Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks137 from public data
- TS2Vec: Towards Universal Representation of Time Series1,201
TS2Vec performs contrastive learning in a hierarchical way over augmented context views, which enables a robust contextual representation for each timestamp, which achieves significant improvement over existing SOTAs of unsupervised time series representation.
- Multivariate Time-Series Anomaly Detection via Graph Attention Network800
This paper proposes a novel self-supervised framework for multivariate time-series anomaly detection that outperforms other state-of-the-art models on three real-world datasets and has good interpretability and is useful for anomaly diagnosis.
- Semantic Flow for Fast and Accurate Scene Parsing456
This paper proposes a Flow Alignment Module (FAM) to learn Semantic Flow between feature maps of adjacent levels, and broadcast high-level features to high resolution features effectively and efficiently and exhibits superior performance over other real-time methods even on light-weight backbone networks.
- Improving Semantic Segmentation via Decoupled Body and Edge Supervision313
This paper proposes a new paradigm for semantic segmentation that establishes new state of the art while retaining high efficiency in inference and shows that the proposed framework with various baselines or backbone networks leads to better object inner consistency and object boundaries.
- Towards Open Vocabulary Learning: A Survey285
This paper thoroughly reviews open vocabulary learning, summarizing and analyzing recent developments in the field, and juxtaposing open vocabulary learning with analogous concepts such as zero-shot learning, open-set recognition, and out-of-distribution detection.
- Gated Fully Fusion for Semantic Segmentation249
This paper proposes a new architecture, named Gated Fully Fusion(GFF), to selectively fuse features from multiple levels using gates in a fully connected way, and achieves the state of the art results on four challenging scene parsing datasets including Cityscapes, Pascal Context, COCO-stuff and ADE20K.
- TransVOD: End-to-End Video Object Detection With Spatial-Temporal Transformers242
TransVOD is presented, the first end-to-end video object detection system based on simple yet effective spatial-temporal Transformer architectures that streamline the pipeline of current VOD, effectively removing the need for many hand-crafted components for feature aggregation.
- Dual Graph Convolutional Network for Semantic Segmentation.196
The Dual Graph Convolutional Network (DGCNet) models the global context of the input feature by modelling two orthogonal graphs in a single framework, which achieves state-of-the-art results on both Cityscapes and Pascal Context datasets.
- Boundary Content Graph Neural Network for Temporal Action Proposal Generation185
A novel Boundary Content Graph Neural Network (BC-GNN) is proposed to model the insightful relations between the boundary and action content of temporal proposals by the graph neural networks.
- Sa2VA: Marrying SAM2 With MLLM for Dense Grounded Understanding of Images and Videos168
Experiments show that Sa2VA achieves strong performance across multiple tasks, particularly in referring video object segmentation, highlighting its potential for complex real-world applications.
- Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees135
This paper proposes a novel framework named Syntax-BERT, which works in a plug-and-play mode and is applicable to an arbitrary pre-trained checkpoint based on Transformer architecture and achieves consistent improvement over multiple pre- trained models, including BERT, RoBERTa, and T5.
- Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation125
Video K-Net is presented, a simple, strong, and unified framework for fully end-to-end video panoptic seg-mentation that achieves state-of-the-art videoPanoptic segmentation results on Citscapes-VPS and KITTI-STEP without bells and whistles and can serve as a new flexible baseline in video segmentation.
- Enhanced Boundary Learning for Glass-like Object Segmentation123
This paper proposes a novel refined differential module that outputs finer boundary cues and introduces an edge-aware point-based graph convolution network module to model the global shape along the boundary.
- End-to-End Video Object Detection with Spatial-Temporal Transformers116
TransVOD is presented, an end-to-end video object detection model based on a spatial-temporal Transformer architecture that streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow, recurrent neural networks, relation networks.
- 115
- PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation111
A point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow, is proposed, which reduces the noise introduced by the background while keeping efficiency.
- Tornado95
Empirical evaluation conducted on Tornado validates that various real-time iterative analysis tasks can improve their performance and efficiently tolerate failures with the proposed execution model.
