Related papers: COMPASS: A Formal Framework and Aggregate Dataset …

Segment anything model (SAM) has demonstrated excellent generalizability in common vision scenarios, yet falling short of the ability to understand specialized data. Recently, several methods have combined parameter-efficient techniques…

Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…

Recently, foundational models such as CLIP and SAM have shown promising performance for the task of Zero-Shot Anomaly Segmentation (ZSAS). However, either CLIP-based or SAM-based ZSAS methods still suffer from non-negligible key drawbacks:…

Purpose: We study the relationship between surgical gestures and motion primitives in dry-lab surgical exercises towards a deeper understanding of surgical activity at fine-grained levels and interpretable feedback in skill assessment.…

Medical image segmentation typically demands extensive dense annotations for model training, which is both time-consuming and skill-intensive. To mitigate this burden, exemplar-based medical image segmentation methods have been introduced…

Referring Video Object Segmentation (RefVOS) seeks to segment target objects in videos guided by natural language descriptions, demanding both temporal reasoning and fine-grained visual comprehension. Existing sampling strategies for…

Recent segmentation methods, which adopt large-scale data training and transformer architecture, aim to create one foundation model that can perform multiple tasks. However, most of these methods rely on heavy encoder and decoder…

Medical image segmentation often faces the challenge of prohibitively expensive annotation costs. While few-shot learning offers a promising solution to alleviate this burden, conventional approaches still rely heavily on pre-training with…

We present ASAP, a new framework for detecting and grounding multi-modal media manipulation (DGM4).Upon thorough examination, we observe that accurate fine-grained cross-modal semantic alignment between the image and text is vital for…

In a setting where segmentation models have to be built for multiple datasets, each with its own corresponding label set, a straightforward way is to learn one model for every dataset and its labels. Alternatively, multi-task architectures…

Surgical AI often involves multiple tasks within a single procedure, like phase recognition or assessing the Critical View of Safety in laparoscopic cholecystectomy. Traditional models, built for one task at a time, lack flexibility,…

Advances in surgical video analysis are transforming operating rooms into intelligent, data-driven environments. Computer-assisted systems support full surgical workflow, from preoperative planning to intraoperative guidance and…

In the fast-growing field of Remote Sensing (RS) image analysis, the gap between massive unlabeled datasets and the ability to fully utilize these datasets for advanced RS analytics presents a significant challenge. To fill the gap, our…

Foundation models have transformed vision and language by learning general-purpose representations from large-scale unlabeled data, yet 3D medical imaging lacks analogous approaches. Existing self-supervised methods rely on low-level…

Robot-assisted surgeries rely on accurate and real-time scene understanding to safely guide surgical instruments. However, segmentation models trained on static datasets face key limitations when deployed in these dynamic and evolving…

Producing manual, pixel-accurate, image segmentation labels is tedious and time-consuming. This is often a rate-limiting factor when large amounts of labeled images are required, such as for training deep convolutional networks for…

Clinical diagnosis of the pediatric musculoskeletal system relies on the analysis of medical imaging examinations. In the medical image processing pipeline, semantic segmentation using deep learning algorithms enables an automatic…

Large language models (LLMs) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performance due to negative cross-lingual interference. To address this, we introduce COMPASS…

Robot-assisted surgery (RAS) has become a critical paradigm in modern surgery, promoting patient recovery and reducing the burden on surgeons through minimally invasive approaches. To fully realize its potential, however, a precise…

Large Language Models (LLMs) have achieved remarkable performance across a wide range of Natural Language Processing (NLP) tasks. However, in long-context scenarios, they face two challenges: high computational cost and information…