5 papers
SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation
Jiadong Pan, Liang Li, Hongcheng Gao +3
Diffusion models (DMs) have demonstrated exceptional performance in text-to-image tasks, leading to their widespread use. With the introduction of classifier-free guidance (CFG), t…
Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
Hongcheng Gao, Jiashu Qu, Jingyi Tang +6
The hallucination of large multimodal models (LMMs), providing responses that appear correct but are actually incorrect, limits their reliability and applicability. This paper aims…
Query-centric Audio-Visual Cognition Network for Moment Retrieval, Segmentation and Step-Captioning
Yunbin Tu, Liang Li, Li Su +1
Video has emerged as a favored multimedia format on the internet. To better gain video contents, a new topic HIREST is presented, including video retrieval, moment retrieval, momen…
Distractors-Immune Representation Learning with Cross-modal Contrastive Regularization for Change Captioning
Yunbin Tu, Liang Li, Li Su +2
Change captioning aims to succinctly describe the semantic change between a pair of similar images, while being immune to distractors (illumination and viewpoint changes). Under th…
Context-aware Difference Distilling for Multi-change Captioning
Yunbin Tu, Liang Li, Li Su +3
Multi-change captioning aims to describe complex and coupled changes within an image pair in natural language. Compared with single-change captioning, this task requires the model…