23 papers
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos
Yue Feng, Jingjing Li, Qijia Lu +9
The rapid advancement of AI-driven video generation has transformed content creation, while simultaneously increasing the risk of misinformation through localized manipulations in…
InstructSAM: Segment Any Instance with Any Instructions
Yuqian Yuan, Wentong Li, Zhaocheng Li +6
In this paper, we introduce InstructSAM, a unified and streamlined framework designed for multi-instance segmentation under arbitrary instructions. We formulates instruction-driven…
Weighted Reverse Convolution for Feature Upsampling
Wentong Li, Zhiyuan Qi, Zichen Zhao +2
Pre-trained vision foundation models (VFMs) provide strong semantic representations, yet their patch-level features are inherently coarse, limiting their effectiveness on tasks req…
GA2-CLIP: Generic Attribute Anchor for Efficient Prompt Tuningin Video-Language Models
Bin Wang, Ruotong Hu, Wentong Li +5
Visual and textual soft prompt tuning can effectively improve the adaptability of Vision-Language Models (VLMs) in downstream tasks. However, fine-tuning on video tasks impairs the…
LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation
Yuqian Yuan, Wenqiao Zhang, Juekai Lin +7
Large Multimodal Models (LMMs) have achieved remarkable progress in general-purpose vision--language understanding, yet they remain limited in tasks requiring precise object-level…
VisionTrim: Unified Vision Token Compression for Training-Free MLLM Acceleration
Hanxun Yu, Wentong Li, Xuan Qu +3
Multimodal large language models (MLLMs) suffer from high computational costs due to excessive visual tokens, particularly in high-resolution and video-based scenarios. Existing to…