2 citations · 7 across the 6 of their papers we have counts for
6 papers
ConKI: Contrastive Knowledge Injection for Multimodal Sentiment Analysis
Yakun Yu, Mingjun Zhao, Shi-ang Qi +6
Multimodal Sentiment Analysis leverages multimodal signals to detect the sentiment of a speaker. Previous approaches concentrate on performing multimodal fusion and representation…
A Sequence-to-Sequence&Set Model for Text-to-Table Generation
Tong Li, Zhihao Wang, Liangying Shao +3
Recently, the text-to-table generation task has attracted increasing attention due to its wide applications. In this aspect, the dominant model formalizes this task as a sequence-t…
Search-Map-Search: A Frame Selection Paradigm for Action Recognition
Mingjun Zhao, Yakun Yu, Xiaoli Wang +2
Despite the success of deep learning in video understanding tasks, processing every frame in a video is computationally expensive and often unnecessary in real-time applications. F…
LA3: Efficient Label-Aware AutoAugment
Mingjun Zhao, Shan Lu, Zixuan Wang +2
Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training. Most existing wo…
Verdi: Quality Estimation and Error Detection for Bilingual Corpora
Mingjun Zhao, Haijiang Wu, Di Niu +2
Translation Quality Estimation is critical to reducing post-editing efforts in machine translation and to cross-lingual corpus cleaning. As a research problem, quality estimation (…
Reinforced Curriculum Learning on Pre-trained Neural Machine Translation Models
Mingjun Zhao, Haijiang Wu, Di Niu +1
The competitive performance of neural machine translation (NMT) critically relies on large amounts of training data. However, acquiring high-quality translation pairs requires expe…