6 papers
FlowDance: Music-Driven Dance Video Generation with Parallel Pose and RGB Streams
Genying Li, Boda Lin, Jiachen Li +5
Music-driven dance video synthesis aims to animate a reference person according to a given music clip. The task is challenging because it requires a model to jointly learn music-to…
KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding
Boda Lin, Yongjie Zhu, Xiaocheng Gong +2
Despite recent advancements, video captioning models still face significant limitations in accurately describing fine-grained motion details and suffer from severe hallucination is…
Analytic Score Optimization for Multi Dimension Video Quality Assessment
Boda Lin, Yongjie Zhu, Wenyu Qin +2
Video Quality Assessment (VQA) is evolving beyond single-number mean opinion score toward richer, multi-faceted evaluations of video content. In this paper, we present a large-scal…
TOP:A New Target-Audience Oriented Content Paraphrase Task
Boda Lin, Jiaxin Shi, Haolong Yan +3
Recommendation systems usually recommend the existing contents to different users. However, in comparison to static recommendation methods, a recommendation logic that dynamically…
ChatGPT is a Potential Zero-Shot Dependency Parser
Boda Lin, Xinyi Zhou, Binghao Tang +2
Pre-trained language models have been widely used in dependency parsing task and have achieved significant improvements in parser performance. However, it remains an understudied q…
Schema-Free Dependency Parsing via Sequence Generation
Boda Lin, Zijun Yao, Jiaxin Shi +6
Dependency parsing aims to extract syntactic dependency structure or semantic dependency structure for sentences. Existing methods suffer the drawbacks of lacking universality or h…