相关论文: SegRAG: Training-Free Retrieval-Augmented Semantic…

Foundational models such as the Segment Anything Model (SAM) are gaining traction in medical imaging segmentation, supporting multiple downstream tasks. However, such models are supervised in nature, still relying on large annotated…

Large Vision-Language Models (VLMs) are increasingly being regarded as foundation models that can be instructed to solve diverse tasks by prompting, without task-specific training. We examine the seemingly obvious question: how to…

We present HySemRAG, a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG) to automate large-scale literature synthesis and identify methodological research gaps. The system addresses…

Different from Object Detection, Visual Grounding deals with detecting a bounding box for each text-image pair. This one box for each text-image data provides sparse supervision signals. Although previous works achieve impressive results,…

The Segment Anything Model (SAM), developed by Meta AI Research, represents a significant breakthrough in computer vision, offering a robust framework for image and video segmentation. This survey provides a comprehensive exploration of the…

Accurate segmentation of tissues and instruments in surgical scenes is annotation-intensive due to irregular shapes, thin structures, specularities, and frequent occlusions. While SAM models support point, box, and mask prompts, points are…

The fragmentation between high-level task semantics and low-level geometric features remains a persistent challenge in robotic manipulation. While vision-language models (VLMs) have shown promise in generating affordance-aware visual…

Segment Anything Model (SAM) represents a large-scale segmentation model that enables powerful zero-shot capabilities with flexible prompts. While SAM can segment any object in zero-shot, it requires user-provided prompts for each target…

Vision-Language Models (VLMs) have shown impressive performance in vision tasks, but adapting them to new domains often requires expensive fine-tuning. Prompt tuning techniques, including textual, visual, and multimodal prompting, offer…

Highlighting particularly relevant regions of an image can improve the performance of vision-language models (VLMs) on various vision-language (VL) tasks by guiding the model to attend more closely to these regions of interest. For example,…

Large language models (LLMs) have demonstrated increasingly sophisticated performance in medical and other fields of knowledge. Traditional methods of creating specialist LLMs require extensive fine-tuning and training of models on large…

We present LSeg, a novel model for language-driven semantic image segmentation. LSeg uses a text encoder to compute embeddings of descriptive input labels (e.g., "grass" or "building") together with a transformer-based image encoder that…

Spatio-Temporal Video Grounding (STVG) aims to localize target objects in videos based on natural language descriptions. Despite recent advances in Multimodal Large Language Models, a significant gap remains between current models and…

In this work we study Weakly Supervised Spatio-Temporal Video Grounding (WSTVG), a challenging task of localizing subjects spatio-temporally in videos using only textual queries and no bounding box supervision. Inspired by recent advances…

Deep learning based methods often suffer from performance degradation caused by domain shift. In recent years, many sophisticated network structures have been designed to tackle this problem. However, the advent of large model trained on…

In geographical image segmentation, performance is often constrained by the limited availability of training data and a lack of generalizability, particularly for segmenting mobility infrastructure such as roads, sidewalks, and crosswalks.…

The Segment Anything Model (SAM) has recently emerged as a groundbreaking foundation model for prompt-driven image segmentation tasks. However, both the original SAM and its medical variants require slice-by-slice manual prompting of target…

Open-vocabulary 3D scene understanding presents a significant challenge in the field. Recent works have sought to transfer knowledge embedded in vision-language models from 2D to 3D domains. However, these approaches often require prior…

Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneous information to the…

Spatial correspondence can be represented by pairs of segmented regions, such that the image registration networks aim to segment corresponding regions rather than predicting displacement fields or transformation parameters. In this work,…