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
- Roger ZimmermannSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works148 from public data
- Learning Intents behind Interactions with Knowledge Graph for Recommendation638
This study explores intents behind a user-item interaction by using auxiliary item knowledge, and proposes a new model, Knowledge Graph-based Intent Network (KGIN), which achieves significant improvements over the state-of-the-art methods like KGAT, KGNN-LS, and CKAN.
- NAIS: Neural Attentive Item Similarity Model for Recommendation593
This work proposes a neural network model named Neural Attentive Item Similarity model (NAIS), which is the first attempt that designs neural network models for item-based CF, opening up new research possibilities for future developments of neural recommender systems.
- Smart Contract Vulnerability Detection using Graph Neural Network475
This paper constructs a contract graph to represent both syntactic and semantic structures of a smart contract function, and proposes a degree-free graph convolutional neural network (DR-GCN) and a novel temporal message propagation network (TMP) to learn from the normalized graphs for vulnerability detection.
- LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting244
The LargeST benchmark dataset is introduced, which encompasses a total number of 8,600 sensors in California with a 5-year time coverage and includes comprehensive metadata and performs in-depth data analysis to extract data insights, benchmark well-known baselines in terms of their performance and efficiency, and identify challenges as well as opportunities for future research.
- Addressing Heterophily in Graph Anomaly Detection: A Perspective of Graph Spectrum242
The proposed indicator can effectively reduce the heterophily degree of the graph, thus boosting the overall GAD performance and showing that prediction errors are less likely to affect the identification process.
- Towards Automated Reentrancy Detection for Smart Contracts Based on Sequential Models228
This work attempts to utilize the deep learning-based approach, namely bidirectional long-short term memory with attention mechanism (BLSTM-ATT), aiming to precisely detect reentrancy bugs, and proposes contract snippet representations for smart contracts, which contributes to capturing essential semantic information and control flow dependencies.
- Smart Contract Vulnerability Detection: From Pure Neural Network to Interpretable Graph Feature and Expert Pattern Fusion178
This paper develops automatic tools to extract expert patterns from the source code and casts the code into a semantic graph to extract deep graph features and significantly outperforms state-of-the-art methods.
- 177
- 147
- Deep Dual Consecutive Network for Human Pose Estimation144
A novel multi-frame human pose estimation framework, leveraging abundant temporal cues between video frames to facilitate keypoint detection is proposed, which ranks No.1 in the Multi-frame Person Pose Estimation Challenge on the large-scale benchmark datasets PoseTrack2017 and PoseTrack2018.
- Rethinking Smart Contract Fuzzing: Fuzzing With Invocation Ordering and Important Branch Revisiting137
This paper implements IR-Fuzz, a fuzzing technique for smart contracts that detects more vulnerabilities and increases the average accuracy of vulnerability detection by 7% over current methods, and is fast, generating an average of 350 test cases per second.
- 127
- Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection123
A novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature, and derives Local Information Loss to guarantee the orthogonality of local representations while preserving comprehensive task-relevant information.
- Cross-Modality Mutual Learning for Enhancing Smart Contract Vulnerability Detection on Bytecode111
A novel cross-modality mutual learning framework for enhancing smart contract vulnerability detection on bytecode and Experimental results show that this method significantly surpasses state-of-the-art approaches.
- 2D Human pose estimation: a survey111
This paper seeks to provide researchers with a more comprehensive and systematic review on human pose estimation, allowing them to acquire a grand panorama and better identify future directions.
- Alleviating Structural Distribution Shift in Graph Anomaly Detection106
A prototype vector is devised to infer and update this distribution of anomaly features during training to mitigate the effect of heterophilous neighbors and make them invariant, and the proposed framework achieves a remarkable performance boost in GAD.
- Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction96
A novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction which simultaneously models local motion contexts and a global context is proposed and achieves much enhanced long-term prediction proficiency, such as retaining natural human-like motions over 50 seconds predictions.
- Behavior pattern clustering in blockchain networks96
This paper introduces the problem of behavior pattern clustering in blockchain networks and proposes a novel algorithm termed BPC for this problem, evaluating a long list of potential sequence similarity measures, and selecting a distance that is suitable for the behaviorpattern clustering problem.
