13 papers
SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding
Yuqing Feng, Jiawei Ma, Kevin Qinghong Lin +6
Surgical procedures unfold as structured and recurring clinical events, whose real-time understanding via intraoperative surgical videos is critical for intraoperative decision-mak…
DSeq-JEPA: Discriminative Sequential Joint-Embedding Predictive Architecture
Xiangteng He, Shunsuke Sakai, Shivam Chandhok +5
Recent advances in self-supervised visual representation learning have demonstrated the effectiveness of predictive latent-space objectives for learning transferable features. In p…
Improving Model Representation and Reducing KV Cache via Skip Connections with First Value Heads
Zhoutong Wu, Yuan Zhang, Yiming Dong +4
Transformer models have driven breakthroughs across various language tasks by their strong capability to learn rich contextual representations. Scaling them to improve representati…
SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video Understanding
Zhen Chen, Xingjian Luo, Kun Yuan +6
Surgical video understanding is crucial for facilitating Computer-Assisted Surgery (CAS) systems. Despite significant progress in existing studies, two major limitations persist, i…
Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models
Jianshu Zeng, Yuxuan Liu, Yutong Feng +6
Video relighting is a challenging yet valuable task, aiming to replace the background in videos while correspondingly adjusting the lighting in the foreground with harmonious blend…
Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition
Britty Baby, Vinkle Srivastav, Pooja P. Jain +3
The Critical View of Safety (CVS) is crucial for safe laparoscopic cholecystectomy, yet assessing CVS criteria remains a complex and challenging task, even for experts. Traditional…