6 papers
CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization
Liangbin Huang, Xiaohua Liao, Chaoqun Cui +4
Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic condit…
From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization
Chaoqun Cui, Shijing Wang, Liangbin Huang +4
The rapid development of Large Language Models (LLMs) has significantly enhanced the general capabilities of machine translation. However, as application scenarios become more comp…
Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling
Chaoqun Cui, Shijing Wang, Liangbin Huang +4
Interlingual subtitling, which translates subtitles of visual media into a target language, is essential for entertainment localization but has not yet been explored in machine tra…
Agentic Reward Modeling: Verifying GUI Agent via Progressive Trajectory-Grounded Interaction
Chaoqun Cui, Jing Huang, Shijing Wang +3
Reinforcement learning with verifiable rewards (RLVR) provides a promising pathway for continuously advancing GUI agents, yet existing reward modeling paradigms face complementary…
VL4Gaze: Unleashing Vision-Language Models for Gaze Following
Shijing Wang, Chaoqun Cui, Yaping Huang +2
Human gaze provides essential cues for interpreting attention, intention, and social interaction in visual scenes, yet gaze understanding remains largely unexplored in current visi…
Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference Optimization
Chaoqun Cui, Liangbin Huang, Shijing Wang +4
Video dubbing aims to translate original speech in visual media programs from the source language to the target language, relying on neural machine translation and text-to-speech t…