- 82
- Blockchain for finance: A survey82
The authors focus on blockchain‐based securities trading, in which blockchain technology plays a vital role in financial services as it ultimately lifts trust and frees the need for third‐party verification by using consensus‐based verification.
- 81
- Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation78
A novel hierarchical alignment framework is presented, which leverages coarse-to-fine deformations to progressively update a neighboring frame to align with the current frame at the feature level and theoretically analyzed the mutual information between the frames and arrived at a loss that maximizes the task-relevant mutual information.
- Locate and Verify: A Two-Stream Network for Improved Deepfake Detection73
An innovative two-stream network is proposed that effectively enlarges the potential regions from which the model extracts forgery evidence, and a Semi-supervised Patch Similarity Learning strategy to estimate patch-level forged location annotations is proposed.
- Aggregated Multi-GANs for Controlled 3D Human Motion Prediction66
A generalization of the human motion prediction task in which control parameters can be readily incorporated to adjust the forecasted motion, and a simple yet effective composite GAN structure, consisting of local GANs for different body parts and aggregated via a global GAN is presented.
- 64
- Hierarchical multi-view context modelling for 3D object classification and retrieval56
A hierarchical multi-view context modelling method for 3D object classification and retrieval that can imitate the human need to look back and forth to identify and compare the discriminative parts of individual 3D objects based on a joint convolutional neural network and bidirectional long short-term memory network.
- 54
- DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues50
A novel incremental learning framework that improves the generalization of deepfake detection models by continual learning from a small number of new samples by preventing overfit to the insufficient new data.
- GPS2Vec49
A novel two-level grid based framework to learn semantic embeddings for geo-coordinates worldwide and improves classification results have been obtained based on a simple early feature fusion technique.
- Research on Multi-UAV Formation and Semi-Physical Simulation With Virtual Structure48
A single-route virtual structure formation method with geometric constraint rules that can achieve formation control and effectively reduce the requirements of network radios during task execution is proposed.
- 48
- Deep Active Learning with Contaminated Tags for Image Aesthetics Assessment47
A novel semi-supervised deep active learning (SDAL) algorithm is proposed, which discovers how humans perceive semantically important regions from a large quantity of images partially assigned with contaminated tags, and a probabilistic model is developed for image aesthetics assessment.
- A Truthful FPTAS Mechanism for Emergency Demand Response in Colocation Data Centers44
This paper formalizes the MEDR problem and proposes a dynamic programming to solve the optimization version of the problem, and design and prove that the mechanism is truthful, an FPTAS, and outperforms near-optimal and high utility.
- 42
- 42
- Transferring Audio Deepfake Detection Capability across Languages41
This paper conducts the first comprehensive study on the cross-lingual perspective of deepfake detection, observing that English data enriched in deepfake algorithms can teach a detector the knowledge of various spoofing artifacts, contributing to performing detection across language domains.
- 39
- Multiview and Multimodal Pervasive Indoor Localization33
This paper addresses the deficiency of using a single measurement by proposing the original idea of localization based on multi-view and multi-modal measurements, and constructs a benchmark dataset for the PIL task, which to this knowledge is the first public dataset that is tailored for multi-View multi- modal indoor localization and contains both magnetic and visual signals.
- Motion Prediction via Joint Dependency Modeling in Phase Space31
This paper introduces a novel convolutional neural model to effectively leverage explicit prior knowledge of motion anatomy, and simultaneously capture both spatial and temporal information of joint trajectory dynamics, and proposes a global optimization module that learns the implicit relationships between individual joint features.
- Weakly Supervised Multimodal Kernel for Categorizing Aerial Photographs30
A new image kernel is proposed for effectively recognizing aerial photographs, to encode high-level semantic cues into local image patches in a weakly supervised way, and integrate multimodal visual features using a newly developed hashing algorithm.
- Detecting Missed Security Operations Through Differential Checking of Object-based Similar Paths28
Inconsistent Path Pairs as a bug Oracle is presented, a static analysis framework for detecting security bugs based on differential checking that eliminates the requirement of constructing a large number of similar code pieces, addressing the limitation of traditional cross-checking approaches.
