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
- Liang HeSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works48 from public data
- A survey of human-in-the-loop for machine learning829
This paper surveys existing works on human-in-the-loop from a data perspective and classify them into three categories with a progressive relationship: the work of improving model performance from data processing, the work through interventional model training, and the design of the system independent human- in- the-loop.
- 113
- 99
- Cross-modal fine-grained alignment and fusion network for multimodal aspect-based sentiment analysis92
- Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis52
Chimera is presented, a framework to derive fine-grained holistic features of aspects and infer the fundamental drivers of sentiment expression from both semantic perspectives and affective-cognitive resonance (the synergistic effect between emotional responses and cognitive interpretations).
- Multi-Channel Attentive Graph Convolutional Network with Sentiment Fusion for Multimodal Sentiment Analysis42
A Multi-channel Attentive Graph Convolutional Network (MAGCN), consisting of two main components: cross-modality interactive learning and sentimental feature fusion, that achieves competitive performance on accuracy and F1 scores compared to several state-of-the-art approaches.
- Targeted Sentiment Classification Based on Attentional Encoding and Graph Convolutional Networks42
This paper considers that the semantic information, syntactic information, and their interaction information are very crucial to targeted sentiment analysis, and proposes an attentional-encoding-based graph convolutional network (AEGCN) model that is mainly composed of multi-head attention and an improved graph convolutionsal network built over the dependency tree of a sentence.
- Multi-head self-attention based gated graph convolutional networks for aspect-based sentiment classification33
A novel gated graph convolutional networks on the dependency tree to encode syntactical information, and a Syntax-aware Context Dynamic Weighted layer is designed to guide the model to pay more attention to the local syntax-aware context.
- 31
- Electroencephalogram Access for Emotion Recognition Based on a Deep Hybrid Network31
A method of EEG access for emotion recognition based on a deep hybrid network was proposed, and the accuracy was improved by 0.99% on valence and 14.58% on dominance, which verified the effectiveness of the proposed method.
- 23
- Bayesian estimation‐based sentiment word embedding model for sentiment analysis20
Bayesian estimation ‐ based sentiment word embedding (BESWE) model, which aims to precisely extract the sentiment information of low ‐ frequency words, has been proposed and shows that BESWE outperforms many state ‐ of ‐ the ‐ art methods, for example, C&W, CBOW, GloVe, SE ‐ HyRank and DLJT1 in sentiment analysis tasks.
- 18
- 18
- 16
- 15
- 14
- 12
- 11
- 10
- 10
- Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering7
A progressive evidence refinement strategy for selecting crucial evidence and a multi-turn retrieval and question-answering strategy to handle multimodal inputs to mitigate the loss of fine-grained information are proposed.
- Cross-domain document layout analysis using document style guide6
This paper integrated the document quality assessment and the document cross-domain analysis into a unified framework that is composed of three components, Document Layout Generator, Document Elements Decorator, and Document Style Discriminator.
- 5
- 5
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.