- 83
- LadaBERT: Lightweight Adaptation of BERT through Hybrid Model Compression81
A tailored solution named LadaBERT (Lightweight adaptation of BERT through hybrid model compression), which combines the advantages of different model compression methods, including weight pruning, matrix factorization and knowledge distillation, is proposed.
- Ranking Scientific Articles by Exploiting Citations, Authors, Journals, and Time Information78
This paper proposes a graph based ranking method, which utilizes citations, authors, journals/conferences and the publication time information collaboratively and shows that the approach is practical and ranks scientific articles more accurately than the state-of-art methods.
- Sfnet: Faster and Accurate Semantic Segmentation Via Semantic Flow70
A Flow Alignment Module (FAM) is proposed to learn Semantic Flow between feature maps of adjacent levels and broadcast high-level features to high-resolution features effectively and efficiently and integrating this FAM to a standard feature pyramid structure exhibits superior performance over other real-time methods.
- TextNAS: A Neural Architecture Search Space Tailored for Text Representation67
Through automatic search, the discovered network architecture outperforms state-of-the-art models on various public datasets on text classification and natural language inference tasks and agrees well with human intuition.
- Towards Robust Referring Image Segmentation66
This work proposes a new formulation of RIS, named Robust Referring Image Segmentation (R-RIS), which considers the negative sentence inputs besides the regular positive text inputs, and proposes a new transformer-based model, called RefSegformer, with a token-based vision and language fusion module.
- A Cooperative Multi-Agent Reinforcement Learning Framework for Resource Balancing in Complex Logistics Network65
This paper introduces an innovative cooperative mechanism for state and reward design resulting in more effective and efficient transportation and shows that this approach can give rise to a significant improvement in terms of both performance and stability.
- Graph Pointer Neural Networks58
A pointer network is used to select the most relevant nodes from a large amount of multi-hop neighborhoods, which constructs an ordered sequence according to the relationship with the central node, and a pointer-network-based ranker in GPNN is joint-optimized with other parts in an end-to-end manner.
- Triple-driven data modeling methodology in data warehousing54
A useful data modeling methodology in data warehousing which integrates three existing approaches normally used in isolation: goal-driven, data-driven and user-driven is presented which gets a more complete, more structured and more layered data model of a data warehouse.
- PolyphonicFormer: Unified Query Learning for Depth-Aware Video Panoptic Segmentation51
PolyphonicFormer, a vision transformer to unify these sub-tasks under the DVPS task and lead to more robust results, achieves state-of-the-art results on two DVPS datasets, and ranks 1st on the ICCV-2021 BMTT Challenge video + depth track.
- Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence50
This work introduces Open-o3-Video, a non-agent framework that integrates explicit spatio-temporal evidence into video reasoning by highlighting key timestamps, objects, and bounding boxes, making the reasoning process traceable and verifiable.
- Towards Language-Driven Video Inpainting via Multimodal Large Language Models48
This work introduces a new task - language-driven video inpainting, which uses natural language instructions to guide the inpainting process, integrating Multimodal Large Language Models to understand and execute complex language-based inpaintingrequests effectively.
- A Position Encoding Convolutional Neural Network Based on Dependency Tree for Relation Classification48
A new perspective on utilizing syntactic information of dependency parse tree is offered and a position encoding convolutional neural network (PECNN) based on dependencyparse tree for relation classification is presented.
- 45
- 41
- Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation40
This work devise a joint Caption Grounding and Generation (CGG) framework, which incorporates a novel grounding loss that only focuses on matching object nouns to improve learning efficiency and introduces a caption generation head that enables additional supervision and contextual modeling as a complementation to the grounding loss.
- VMoBA: Mixture-of-Block Attention for Video Diffusion Models39
Video Mixture of Block Attention (VMoBA) is introduced, a novel sparse attention mechanism specifically adapted for VDMs that significantly accelerates the training of VDMs on longer sequences, and exhibits competitive performance in training-free inference.
- Spherical Criteria for Fast and Accurate 360° Object Detection36
Experimental results reveal that compared with the existing criteria, the two-stage detector with spherical criteria achieves the best mAP results under the same inference speed, demonstrating that the spherical criteria can be more suitable for 360◦ object detection.