- 24
- Learning Human Motion Prediction via Stochastic Differential Equations23
This work proposes a novel approach in modeling the motion prediction problem based on stochastic differential equations and path integrals, and develops a strategy of employing GANs to simulate path Integrals that amounts to optimizing over possible future paths.
- Category-Level Articulated Object 9D Pose Estimation via Reinforcement Learning22
A novel framework called Articulated object 9D Pose Estimation via Reinforcement Learning (ArtPERL), which formulates the category-level ArtOPE as a reinforcement learning problem, and introduces a joint-centric pose modeling strategy that estimates 9D pose by fitting joint states via reinforced agent training.
- 22
- 21
- 21
- Fast and parameter-light rare behavior detection in maritime trajectories21
A scheme cross trajectories, vessel attributes and the movement context for detecting rare behaviors through preprocessing, kNN-based clustering, and verification is concerned, which shows that high accuracy to labelled anomalies and useful rare behaviors can be achieved.
- FastShrinkage21
A novel retargeting framework which fast shrinks photo/video by leveraging human gaze behavior, and the retargeted photos/videos produced by the method outperform its competitors significantly based on the paired-comparison-based user study.
- Joint-Motion Mutual Learning for Pose Estimation in Video20
A novel joint-motion mutual learning framework for pose estimation that effectively concentrates on both local joint dependency and global pixel-level motion dynamics, and introduces a context-aware joint learner that adaptively leverages initial heatmaps and motion flow to retrieve robust local joint feature.
- Empirical Review of Smart Contract and DeFi Security: Vulnerability Detection and Automated Repair20
This paper presents an empirical study of 42 state-of-the-art techniques that can detect smart contract and DeFi vulnerabilities, and evaluates the effectiveness of traditional smart contract bug detection tools in analyzing complex DeFi protocols.
- Do as I Do: Pose Guided Human Motion Copy19
This work constrain pose-to-appearance generation with a perceptual loss and a theoretically motivated Gromov-Wasserstein loss to bridge the gap between pose and appearance and presents an episodic memory module in the pose-to-appearance generation to propel continuous learning that helps the model learn from its past poor generations.
- Enhanced Audio Tagging via Multi- to Single-Modal Teacher-Student Mutual Learning19
This work presents a novel visual-assisted teacher-student mutual learning framework for robust sound event detection from audio recordings that takes the advantages of joint audio-visual analysis in training while maximizing the feasibility of the model in use cases.
- Prior-free rare category detection: More effective and efficient solutions19
Two prior-free RCD algorithms are proposed, namely (1) iFRED which achieves linear time complexity w.r.t. N, and (2) vFREDWhich substantially reduces the number of labeling queries.
- 17
- Learning from Crowds under Experts’ Supervision17
This work proposes to improve the performance of crowdsourcing learning tasks with some additional expert labels by treating each labeler as a personal classifier and combining all labelers’ opinions from a model combination perspective.
- TTIDA: Controllable Generative Data Augmentation via Text-to-Text and Text-to-Image Models16
By conditioning the T2I model on detailed descriptions produced by T2T models, TTIDA is able to generate photo-realistic labeled images in a flexible and controllable manner, and shows consistent improvements over other data augmentation baselines.
- 16
- 15
- 15
- GLPose: Global-Local Representation Learning for Human Pose Estimation15
This paper argues that combining global semantically similar information and local temporal visual context will deliver more comprehensive and more robust representations for human pose estimation and presents an effective framework, namely global-local enhanced pose estimation (GLPose) network.
- 15
- 15
- Perceptual multi-channel visual feature fusion for scene categorization15
This work designs a weakly supervised embedding algorithm which projects the local image features of graphlets onto the pre-defined semantic space, and formulates a sparsity-constrained graphlet ranking algorithm which incorporates visual clues at both the low-level and the high-level.
- Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization14
This paper proposes to incorporate an acceleration representation, explicitly modeling the higher-order variations in motion, and introduces a novel Stream-GCN network equipped with multi-stream components and channel attention, where different representations supplement each other towards a more precise action recognition while attention capitalizes on those important channels.
