default author photo

Mingli Song

Zhejiang University

38 Zheda Road

Hangzhou, 310058

China

  • Zhejiang University

SCHOLARLY PAPERS

3

DOWNLOADS

145

TOTAL CITATIONS

0

Scholarly Papers (3)

Actions:
Email selected abstracts
1.

An Accessible Communication System for Intelligent Assistance to the Hearing-Impaired

Number of pages: 34 Posted: 02 Oct 2024
Wei Feng, Zekang Liu, Liqing Gao, Zhijian Liu, Mingli Song, Longbiao Wang and Zhanhua Huang
Tianjin University, Tianjin University, Tianjin University, affiliation not provided to SSRN, Zhejiang University, Tianjin University and Tianjin University
Downloads 79 (816,709)

Abstract:

Loading...

Accessible communication system, First-person data record, Active/passive dialogue trigger, Cross-modal accessible communication, Light hearing aid head-ring, Conversational cross-modal sign language translation

2.

Pair-wise Layer Attention with Spatial Masking for Video Prediction

Downloads 49 (1,097,529)

Pair-wise Layer Attention with Spatial Masking for Video Prediction

Number of pages: 23 Posted: 16 Sep 2025
Ping Li, Chenhan Zhang, Zheng Yang, Xianghua Xu and Mingli Song
Hangzhou Dianzi University, Hangzhou Dianzi University, affiliation not provided to SSRN, Hangzhou Dianzi University and Zhejiang University
Downloads 24 (1,459,262)

Abstract:

Loading...

Video prediction, spatiotemporal modeling, pretraining, spatial masking, pair-wise layer attention

Pair-wise Layer Attention with Spatial Masking for Video Prediction

Number of pages: 23 Posted: 16 Sep 2025
Ping Li, Chenhan Zhang, Zheng Yang, Xianghua Xu and Mingli Song
Hangzhou Dianzi University, Hangzhou Dianzi University, affiliation not provided to SSRN, Hangzhou Dianzi University and Zhejiang University
Downloads 17 (1,548,841)

Abstract:

Loading...

Video prediction, spatiotemporal modeling, pretraining, spatial masking, pair-wise layer attention

Pair-wise Layer Attention with Spatial Masking for Video Prediction

Number of pages: 23 Posted: 28 Aug 2025
Ping Li, Chenhan Zhang, Zheng Yang, Xianghua Xu and Mingli Song
Hangzhou Dianzi University, Hangzhou Dianzi University, affiliation not provided to SSRN, Hangzhou Dianzi University and Zhejiang University
Downloads 8 (1,621,812)

Abstract:

Loading...

Video prediction, spatiotemporal modeling, pretraining, spatial masking, pair-wise layer attention

3.

Self-Improved Visual Preference Alignment by Iteratively Generating Holistic Winner

Number of pages: 28 Posted: 15 Jul 2025
Zunlei Feng, Kejia Chen, Jiawen Zhang, Jiazhen Yang and Mingli Song
Zhejiang University, Zhejiang University, Zhejiang University, Zhejiang University and Zhejiang University
Downloads 17 (1,481,165)

Abstract:

Loading...

Visual question answering, Preference Alignment, Hallucination