- Privacy Preserving Naive Bayes Classification35
This paper proposes a new randomization method, Randomized Response with Partial Hiding (RRPH), for distorting the original data, and an effective naive Bayes classifier is presented to predict the class labels for unknown samples according to the distorted data by RRPH.
- SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning34
Results collected from the production environment of ICBC show that SEFraud can provide accurate detection results and comprehensive explanations that align with the expert business understanding, confirming its efficiency and applicability in large-scale online services.
- 34
- The history, hotspots, and trends of electrocardiogram.34
The authors believe that improvement of the ECG instrumentation, big data mining for ECG, and the accuracy of diagnosis and application will be areas of continuous concern.
- 33
- Panoptic-PartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation29
The first end-to-end unified framework, Panoptic-PartFormer is designed, designing a meta-architecture that decouples part features and things/stuff features, respectively and proposes a new metric Part-Whole Quality (PWQ), better to measure this task from pixel-region and part-whole perspectives.
- 29
- SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow26
This work proposes a unified framework (SemFlow) and model them as a pair of reverse problems, motivated by rectified flow theory, and trains an ordinary differential equation model to transport between the distributions of real images and semantic masks.
- LLAVADI: What Matters For Multimodal Large Language Models Distillation26
Results show that joint alignment for both tokens and logit alignment plays critical roles in teacher-student frameworks and even a 2.7B small-scale model can perform on par with larger models with 7B or 13B parameters.
- Training-free Diffusion Acceleration with Bottleneck Sampling25
Bottleneck Sampling is introduced, a training-free framework that leverages low-resolution priors to reduce computational overhead while preserving output fidelity while maintaining output quality comparable to the standard full-resolution sampling process across multiple evaluation metrics.
- DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation23
This work proposes a new task: customized manga generation and introduces DiffSensei, an innovative framework specifically designed for generating manga with dynamic multi-character control, marking a significant advancement in manga generation by enabling text- adaptable character customization.
- Global Aggregation Then Local Distribution for Scene Parsing23
A novel local distribution module is designed which models the affinity map between global and local relationship for each pixel adaptively and can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks, giving rise to the GALD networks.
- NetRating: Credit Risk Evaluation for Loan Guarantee Chain in China22
A novel risk evaluation strategy, NetRating, is proposed to assess the risk level of each enterprise involved in the guaranteed loans, based on the k-shell decomposition method, and extended to deal with the direct guarantee networks.
- Representing document as dependency graph for document clustering21
A new similarity measure is proposed to compute the pairwise similarity of documents based on their corresponding dependency graphs and applied in the Group-average Agglomerative Hierarchial Clustering (GAHC) algorithm, the final clusters of documents can be obtained.
- Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models20
A unified yet straightforward framework that contains a mixed reward function design (Mixed-Reward) and a mixed post-training dataset (Mixed-45K) and a new open-ended reward named Bidirectional Max-Average Similarity (BMAS) by leveraging tokenizer embedding matching between the generated response and the ground truth.
- Competence-based Curriculum Learning for Multilingual Machine Translation20
This work focuses on balancing the learning competencies of different languages and proposes Competence-based Curriculum Learning for Multilingual Machine Translation, named CCL-M, and proposes a novel competenceaware dynamic balancing sampling strategy for better selecting training samples in multilingual training.
- 19
- Three-Fast-Inter Incremental Association Markov Blanket learning algorithm19
Experiments showed that Fit-IAMB had comparable accuracy and much better efficiency than state-of-the-art algorithms, especially for the high-dimensional data with limited samples, especially in the medical and biological study with expensive sample collection.
- 18
- Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs18
This work introduces Grasp Any Region (GAR) for region-level visual understanding, and constructs GAR-Bench, which not only provides a more accurate evaluation of single-region comprehension, but also, more importantly, measures interactions and complex reasoning across multiple regions.
- 17
- VG4D: Vision-Language Model Goes 4D Video Recognition17
This work proposes the Vision-Language Models Goes 4D (VG4D) framework, a framework to transfer VLM knowledge from visual-text pretrained models to a 4D point cloud network, and achieves improved recognition performance.
