2 papers
cs.CV2024
Debiased Orthogonal Boundary-Driven Efficient Noise Mitigation
Hao Li, Jiayang Gu, Jingkuan Song +2
Mitigating the detrimental effects of noisy labels on the training process has become increasingly critical, as obtaining entirely clean or human-annotated samples for large-scale…
cs.CV2023
Incorporating granularity bias as the margin into contrastive loss for video captioning
Jiayang Gu, Fengming Yao
Video captioning models easily suffer from long-tail distribution of phrases, which makes captioning models prone to generate vague sentences instead of accurate ones. However, exi…