2024

Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting
Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting

Jianxiang Zhou, Erdong Liu, Wei Chen, Siru Zhong, Yuxuan Liang

Under review. 2024

Introduce STGormer, a Spatio-Temporal Graph Transformer that integrates traffic data attributes and structures with a mixture-of experts module to capture spatio-temporal heterogeneity, achieving state-of-the-art performance in traffic forecasting

Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting
Navigating Spatio-Temporal Heterogeneity: A Graph Transformer Approach for Traffic Forecasting

Jianxiang Zhou, Erdong Liu, Wei Chen, Siru Zhong, Yuxuan Liang

Under review. 2024

Introduce STGormer, a Spatio-Temporal Graph Transformer that integrates traffic data attributes and structures with a mixture-of experts module to capture spatio-temporal heterogeneity, achieving state-of-the-art performance in traffic forecasting

UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation
UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation

Siru Zhong, Xixuan Hao, Yibo Yan, Ying Zhang, Yangqiu Song, Yuxuan Liang

ACM International Conference on Multimedia (ACM MM) 2024 Poster

Introduced UrbanCross, a cross-domain satellite image-text retrieval framework that leverages multimodal enhancements and adaptive domain adaptation techniques to bridge diverse urban landscapes, achieving up to a 15% improvement in retrieval performance.

UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation
UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation

Siru Zhong, Xixuan Hao, Yibo Yan, Ying Zhang, Yangqiu Song, Yuxuan Liang

ACM International Conference on Multimedia (ACM MM) 2024 Poster

Introduced UrbanCross, a cross-domain satellite image-text retrieval framework that leverages multimodal enhancements and adaptive domain adaptation techniques to bridge diverse urban landscapes, achieving up to a 15% improvement in retrieval performance.

Spatio-Temporal Field Neural Networks for Air Quality Inference
Spatio-Temporal Field Neural Networks for Air Quality Inference

Yutong Feng, Qiongyan Wang, Yutong Xia, Junlin Huang, Siru Zhong, Kun Wang, Shifen Cheng, Yuxuan Liang

The International Joint Conference on Artificial Intelligence (IJCAI) 2024

Present the Spatio-Temporal Field Neural Network and Pyramidal Inference framework, which integrate field and graph perspectives to achieve state-of-the-art nationwide air quality inference in Mainland China.

Spatio-Temporal Field Neural Networks for Air Quality Inference
Spatio-Temporal Field Neural Networks for Air Quality Inference

Yutong Feng, Qiongyan Wang, Yutong Xia, Junlin Huang, Siru Zhong, Kun Wang, Shifen Cheng, Yuxuan Liang

The International Joint Conference on Artificial Intelligence (IJCAI) 2024

Present the Spatio-Temporal Field Neural Network and Pyramidal Inference framework, which integrate field and graph perspectives to achieve state-of-the-art nationwide air quality inference in Mainland China.

Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach
Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach

Huaiwu Zhang, Yutong Xia, Siru Zhong, Kun Wang, Zekun Tong, Qingsong Wen, Roger Zimmermann, Yuxuan Liang

The International Joint Conference on Artificial Intelligence (IJCAI) 2024

Introduce DeepPA, a deep-learning framework and the SINPA dataset for accurately predicting real-time parking availability across Singapore, outperforming existing models and supporting urban planning through a deployed web platform.

Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach
Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach

Huaiwu Zhang, Yutong Xia, Siru Zhong, Kun Wang, Zekun Tong, Qingsong Wen, Roger Zimmermann, Yuxuan Liang

The International Joint Conference on Artificial Intelligence (IJCAI) 2024

Introduce DeepPA, a deep-learning framework and the SINPA dataset for accurately predicting real-time parking availability across Singapore, outperforming existing models and supporting urban planning through a deployed web platform.

UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Model for Urban Indicator Prediction
UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Model for Urban Indicator Prediction

Xixuan Hao, Wei Chen, Yibo Yan, Siru Zhong, Kun Wang, Qingsong Wen, Yuxuan Liang

Under review. 2024

Present UrbanVLP, a novel vision-language pretraining framework that integrates both macro and micro-level urban data and enhances interpretability through automatic text generation, achieving superior performance in urban region profiling.

UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Model for Urban Indicator Prediction
UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Model for Urban Indicator Prediction

Xixuan Hao, Wei Chen, Yibo Yan, Siru Zhong, Kun Wang, Qingsong Wen, Yuxuan Liang

Under review. 2024

Present UrbanVLP, a novel vision-language pretraining framework that integrates both macro and micro-level urban data and enhances interpretability through automatic text generation, achieving superior performance in urban region profiling.

UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web
UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web

Yibo Yan, Haomin Wen, Siru Zhong, Wei Chen, Haodong Chen, Qingsong Wen, Roger Zimmermann, Yuxuan Liang

The International World Wide Web Conference (WWW) 2024 Oral

Introduce UrbanCLIP, the first large language model–enhanced framework that integrates textual descriptions with satellite imagery through contrastive language-image pretraining, significantly improving urban region profiling performance across major cities.

UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web
UrbanCLIP: Learning Text-enhanced Urban Region Profiling with Contrastive Language-Image Pretraining from the Web

Yibo Yan, Haomin Wen, Siru Zhong, Wei Chen, Haodong Chen, Qingsong Wen, Roger Zimmermann, Yuxuan Liang

The International World Wide Web Conference (WWW) 2024 Oral

Introduce UrbanCLIP, the first large language model–enhanced framework that integrates textual descriptions with satellite imagery through contrastive language-image pretraining, significantly improving urban region profiling performance across major cities.