Tongwei Ren

SPLG-Mamba: Structure-Preserving Local-Global Mamba Network for Salient Object Detection in Optical Remote Sensing Images

Yi Xu, Ruichao Hou, Tongwei Ren, Gangshan Wu

Salient object detection in optical remote sensing images (ORSI-SOD) requires dense predictions that preserve object completeness and structural continuity under complex backgrounds, scale variation, and irregular object shapes. Existing methods often localize salient regions, but their predictions may still suffer from structural …

Enhancing Localized Reasoning for Long Video Understanding via Efficient Segment-to-Video Supervision

Beibei Zhang, Chao Xu, Jun Lan, Zongyi Li et autres

Though Multimodal Large Language Models (MLLMs) have shown impressive potential in video understanding, long video understanding (LVU) remains challenging since distracting noise in complex and lengthy contexts can obscure localized details, misleading MLLMs to produce incorrect answers. Recent works mitigate these issues …

S$^3$AM: A Single-Stream SAM with Reliability-Calibrated Frequency Adapter for Multi-modal Salient Object Detection

Ruichao Hou, Boyue Xu, Tongwei Ren, Dongming Zhou et autres

Vision foundation models have recently advanced multi-modal salient object detection (MSOD) through parameter-efficient tuning and prompt learning. However, existing Segment Anything Model (SAM)-adapted MSOD methods often rely on dual-stream encoders or auxiliary prompt generators, leading to redundant computation. Although a single-stream alternative …

Lightweight Underwater Sonar Object Detection via RGB-Guided Heterogeneous Distillation

Qianqian Qiao, Jia Liu, Feng Liu, Chengpeng Hao et autres

Underwater object detection is a fundamental task in underwater sensing and is generally approached using either optical or sonar sensors. Although optical imaging provides rich semantic information, it is highly susceptible to water turbidity and illumination variations. By contrast, sonar imaging can …

cn (code pays fourni par la source)

Segmentation-guided transformer network for subtle visual relationship detection

Fan Yu, Cao Hanxi, Ruichao Hou, Tongwei Ren

cn (code pays fourni par la source)

Real-time visualization of infection dynamics using a bioluminescent reporter-expressing recombinant Getah virus

Tongwei Ren, Guowei Wang, Peijie Li, Zhen Zhong et autres

cn (code pays fourni par la source)

Thermal crowd counting by distilling multi-modal knowledge

Xiaoxu Liu, Yi Shi, Ruichao Hou, Tongwei Ren

cn (code pays fourni par la source)

Reverberation Suppression Algorithm for Obstacle Avoidance Sonar Based on Sparse Decomposition

Xiaoyu Ma, Jinyan Liu, Chengpeng Hao, Feng Liu et autres

cn (code pays fourni par la source)

Defining the impact of Getah virus envelope protein glycosylation site mutations on viral replication, host adaptation, virulence, and immune evasion

Tongwei Ren, Muyang Liu, Peijie Li, Liping Zhang et autres

The N-linked glycosylation of alphavirus envelope proteins plays critical roles in glycoprotein folding, host-receptor interactions, immune evasion, and pathogenicity. Getah virus (GETV) has two putative N-linked glycosylation sites (N-200 and N-262) in the E2 and one (N-141) in E1. We generated seven …

cn (code pays fourni par la source)

Improving Region Representation Learning from Urban Imagery with Noisy Long-Caption Supervision

Yimei Zhang, Guojiang Shen, Kaili Ning, Tongwei Ren et autres

Region representation learning plays a pivotal role in urban computing by extracting meaningful features from unlabeled urban data. Analogous to how perceived facial age reflects an individual's health, the visual appearance of a city serves as its "portrait", encapsulating latent socio-economic and …

cn (code pays fourni par la source)

Panoptic Scene Graph Grounded Training‐Free Image Editing With Mutually Exclusive Attention Manipulation

Yunqing He, Ruichao Hou, Jia Bei, Tongwei Ren

ABSTRACT Prevailing image editing methods heavily rely on user‐provided bounding boxes or pixel‐level masks to ensure visual consistency in nonedited regions. Although some attention‐based approaches eliminate the need for manually annotated input, they often unexpectedly alter nontarget areas due to semantic leakage …

cn (code pays fourni par la source)

Coarse-to-Fine Multimodal Information Selection for Video Speaking Style Recognition with Large Language Models

Beibei Zhang, Yanan Lu, Lin Fen, Tongwei Ren

Video Speaking Style Recognition (VSSR) aims to classify conversation videos into different types, significantly facilitating human interaction understanding.Recent approaches explore the potential of large language models (LLM) in VSSR with a training-free process.However, directly integrating all multimodal data yields suboptimal results, since …

cn (code pays fourni par la source)