- Improving Video Instance Segmentation via Temporal Pyramid Routing17
A Temporal Pyramid Routing strategy to conditionally align and conduct pixel-level aggregation from a feature pyramid pair of two adjacent frames is proposed, which is a light-weight and plug-and-play module and can be easily applied to existing instance segmentation methods.
- 17
- Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer16
This work proposes DeT, a method that adapts DiT models to improve motion transfer ability and introduces a simple yet effective temporal kernel to smooth DiT features along the temporal dimension, facilitating the decoupling of foreground motion from background appearance.
- Convolution-Enhanced Evolving Attention Networks14
This work proposes a novel and generic evolving attention mechanism, which directly models the evolution of inter-token relationships through a chain of residual convolutional modules, and is the first work that explicitly models the layer-wise evolution of attention maps.
- 14
- 13
- Protecting the Publishing Identity in Multiple Tuples13
This paper analyzes the individually identifying attribute in the privacy preserving data publishing and proposes the concept of identity-reserved anonymity, and develops two approaches to meet identity- Reserved anonymity requirement.
- RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything12
This work explores a new real-time segmentation setting, named all-purpose segmentation in real-time, to transfer VFMs in real-time deployment and presents Real-Time All Purpose SAM (RAP-SAM), which contains an efficient encoder and an efficient decoupled decoder to perform prompt-driven decoding.
- DreamRelation: Bridging Customization and Relation Generation11
This work introduces DreamRelation, a framework that disentangles identity and relation learning using a carefully curated dataset and proposes two key modules to tackle the two main challenges of generating accurate and natural relationships, especially when significant pose adjustments are required, and avoiding object confusion in cases of overlap.
- Enhancing Self-Attention with Knowledge-Assisted Attention Maps11
This paper proposes a novel and generic solution, KAM-BERT, which directly incorporates knowledge-generated attention maps into the self-attention mechanism and requires only a few extra parameters and supports efficient fine-tuning once new knowledge is added.
- Fast and Accurate Scene Parsing via Bi-Direction Alignment Networks11
An effective method for fast and accurate scene parsing called Bidirectional Alignment Network (BiAlignNet) is proposed by aligning two-path information into each other through a learned flow field to avoid the noise and semantic gaps.
- Improving BERT With Self-Supervised Attention11
This paper proposes a novel technique, called Self-Supervised Attention (SSA), which automatically generates weak, token-level attention labels iteratively by probing the fine-tuned model from the previous iteration.
- StroMAX: Partitioning-Based Scheduler for Real-Time Stream Processing System11
StroMAX is presented, a graph-partitioning based approach of workload scheduling for real-time stream processing systems that reduces the inter-node communication cost while keeping the workload of nodes below a certain computational load threshold.
- Multi-view clustering with exemplars for scientific mapping10
This paper extracts the similarity matrices from the journal data sets in both cross citation view and text view and uses the AP algorithm to cluster the journals, and concludes that these two clustering results by the two single views are highly complementary.
- Identity-Reserved Anonymity in Privacy Preserving Data Publishing10
This paper analyzes the situation of multiple records one individual and proposes the principle of identity-reserved anonymity, which reserves more information while maintaining the individual privacy.
- MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation9
This work proposes a parallel multimodal diffusion framework, MMaDA-Parallel, that enables continuous, bidirectional interaction between text and images throughout the entire denoising trajectory, establishing a more robust paradigm for thinking-aware image synthesis.
- 9
- You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning9
This paper develops a unified graph denoising (UGD) framework to unravel the deadlock between structure and feature denoising, and proposes to refine noisy features with reconstruction based on a graph auto-encoder.
- 9
- 8
- Direct Preference Optimization for LLM-Enhanced Recommendation Systems8
DPO4Rec is proposed, a novel framework that integrates Direct Preference Optimization (DPO) into LLM-enhanced recommendation systems and significantly improves re-ranking performance over strong baselines, demonstrating enhanced instruction-following capabilities of LLMs in recommendation tasks.
