楊 沢坤

Multi-Modal Video Summarization Based on Two-Stage Fusion of Audio, Visual, and Recognized Text Information. 

APSIPA 1-6 2024年  

Multi-modal humor segment prediction in video 

Multimedia Systems 29(4) 2389-2398 2023年8月  

ED-CEC: Improving Rare word Recognition Using ASR Postprocessing Based on Error Detection and Context-Aware Error Correction 

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 2023年  

A comparative study of language transformers for video question answering 

Neurocomputing 445 121-133 2021年7月20日  

The laughing machine: Predicting humor in video 

Proceedings - 2021 IEEE Winter Conference on Applications of Computer Vision, WACV 2021 2072-2081 2021年1月  

Review on image-stitching techniques 

Multimedia Systems 26(4) 413-430 2020年8月1日  

BERT representations for video question answering 

Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020 1545-1554 2020年3月  

Seam elimination based on Curvelet for image stitching 

Soft Computing 23(13) 5065-5080 2019年7月1日  

Leaf Recognition Based on DPCNN and BOW 

Neural Processing Letters 47(1) 99-115 2018年2月1日