- Who is gambling? Finding cryptocurrency gamblers using multi-modal retrieval methods14
A tool to automatically detect the smart contracts and addresses involved in gambling by scrutinizing the smart contract code and address transaction records is proposed, and a novel LightGBM model with memory components, which possesses the ability to learn from its own misclassifications, is presented.
- False data separation for data security in smart grids14
This paper modeling the false data problem as a rank-bounded L1 norm optimization and proposing both offline and online algorithms to filter out the injected false data and recover original measurement data is proposed.
- Toward seed-insensitive solutions to local community detection14
A seed-insensitive method called GMAC and its variation iGMAC are presented and it is shown that they estimate the similarity among vertices by investigating vertices’ neighborhoods, and reveal a local community by maximizing its internal similarity and minimizing its external similarity simultaneously.
- 13
- Conan's Bow Tie: A Streaming Voice Conversion for Real-Time VTuber Livestreaming13
This work introduces VTuberBowTie, a user-friendly streaming voice conversion system for real-time VTuber livestreaming, and proposes an innovative streaming voice conversion approach that tackles the challenges of limited context modeling and bidirectional context dependence inherent to conventional real-time voice conversion.
- 13
- Exploring lottery ticket hypothesis in media recommender systems13
The recently proposed lottery ticket hypothesis (LTH) is extended to media recommender systems, aiming to find the winning tickets in deep recommender models, with Matrix Factorization and Light Graph Convolution Networks as the backbone models.
- Toward Personalized Activity Level Prediction in Community Question Answering Websites13
An algorithm termed PALP is the first approach to address a personalized activity level prediction model for CQA websites and takes into consideration user behavior change over time and focuses specifically on expert users.
- Multi-threshold deep metric learning for facial expression recognition12
This paper presents the multi-threshold deep metric learning technique, which not only avoids the difficult threshold validation but also vastly increases the capacity of triplet loss learning to construct expression feature representations.
- Multi-Level Fusion based Class-aware Attention Model for Weakly Labeled Audio Tagging12
A novel end-to-end multi-level attention model that first makes segment-level predictions with temporal modeling, followed by advanced aggregations along both time and feature domains and introduces a weight sharing strategy to reduce model complexity and overfitting is presented.
- 12
- 11
- A Causal View for Item-level Effect of Recommendation on User Preference11
This work designs a method to estimate the item-level effects from the causal perspective and resorts to causal graphs to characterize the average treatment effect of recommending an item on the preference of another item.
- Dual Learning Music Composition and Dance Choreography11
A novel extension of generative models for dance sequences conditioned on music by introducing an optimal transport objective to align feature embeddings, as well as a cycle consistency loss to foster overall consistency.
- 11
- 10
- Learning Multi-context Aware Location Representations from Large-scale Geotagged Images10
This paper presents a machine learning based approach, termed GPS2Vec+, which learns rich location representations by capitalizing on the world-wide geotagged images, and yields significant performance improvements over the state-of-the-art geotag encoding methods on image classification and venue annotation.
- Multi-Modal Multi-Task Learning for Automatic Dietary Assessment10
An end-to-end neural model is proposed for automatic dietary assessment that outperforms two strong image captioning baselines significantly and introduces a novel memory network architecture to store meal representations and reason over the meal representations to support predictions.
- Rare Category Exploration on Linear Time Complexity10
Free is presented, an effective and efficient RCE solution to explore rare categories of arbitrary shapes on a linear time complexity w.r.t. data set size and results on both synthetic and real data sets verify the effectiveness and efficiency of this approach.
- A formalized framework for incorporating expert labels in crowdsourcing environment10
This paper proposes a novel framewor for improving the performance of crowdsourcing learning tasks by some additional expert labels, that is, it treats each labeler as a personal classifier and combine all labelers’ opinions from a model combination perspective, and summarizes the evidence from crowds and experts naturally via a Bayesian classifier in the intermediate feature space formed by personal classifiers.
- 9
- Personalized motion kernel learning for human pose estimation9
This paper proposes a novel approach to learn specific keypoint motion representations for each person, termed Personalized Motion‐Aware Network (PMAN), which surpasses the state‐of‐the‐art method by +1.7 mAP and achieves 82.9 mAP on PoseTrack2017 dataset.