- 8
- 8
- CyberV: Cybernetics for Test-time Scaling in Video Understanding7
This work proposes a novel framework inspired by cybernetic principles, redesigning video MLLMs as adaptive systems capable of self-monitoring, self-correction, and dynamic resource allocation during inference, and demonstrates consistent gains on general-purpose benchmarks, such as VideoMME and WorldSense.
- VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification6
VideoZeroBench, a challenging long-video benchmark with manually annotated question-answer pairs spanning 13 video domains, is introduced, and findings motivate more precise evidence search and localization for long-video question answering.
- LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing6
This work introduces a zero-overhead Scale-and-Add conditioning approach for video editing and eliminates the need for token concatenation, drastically reducing computational cost while maintaining robust capabilities for complex, non-rigid edits.
- Diffusion-Sharpening: Fine-tuning Diffusion Models with Denoising Trajectory Sharpening6
Diffusion-Sharpening is proposed, a fine-tuning approach that enhances downstream alignment by optimizing sampling trajectories by using a path integral framework to select optimal trajectories during training, leveraging reward feedback, and amortizing inference costs.
- Customizing graph neural networks using path reweighting6
The proposed CustomGNN can automatically learn the high-level semantics for specific downstream tasks to highlight semantically relevant paths as well to filter out task-irrelevant noises in a graph.
- 6
- Efficient incremental maintenance of frequent patterns with FP-tree6
In this paper, an efficient incremental mining algorithm, Incremental-Mining (IM), is proposed for maintenance of the frequent patterns when incremental data come, and it outperforms three other incremental algorithms: FUP, DB-tree and re-running frequent pattern growth (FP-growth).
- RecTok: Reconstruction Distillation along Rectified Flow5
This work proposes RecTok, which overcomes the limitations of high-dimensional visual tokenizers through two key innovations: flow semantic distillation and reconstruction--alignment distillation, to make the forward flow in flow matching semantically rich, rather than focusing on the latent space as in previous works.
- 5
- 5
- AutoADR4
This paper proposes AutoADR (Automatic model design for AD Relevance) --- a novel end-to-end framework to address the challenge of pre-trained language models deployment into industrial online systems, and shares the experience to ship these cutting-edge techniques into online Ad Relevantance system at Microsoft Bing.
- 4
- 4
- Watch, Remember, Reason: Human-View Video Understanding with MLLMs3
This work presents a human-view perspective on LLM-based video understanding, organized around three functional abilities: watching, remembering, and reasoning, and introduces a formulation that characterizes video understanding systems by their perceptual representations, memory states, reasoning traces, and final predictions.
- 3
- Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning3
This work presents Semantic-aware Active learning framework for Graphs (SAG) to mitigate the semantic confusion problem, and extensive experiments demonstrate that SAG significantly improves node classification performances and consistently outperforms previous methods.
- Flow2Seg: Motion-Aided Semantic Segmentation3
This paper leverages motion information densely represented by optical flow to assist the semantic segmentation task and finds that optical flow improves image-based segmentation on object boundaries especially on small thin objects.
- GVoS3
This article proposes a general NDV system on Storm (GVoS)—a popular distributed real-time stream processing platform—to simultaneously support a wide variety of video applications and presents an algorithm to reduce the size of SSM in order to avoid the data explosion and decrease the network latency.
- 3
- An approach for identifying attribute correspondences in multilingual schemas3
This paper focuses on a new problem in database integration---attribute correspondence identification in multilingual schemas, and gives a rule-based method for the problem, and implemented a prototype that shows its effectiveness in application.
- 2
- 2
- Multiple Connectivity Views for Session-based Recommendation2
This work develops the Multiple Connectivity Views for Session-based Recommendation (MCV-SBR), a unified framework that incorporates different modeling choices in a single model through the lens of connectivity view, and allows the search space of the combinations of connectivity views by the Tree-structured Parzen Estimator (TPE) algorithm.
- Label-Efficient Interactive Time-Series Anomaly Detection2
A Label-Efficient Interactive Time-Series Anomaly Detection (LEIAD) system, which enables a user to improve the results of unsupervised anomaly detection by performing only a small amount of interactions with the system.
