8 papers · 1 filter
HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video Understanding
Leon Mayer, Lucas Luttner, Patrick Godau +42
Recent advances in Vision-Language Models (VLMs) have led to rapid progress in video understanding across a wide range of benchmark tasks. However, existing evaluations largely foc…
Limitations of Synthetic Data Generation in Specialized Data-Scarce Domains
Edward Zhang, Marcel Hussing, Tanay Tandon +12
Advances in diffusion-based generative models have motivated the use of synthetic image generation to alleviate data scarcity in vision tasks. While this strategy has shown promise…
Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs
Guiqiu Liao, Matjaz Jogan, Daniel A. Hashimoto
Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leading to costly inference and lim…
Active Learning for Efficient Annotation of Surgical Videos with Weak Supervision
Manasa Dendukuri, Matjaz Jogan, Daniel A. Hashimoto +1
Precise spatial-temporal annotation of laparoscopic videos is time-consuming and requires expert knowledge. We propose a human-in-the-loop knowledge acquisition framework that comb…
DenseTRF: Texture-Aware Unsupervised Representation Adaptation for Surgical Scene Dense Prediction
Guiqiu Liao, Matjaž Jogan, Daniel A. Hashimoto
Dense prediction tasks in surgical computer vision, such as segmentation and surgical zone prediction, can provide valuable guidance for laparoscopic and robotic surgery. However,…
Future Slot Prediction for Unsupervised Object Discovery in Surgical Video
Guiqiu Liao, Matjaz Jogan, Marcel Hussing +3
Object-centric slot attention is an emerging paradigm for unsupervised learning of structured, interpretable object-centric representations (slots). This enables effective reasonin…
FORLA: Federated Object-centric Representation Learning with Slot Attention
Guiqiu Liao, Matjaz Jogan, Eric Eaton +1
Learning efficient visual representations across heterogeneous unlabeled datasets remains a central challenge in federated learning. Effective federated representations require fea…
Disentangling spatio-temporal knowledge for weakly supervised object detection and segmentation in surgical video
Guiqiu Liao, Matjaz Jogan, Sai Koushik +2
Weakly supervised video object segmentation (WSVOS) enables the identification of segmentation maps without requiring an extensive training dataset of object masks, relying instead…