RoiMAM: Region-of-Interest Medical Attention Model for Efficient Vision-Language Understanding

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Yang, Jiayan, Wu, Zhuoyu, Fang, Wenqi
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

RT-Focuser: A Real-Time Lightweight Model for Edge-side Image Deblurring
von: Wu, Zhuoyu, et al.
Veröffentlicht: (2025)

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest
von: Zhang, Shilong, et al.
Veröffentlicht: (2023)

EndoCaver: Handling Fog, Blur and Glare in Endoscopic Images via Joint Deblurring-Segmentation
von: Wu, Zhuoyu, et al.
Veröffentlicht: (2026)

PAM-UNet: Shifting Attention on Region of Interest in Medical Images
von: Das, Abhijit, et al.
Veröffentlicht: (2024)

RegionGPT: Towards Region Understanding Vision Language Model
von: Guo, Qiushan, et al.
Veröffentlicht: (2024)

EVLM: An Efficient Vision-Language Model for Visual Understanding
von: Chen, Kaibing, et al.
Veröffentlicht: (2024)

MAM-CLIP: Vision-Language Pretraining on Mammography Atlases for BI-RADS Classification
von: Gulluk, Halil Ibrahim, et al.
Veröffentlicht: (2026)

Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding
von: Jiang, Songtao, et al.
Veröffentlicht: (2025)

Privacy-Preserving Automated Rosacea Detection Based on Medically Inspired Region of Interest Selection
von: Yang, Chengyu, et al.
Veröffentlicht: (2025)

Semantically Grounded QFormer for Efficient Vision Language Understanding
von: Choraria, Moulik, et al.
Veröffentlicht: (2023)

PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model
von: Liang, Wenqi, et al.
Veröffentlicht: (2025)

FlexAttention for Efficient High-Resolution Vision-Language Models
von: Li, Junyan, et al.
Veröffentlicht: (2024)

SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning
von: Chen, Zewen, et al.
Veröffentlicht: (2024)

Toward Interactive Regional Understanding in Vision-Large Language Models
von: Lee, Jungbeom, et al.
Veröffentlicht: (2024)

MedROI: Codec-Agnostic Region of Interest-Centric Compression for Medical Images
von: Kim, Jiwon, et al.
Veröffentlicht: (2026)

Understanding Degradation with Vision Language Model
von: Lan, Guanzhou, et al.
Veröffentlicht: (2026)

NEARL-CLIP: Interacted Query Adaptation with Orthogonal Regularization for Medical Vision-Language Understanding
von: Peng, Zelin, et al.
Veröffentlicht: (2025)

Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment Tuning
von: Chang, Aofei, et al.
Veröffentlicht: (2025)

MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models
von: Meng, Fanqing, et al.
Veröffentlicht: (2024)

Region of Interest based Medical Image Compression
von: Srivastava, Utkarsh Prakash, et al.
Veröffentlicht: (2025)

Event-Priori-Based Vision-Language Model for Efficient Visual Understanding
von: Qin, Haotong, et al.
Veröffentlicht: (2025)

Detecting and Evaluating Medical Hallucinations in Large Vision Language Models
von: Chen, Jiawei, et al.
Veröffentlicht: (2024)

HiPrune: Hierarchical Attention for Efficient Token Pruning in Vision-Language Models
von: Liu, Jizhihui, et al.
Veröffentlicht: (2025)

Cross-Modal Attention Guided Unlearning in Vision-Language Models
von: Bhaila, Karuna, et al.
Veröffentlicht: (2025)

Towards Vision-Language-Garment Models for Web Knowledge Garment Understanding and Generation
von: Ackermann, Jan, et al.
Veröffentlicht: (2025)

Attention Guided Alignment in Efficient Vision-Language Models
von: Mahajan, Shweta, et al.
Veröffentlicht: (2025)

RegionMed-CLIP: A Region-Aware Multimodal Contrastive Learning Pre-trained Model for Medical Image Understanding
von: Fang, Tianchen, et al.
Veröffentlicht: (2025)

TCSAFormer: Efficient Vision Transformer with Token Compression and Sparse Attention for Medical Image Segmentation
von: Xia, Zunhui, et al.
Veröffentlicht: (2025)

VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge
von: Nath, Vishwesh, et al.
Veröffentlicht: (2024)

Particle-Based Shape Modeling for Arbitrary Regions-of-Interest
von: Xu, Hong, et al.
Veröffentlicht: (2023)

Remodeling Semantic Relationships in Vision-Language Fine-Tuning
von: Wu, Xiangyang, et al.
Veröffentlicht: (2025)

Optimizing Vision-Language Consistency via Cross-Layer Regional Attention Alignment
von: Wang, Yifan, et al.
Veröffentlicht: (2025)

MMCLIP: Cross-modal Attention Masked Modelling for Medical Language-Image Pre-Training
von: Wu, Biao, et al.
Veröffentlicht: (2024)

HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language Models
von: Jiang, Songtao, et al.
Veröffentlicht: (2025)

Segmenting and Understanding: Region-aware Semantic Attention for Fine-grained Image Quality Assessment with Large Language Models
von: Song, Chenyue, et al.
Veröffentlicht: (2025)

Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking
von: Chung, Sangyun, et al.
Veröffentlicht: (2024)

EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis
von: Chen, Jiayan, et al.
Veröffentlicht: (2025)

Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention
von: Zhang, Wenhu, et al.
Veröffentlicht: (2026)