- Handwriting posture prediction based on unsupervised model9
This paper proposes a neural network constructed with small convolution kernels to extract features from handwriting, and incorporate unsupervised learning and handwriting data analysis to predict writing postures and achieves an accuracy rate significantly higher than the human experts.
- 9
- Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction8
A deep learning model composed of Parallel multi-graph convolution and stacked Bidirectional unidirectional Gated Recurrent Unit (PB-GRU) achieves much lower prediction error compared with the existing methods.
- A Spatial Regulated Patch-Wise Approach for Cervical Dysplasia Diagnosis8
This work divides an image into patches and then represents it from patch features in a weighted manner by considering the patch--image label relation, and introduces a spatial regulator to guide the classifier to focus on the cervix region and to adjust the weight distribution, without requiring any manual annotations of the cervIX region.
- 8
- 8
- 8
- ANNProof: Building a verifiable and efficient outsourced approximate nearest neighbor search system on blockchain7
ANNProof is proposed, a novel framework supporting verifiable outsourced K-ANNS on the blockchain supporting verifiable outsourced K-ANNS on the blockchain and utilizes two innovative authenticated data structures (ADS), the Merkle HNSW node tree.
- 7
- Cofopose: Conditional 2D Pose Estimation with Transformers7
Cofopose is a two-stage approach consisting of a person and keypoint detection transformers for 2D human pose estimation that uses conditional cross-attention, a conditional DEtection TRansformer, and an encoder-decoder in the transformer framework; this allows it to achieve person andKeypoint detection.
- 5
- Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection5
A novel prototype-based knowledge filtering method to estimate the transferability of cross-domain samples and optimize the shared feature space by aligning the cross- domain image representations simultaneously on domain level with early alignment and class level with supervised contrastive learning, which endows model training and knowledge transfer with stronger robustness.
- Rare category exploration via wavelet analysis: Theory and applications5
A novel approach RCEWA for RCE which achieves a linear time complexity and achieves a higher F-score of mining results, and a solid theoretical analysis is conducted to prove the feasibility of this solution.
- 4
- A Survey on Image Segmentation and Super-resolution Reconstruction in Visual Sensor Networks4
This survey provides a comprehensive review on image segmentation and super-resolution reconstruction, two key image processing tasks for VSNs, since these two tasks can effectively improve the performance and balance key factors for the performance of VSNs.
- Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models4
CoprGuard is introduced, a robust frequency domain watermarking framework to safeguard against unauthorized image usage in diffusion model training and fine-tuning and demonstrates remarkable effectiveness against a wide range of models.
- I Know Who Clones Your Code: Interpretable Smart Contract Similarity Detection4
This work introduces SmartDetector, a novel approach for computing similarity between smart contract functions, explainable at the fine-grained statement level, and mathematically derives a cosine-wise diffusion process to efficiently search optimal hyperparameters.
- 4
- 3
- PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack3
PhyCamo is introduced, a robust physical camouflage framework based on contrastive learning that distinguishes itself from prior research in various critical ways: data augmentation - it utilizes the diffusion model for data augmentation to efficiently simulate sophisticated physical dynamics in real-world, and robustness - it leverages contrastive learning to optimize physical camouflage against encoders with the state-of-the-art (SOTA) attack performance.
- 3
- OpenAVS: Training-Free Open-Vocabulary Audio Visual Segmentation with Foundational Models3
A novel training-free language-based approach that effectively aligns audio and visual modalities using text as a proxy for open-vocabulary Audio-Visual Segmentation (AVS) and a model-agnostic framework OpenAVS-ST that enables the integration of OpenAVS with any advanced supervised AVS model via pseudo-label based self-training.
- 3
- Rare Category Detection Forest3
A novel tree-based algorithm known as RCD-Forest with time complexity and high query efficiency where n is the size of the unlabeled data set and the effectiveness and efficiency of this method is verified.
- When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection2
This paper identifies, for the first time, a key failure mechanism, termed semantic fallback, wherein forensic fine-tuning fails to fully reshape the representation space, and proposes a GSD framework, which explicitly suppresses semantically dominant directions, thereby promoting invariant forensic representations.
