3 papers
eess.AS2025
Effective Modeling of Critical Contextual Information for TDNN-based Speaker Verification
Shilong Weng, Liu Yang, Ji Mao
Today, Time Delay Neural Network (TDNN) has become the mainstream architecture for speaker verification task, in which the ECAPA-TDNN is one of the state-of-the-art models. The cur…
cs.CV2024
Training-free Video Temporal Grounding using Large-scale Pre-trained Models
Minghang Zheng, Xinhao Cai, Qingchao Chen +2
Video temporal grounding aims to identify video segments within untrimmed videos that are most relevant to a given natural language query. Existing video temporal localization mode…
cs.CV2024
Comment-aided Video-Language Alignment via Contrastive Pre-training for Short-form Video Humor Detection
Yang Liu, Tongfei Shen, Dong Zhang +3
The growing importance of multi-modal humor detection within affective computing correlates with the expanding influence of short-form video sharing on social media platforms. In t…