Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks397 from public data
- 1,208
- Two-Archive Evolutionary Algorithm for Constrained Multiobjective Optimization752
A parameter-free constraint handling technique, a two-archive evolutionary algorithm, for constrained multiobjective optimization that maintains two collaborative archives simultaneously and develops a restricted mating selection mechanism that adaptively chooses appropriate mating parents from them according to their evolution status.
- 427
- 357
- CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation241
This paper explores the potential of Contrastive Language-Image Pre-training models (CLIP) to localize different categories with only image-level labels and without further training, and proposes a novel WSSS framework called CLIP-ES.
- Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM215
This paper proposes a novel speech-text multimodal LLM architecture called Freeze-Omni, holding great potential to conduct speech-to-speech dialogue based on a multimodal LLM under the condition of a frozen LLM, avoiding the catastrophic forgetting problem caused by limited data and training resources.
- Dynamic Multiobjectives Optimization With a Changing Number of Objectives212
A dynamic two-archive evolutionary algorithm is implemented which maintains two co-evolving populations simultaneously which are complementary to each other: one concerns more about the convergence while the other concerns moreabout the diversity.
- 167
- speechocean762: An Open-Source Non-Native English Speech Corpus for Pronunciation Assessment152
This paper introduces a new open-source speech corpus, consisting of 5000 English utterances from 250 non-native speakers, where half of the speakers are children, designed for pronunciation assessment use.
- 148
- Achieving balance between proximity and diversity in multi-objective evolutionary algorithm147
A dynamic neighborhood multi-objective evolutionary algorithm based on hyper volume indicator (DNMOEA/HI), which benefits from both Pareto dominance and hypervolume indicator based frameworks is presented.
- 142
- From cloud to edge134
This study performs a first-of-its-kind measurement study on a leading public edge platform that has been densely deployed in China and quantitatively reveals the status quo of today's public edge platforms, and provides crucial insights towards developing and operating future edge services.
- 128
- R-Metric: Evaluating the Performance of Preference-Based Evolutionary Multiobjective Optimization Using Reference Points126
This paper suggests a systematic way to adapt the existing metrics to quantitatively evaluate the performance of a preference-based evolutionary multiobjective optimization algorithm using reference points using multicriterion decision making approach.
- Evolutionary Many-Objective Optimization Based on Adversarial Decomposition124
This paper develops an adversarial decomposition method for many-objective optimization, which leverages the complementary characteristics of different subproblem formulations within a single paradigm.
- CF-ViT: A General Coarse-to-Fine Method for Vision Transformer121
A coarse-to-fine vision transformer (CF-ViT) to relieve computational burden while retaining performance in this paper, motivated by two important observations in modern ViT models: The coarse-grained patch splitting can locate informative regions of an input image and network inference in a two-stage manner.
- SelfMatch: Robust semisupervised time‐series classification with self‐distillation118
A feature extractor for TSC is designed, called ResNet–LSTMaN, responsible for feature and relation extraction, and the experimental results show that SelfMatch achieves excellent SSL performance on 35 widely adopted UCR2018 data sets, compared with a number of state‐of‐the‐art semisupervised and supervised algorithms.
- 115
- A novel ensemble classification model based on neural networks and a classifier optimisation technique for imbalanced credit risk evaluation110
An ensemble model based on the synthetic minority over-sampling technique (SMOTE) and a classifier optimisation technique is proposed for personal credit risk evaluation that is more effective at processing credit data problems compared to the other classification models examined in this study.
- 106
- A dual-population paradigm for evolutionary multiobjective optimization100
A dual-population paradigm (DPP) that uses two separate and co-evolving populations to deal with convergence and diversity simultaneously and paves an avenue to integrate Pareto- and decomposition-based techniques in a single paradigm.
- Matching-Based Selection With Incomplete Lists for Decomposition Multiobjective Optimization94
The concept of incomplete preference lists is introduced into the stable matching model to remedy the loss of population diversity and an adaptive mechanism is developed to automatically set the length of the incomplete preference list for each solution according to its local competitiveness.
- Class-specific soft voting based multiple extreme learning machines ensemble90
A SpaCSSV-ELM method is proposed by transforming the weight optimization problem to a sparse coding problem, which uses the sparse representation technique for maintaining classification performance with less nonzero weight coefficients.
- Distributed coordinative transaction of a community integrated energy system based on a tri-level game model81
The effectiveness of the proposed tri-level game model and distributed solution algorithm was verified by case study, which confirmed that all stakeholders could benefit from the proposed transaction mechanism.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-15. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.