- 2
- 2
- 2
- Fight Perturbations With Perturbations: Defending Adversarial Attacks via Neuron Influence2
Neuron-level Inverse Perturbation (NIP), a novel defense against general adversarial attacks, is proposed, which can quantitatively measure neurons’ contribution to correct classification.
- GITPose: going shallow and deeper using vision transformers for human pose estimation2
Comprehensive evaluation and testing on the COCO and MPII benchmark datasets reveal that GITPose achieves a competitive average precision (AP) on pose estimation compared to its state-of-the-art approaches.
- 2
- Interactive Rare-Category-of-Interest Mining from Large Datasets2
A new model named IRim is contributed, which can interactively mine rare category data examples of interest over large datasets and achieves the response time in seconds for user interactions, and outperforms state-of-the-art competitors significantly in accuracy and number of queries.
- Rare category exploration with noisy labels2
Extensive experiments have been conducted on six real-world datasets, which show that the proposed label propagation based algorithm SLP outperforms the state-of-the-art RCE approaches and is able to achieve a satisfactory accuracy.
- 2
- Unveiling Deepfakes: A Frequency-Aware Triple Branch Network for Deepfake Detection1
A triple-branch network is proposed that jointly captures spatial and frequency features by learning from both original image and image reconstructed by different frequency channels and is mathematically derive feature decoupling and fusion losses grounded in the mutual information theory, which enhances the model to focus on task-relevant features across the original image and the image reconstructed by different frequency channels.
- BINALIGNER: Aligning Binary Code for Cross-Compilation Environment Diffing1
A novel diffing approach B IN A LIGNER is proposed to alleviate the above limitations at the binary level and to reduce the likelihood of false and missed matches corresponding to the same source code snippets, and instruction-independent basic block features for sub-graph embedding generation.
- 1
- Blockchain-Based Federated Recommendation with Incentive Mechanism1
The experimental results show that the proposed incentive mechanism can attract clients with superior training data to engage in the federal recommendation at a lower cost, which can increase the economic benefit of federal recommendation by 54.9\% while improve the recommendation performance.
- Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization1
This paper proposes to disentangle an original high-dimensional feature into multiple sub-features, explicitly disentangling the feature into exclusive lower-dimensional components, and theoretically analyzed the mutual information between the label and the disentangled features, arriving at a loss that maximizes the extraction of task-relevant information from the original feature.
- Cross-Modal and Multi-Attribute Face Recognition: A Benchmark1
This work proposes a NIR-VIS cross-modal face recognition model that can effectively extract modal information by constraining the similarity distribution of modalities and then using the orthogonal loss to removemodal information from identity features.
- 1
- 1
- 1
- –
- Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios–
A developer-centric perspective is adopted and three representative risk scenarios that commonly lead to security vulnerabilities in LLM-generated code are identified: Ambiguous Requirements, Under-Specified Operational Context, and Security--Functionality Conflict are identified.
- –
- –
- DeFiScreener: Efficient DeFi Attack Pre-screening in Smart Contracts via Historical Case Matching–
DeFiScreener is proposed, the first automated pre-screening framework for DeFi attacks that uses historical exploit cases to identify potentially vulnerable functions and call sequences and achieves a remarkable 98.55% recall and 84.30% precision in attack pre-screening.
- –
- –
- Morphology-optimized Multi-Scale Fusion: Combining Local Artifacts and Mesoscopic Semantics for Deepfake Detection and Localization–
This work proposes a novel approach that independently predicts manipulated regions using both local and global perspectives, and employs morphological operations to fuse the outputs, effectively suppressing noise while enhancing spatial coherence.
- –
- –
- –
- An Innovative Obstacle Avoidance Algorithm for UAV Based on Hemispherical Optimal Path–
The nonlinear numerical simulation of a type of UAV shows that the presented obstacle avoidance algorithm can avoid obstacles effectively with high accuracy for 3D trajectory tracking, which can be applied to UAV’s obstacle avoidance missions.
- Special issue on multimedia recommendation and multi-modal data analysis–
This special issue seeks original contributions related to either multimedia recommendation or multi-modal data analysis related to recommendation, including music recommendation and retrieval, clothes recommendation, app usage recommender system, and multi- modal 3D model recognition.
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.