SpatialBot: Precise Spatial Understanding with Vision Language Models
von: Cai, Wenxiao, et al.
Veröffentlicht: (2024)

MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding
von: Chopra, Shivang, et al.
Veröffentlicht: (2025)

if (filemtime($filename) + $maxlifetime < time()) { unlink($filename); $count++; } } return $count; } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ protected function saveSession($sessId, $data): bool { $sessFile = $this->path . '/sess_' . $sessId; if ($handle = fopen($sessFile, 'w')) { $return = false; // Lock the file for exclusive access to avoid issues with multiple // processes writing session simultaneously: if (flock($handle, LOCK_EX)) { $return = fwrite($handle, $data); // Make sure that there's no trailing data by truncating the file to // the correct length: ftruncate($handle, strlen($data)); fflush($handle); flock($handle, LOCK_UN); } fclose($handle); if ($return !== false) { return true; } } // If we got this far, something went wrong with the file output... // It is tempting to throw an exception here, but this code is called // outside of the context of exception handling, so all we can do is // echo a message.

// Anecdotal testing Today and Yesterday seems to indicate destroy() // is called by the garbage collector and everything is good. // Something to keep in mind though. return 0; } /** * Write function that is called when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ public function write($sessId, $data): bool { if ($this->writesDisabled) { return true; } return $this->saveSession($sessId, $data); } /** * A function that is called internally when session data is to be saved. * * @param string $sessId The current session ID * @param string $data The session data to write * * @return bool */ abstract protected function saveSession($sessId, $data): bool; }

* * @return void */ public function writeClose() { // The assumption is that we're using PHP's ext/session. // session_write_close() will actually overwrite $_SESSION with an // empty array on completion -- which leads to a mismatch between what // is in the storage object and $_SESSION. To get around this, we // temporarily reset $_SESSION to an array, and then re-link it to // the storage object. // // Additionally, while you _can_ write to $_SESSION following a // session_write_close() operation, no changes made to it will be // flushed to the session handler. As such, we now mark the storage // object isImmutable. $storage = $this->getStorage(); if (! $storage->isImmutable()) { $_SESSION = $storage->toArray(true); session_write_close(); $storage->fromArray($_SESSION); $storage->markImmutable(); } } /** * Attempt to set the session name * * If the session has already been started, or if the name provided fails * validation, an exception will be raised. * * @param string $name * @return SessionManager * @throws Exception\InvalidArgumentException */ public function setName($name) { if ($this->sessionExists()) { throw new Exception\InvalidArgumentException( 'Cannot set session name after a session has already started'

Environment & details:

GET Data empty

POST Data empty

Files empty

Key	Value
language	"de"
ui	"standard"
VUFIND_SESSION	"d7c0849960c2ba0e10052915b5b7e4a4"

Session

Key	Value
__Laminas	array:2 [`"_REQUEST_ACCESS_TIME" => 1790990759.2815 "_VALID" => array:1 [ "Laminas\Session\Validator\Id" => "d7c0849960c2ba0e10052915b5b7e4a4" ]`]
SessionState	Laminas\Stdlib\ArrayObject {#938}
FlashMessenger	Laminas\Stdlib\ArrayObject {#1433}
SessionHelper	Laminas\Stdlib\ArrayObject {#1759}

Server/Request Data

Key	Value
REDIRECT_VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
REDIRECT_HTTPS	"on"
REDIRECT_SSL_TLS_SNI	"info.umar.mx"
REDIRECT_STATUS	"200"
VUFIND_LOCAL_DIR	"/usr/local/vufind/local"
HTTPS	"on"
SSL_TLS_SNI	"info.umar.mx"
HTTP_ACCEPT	"/"
HTTP_USER_AGENT	"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)"
HTTP_COOKIE	"language=de; ui=standard; VUFIND_SESSION=d7c0849960c2ba0e10052915b5b7e4a4"
HTTP_ACCEPT_ENCODING	"gzip, br, zstd, deflate"
HTTP_HOST	"info.umar.mx"
PATH	"/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/snap/bin"
SERVER_SIGNATURE	"<address>Apache/2.4.66 (Ubuntu) Server at info.umar.mx Port 443</address>\n"
SERVER_SOFTWARE	"Apache/2.4.66 (Ubuntu)"
SERVER_NAME	"info.umar.mx"
SERVER_ADDR	"200.23.222.19"
SERVER_PORT	"443"
REMOTE_ADDR	"216.73.217.142"
DOCUMENT_ROOT	"/usr/local/vufind/public"
REQUEST_SCHEME	"https"
CONTEXT_PREFIX	""
CONTEXT_DOCUMENT_ROOT	"/usr/local/vufind/public"
SERVER_ADMIN	"admin@localhost"
SCRIPT_FILENAME	"/usr/local/vufind/public/index.php"
REMOTE_PORT	"42613"
REDIRECT_URL	""" /Record/\n arxiv_https___arxiv_org_abs_2605_15561/Similar """
GATEWAY_INTERFACE	"CGI/1.1"
SERVER_PROTOCOL	"HTTP/1.1"
REQUEST_METHOD	"GET"
QUERY_STRING	""
REQUEST_URI	"/Record/%0Aarxiv_https___arxiv_org_abs_2605_15561/Similar"
SCRIPT_NAME	"/index.php"
PHP_SELF	"/index.php"
REQUEST_TIME_FLOAT	1790990759.2772
REQUEST_TIME	1790990759

Environment Variables empty

Registered Handlers

0. Whoops\Handler\PrettyPageHandler