- 2
- 2
- Improved IAMB with Expanded Markov Blanket for High‐Dimensional Time Series Prediction2
Empirical results show that the method based on EMB for macroeconomic prediction has less mean-square forecast error than other classic methods, especially when predicting the value with sharp fluctua- tion.
- Identifying Key Drivers of Return Reversal with Dynamical Bayesian Factor Graph2
A new method is developed to identify key drivers of return reversal by incorporating a comprehensive set of factors derived from different economic theories into one unified dynamical Bayesian factor graph, and finds that stocks with high turnover rates or high Amihud illiquidity measures have a greater probability of experiencing return reversals.
- 2
- Efficient and effective Bayesian network local structure learning2
This algorithm significantly improves computational efficiency by restricting the neighbors of each variable to a small subset of candidates and storing necessary information to uncover the spouses, at the same time guaranteeing to find the optimal neighbor set in the same sense as SLL.
- T-rotation: Multiple Publications of Privacy Preserving Data Sequence2
T-rotation mixes t continuous periods to form the dataset and then anonymizes, which avoids the inference by the temporal background knowledge and considerably improves the anonymity quality.
- IECS: An Integrated E-Community System for Management, Decision and Service2
The IECS supports management, decision and service of a government based on a unified data platform – the CDB and ensures data security by providing different workplaces and rights for different users.
- PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models1
PerceptionDLM is the first to achieve parallel region caption and perception by leveraging the advantages of diffusion language models, and highlights the potential of multimodal diffusion language models for efficient, parallel visual perception.
- One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration1
Fixed-Point Distillation is introduced, an end-to-end framework that constructs local correction targets by partially corrupting the student's one-step draft and refining it with a single teacher step, narrowing the gap to multi-step teachers while outperforming existing discrete distillation baselines.
- 1
- 1
- Dynamic Dual Sampling Module For Fine-Grained Semantic Segmentation1
A Dynamic Dual Sampling Module (DDSM) is proposed to conduct dynamic affinity modeling and propagate semantic context to local details, which yields a more discriminative representation.
- 1
- An Adaptive Approach to Schema Classification for Data Warehouse Modeling1
A method of classification of schema elements for DW modeling is proposed, putting forward the vector space models for subjects and schema elements, then an adaptive approach with self-tuning theory to construct context vectors of subjects, and finally classify the source schema elements into different subjects of the DW automatically.
- KD3 Scheme for Privacy Preserving Data Mining1
Privacy preserving data mining is a novel research direction to develop algorithms for modifying the original data in some way, so that the private information remains private even fter the mining process.
- Mining Association Rules from Distorted Data for Privacy Preservation1
A new association rule mining scheme based on data distortion that can simultaneously provide a higher privacy preserving level to the users and retain a higher accuracy in the mining results is presented.
- CyberETL: Towards Visual Debugging Transformations in Data Integration1
CyberETL has some innovative features, such as visual designing of transformations, bi-direction translation between transformations and SQL queries, and lineage-based data comparison and debugging.
- –
- Rethinking Vector Field Learning for Generative Segmentation–
This work revisits diffusion segmentation from the perspective of vector field learning, and proposes a principled vector field reshaping strategy that augments the learned velocity field with a detached distance-aware correction term.
- –
- Towards Customized Multimodal Role-Play–
It is argued that CMRP, coupled with unified modeling, provides a basis for next-generation characterful and immersive interactive agents.
- –
- –
- –
- –
- Customized Graph Embedding: Tailoring the Embedding Vector to a Specific Application.–
The CGE algo-rithm learns a customized vector representation of the graph by differentiating the varying importance of distinct graph paths by differentiating the varying importance of distinct graph paths.
- A Structural Based Community Similarity Algorithm and Its Application in Scientific Event Detection–
It is demonstrated that the novel algorithm is effective in detecting the anomalous events about the transition of communities’ structure, and performs better than the state-of-art algorithms.
- –
- –
- –
- –
- File Correspondences Dictionary Construction in Multilingual P2P File Sharing Systems–
A name-based approach for identifying sharing file correspondences in multilingual P2P systems and based on the relationships of those files names, a computer-aided method is proposed to solve the problem.
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.