Picture for Jianxing Yu

Jianxing Yu

School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519082, Guangdong Key Laboratory of Big Data Analysis and Processing, 510006, China, Pazhou Lab, Guangzhou, 510330, China

Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference

Add code
Oct 10, 2024
Figure 1 for Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference
Figure 2 for Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference
Figure 3 for Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference
Figure 4 for Multimodal Clickbait Detection by De-confounding Biases Using Causal Representation Inference
Viaarxiv icon

VideoQA in the Era of LLMs: An Empirical Study

Add code
Aug 08, 2024
Viaarxiv icon

Answering Subjective Induction Questions on Products by Summarizing Multi-sources Multi-viewpoints Knowledge

Add code
Sep 12, 2023
Viaarxiv icon

UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning

Add code
Jun 01, 2023
Viaarxiv icon

Leveraging Contaminated Datasets to Learn Clean-Data Distribution with Purified Generative Adversarial Networks

Add code
Feb 03, 2023
Viaarxiv icon

Efficient Document Retrieval by End-to-End Refining and Quantizing BERT Embedding with Contrastive Product Quantization

Add code
Oct 31, 2022
Viaarxiv icon

Refining BERT Embeddings for Document Hashing via Mutual Information Maximization

Add code
Sep 07, 2021
Figure 1 for Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
Figure 2 for Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
Figure 3 for Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
Figure 4 for Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
Viaarxiv icon

Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory

Add code
Jun 27, 2021
Figure 1 for Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
Figure 2 for Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
Figure 3 for Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
Figure 4 for Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
Viaarxiv icon

Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval

Add code
May 27, 2021
Figure 1 for Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval
Figure 2 for Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval
Figure 3 for Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval
Figure 4 for Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval
Viaarxiv icon

Unsupervised Hashing with Contrastive Information Bottleneck

Add code
May 19, 2021
Figure 1 for Unsupervised Hashing with Contrastive Information Bottleneck
Figure 2 for Unsupervised Hashing with Contrastive Information Bottleneck
Figure 3 for Unsupervised Hashing with Contrastive Information Bottleneck
Figure 4 for Unsupervised Hashing with Contrastive Information Bottleneck
Viaarxiv icon