3 accepted papers
Speech-driven talking head generation is a critical yet challenging task with applications in augmented reality and virtual human modeling. While recent approaches using autoregressive and diffusion-based models have achieved notable progress, they often suffer from modality inconsistencies, particu
There is a growing demand of automatically synthesizing co-speech gestures for virtual characters. However, it remains a challenge due to the complex relationship between input speeches and target gestures. Most existing works focus on predicting the next gesture that fits the data best, however, su…
Sequence labeling serves as the most commonly used scheme for Chinese named entity recognition(NER). However, traditional sequence labeling methods classify tokens within an entity into different classes according to their positions. As a result, different tokens in the same entity may be learned wi…