 2
- 1
- 1
- Intent Recognition Based on Gaussian Mixture and Lane Change Decision Control for Intelligent Vehicles1
The effectiveness of the proposed method for intent recognition is demonstrated through simulation results, which show its capability in recognizing surrounding vehicles’ driving intentions and enabling decision-making and control based on both vehicle state and driving intent.
- 1
- An Incremental Regularization Kernel Randomized Neural Network for Electrical Energy Output Prediction in Combined Cycle Power Plant1
Experimental results indicate that the proposed IRKRNN achieves satisfactory generalization performance, and it has good potential for industrial data modeling tasks.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Variance-aware spatial decoupling attention for stereo matching1
An attention mechanism based on variance features is proposed, which promotes the neural network to deal with complicated regions by decoupling the space of the image, and a linear complexity attention mechanism is realized.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- INVALIDATION ANALYSIS AND REVISION OF POLAR FORMAT ALGORITHM FOR DECHIRPED ECHO SIGNALS IN ISAR IMAGING1
A revision method by range shifting is proposed to compensate the echo signals, and the standard polar section of the PFA is obtained.
- 1
- A Comprehensive Study of Inappropriate Hierarchy in WordNet1
A comprehensive study of the cases of ring and isolator for short is offered, finding two kinds of inappropriate hierarchy in WordNet that can cause a degenerate structure, harass the reasoning and eventually lead to errors.
- –
- –
- –
- –
- –
- Adaptive integrated weight unsupervised multi-source domain adaptation without source data–
This work addresses the source-free unsupervised multi-source domain adaptation problem, where only the source models are available during the adaptation and proposes a trust center sample-based source-free domain adaptation (TSDA) method to solve this problem.
- –
- –
- –
- Data-driven parallel optimization method for sensor placement and state estimation based on generative adversarial principle in unobservable systems–
A data-driven parallel optimization method for sensor placement and state estimation based on the generative adversarial principle in unobservable systems is proposed, which yields a significantly reduced number of sensor placement schemes compared to traditional methods, while maintaining high precision of DDSE.
- –
- –
- –
- –
- –
- Gated Recurrent Neural Network with Interaction Model of Multiple Targets for Traffic Radar Tracking–
- –
- –
- –
- UAV Target Detection under Complex Sky Background–
Experimental results show that this multi-sensor fusion model can effectively enhance the UAV target signal in a complex environment, and the threshold segmentation method also has good adaptability, and can effectively screen UAVs under a complex sky background.
- –
- –
- –
- Received Signal Strength Based Wireless Source Localization with Inexact Anchor Position.–
A relaxed semi-definite programming model to circumvent the non-convexity and a rounding algorithm concerning both the inexact source location and the inaccurate anchor location are proposed.
- –
- –
- –
- On the Partition of 3-Colorable Graphs–
This paper develops the first parameter algorithm of complexity O*(1.713k), taking the size of the bipartite subgraph as the parameter k, and uses measures other than the given parameter k to achieve better analysis on running time.
- –
- Measure-driven algorithm design and analysis: a new approach for solving np-hard problems–
This dissertation proposes a new approach of algorithm design and analysis: discovering better measures for problems that is extremely powerful for designing fixed-parameter tractable algorithms and good for designing exact algorithms for NP-hard problems by presenting an improved exact algorithm for the well-known SATISFIABILITY problem.
- A Region-Based Compilation Framework–
A new region-based compilation framework driven by the considerations of compilation resources and performance opportunities is proposed, which means some optimization-directed attributes can be passed and observed from optimization phase to phase on a region basis.
- –
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.