11 papers
Beyond Unfolding: 60x Faster One-Stage Unmixing for Closely-Spaced Infrared Small Targets
Ximeng Zhai, Zheng Wang, Yaohong Chen +3
Due to the optical diffraction limit and long imaging distances, Closely-Spaced Infrared Small Targets (CSIST) typically exhibit energy overlap, manifesting as indistinguishable bl…
Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing
Chenxu Peng, Chongtian zhou, Dicheng Liu +5
Fusing standard RGB frames with asynchronous event streams has emerged as a definitive paradigm for robust perception in degraded environments. Although unified backbones have rece…
RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extraction
Chenxu Peng, Chenxu Wang, Yimian Dai +3
Accurate road segmentation from aerial imagery is fundamental to many geospatial applications. However, existing datasets often suffer from limited scene diversity, low semantic gr…
WOW-Seg: A Word-free Open World Segmentation Model
Danyang Li, Tianhao Wu, Bin Li +5
Open world image segmentation aims to achieve precise segmentation and semantic understanding of targets within images by addressing the infinitely open set of object categories en…
NAIPv2: Debiased Pairwise Learning for Efficient Paper Quality Estimation
Penghai Zhao, Jinyu Tian, Qinghua Xing +5
The ability to estimate the quality of scientific papers is central to how both humans and AI systems will advance scientific knowledge in the future. However, existing LLM-based e…
Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Framework
Wenhao Tang, Heng Fang, Ge Wu +2
Computational pathology (CPath) digitizes pathology slides into whole slide images (WSIs), enabling analysis for critical healthcare tasks such as cancer diagnosis and prognosis. H…
Visual Instruction Pretraining for Domain-Specific Foundation Models
Yuxuan Li, Yicheng Zhang, Wenhao Tang +4
Modern computer vision is converging on a closed loop in which perception, reasoning and generation mutually reinforce each other. However, this loop remains incomplete: the top-do…
DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection
Kang Ni, Minrui Zou, Yuxuan Li +4
One of the primary challenges in Synthetic Aperture Radar (SAR) object detection lies in the pervasive influence of coherent noise. As a common practice, most existing methods, whe…
Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology
Wenhao Tang, Rong Qin, Heng Fang +4
Pre-trained encoders for offline feature extraction followed by multiple instance learning (MIL) aggregators have become the dominant paradigm in computational pathology (CPath), b…
A Simple Detector with Frame Dynamics is a Strong Tracker
Chenxu Peng, Chenxu Wang, Minrui Zou +5
Infrared object tracking plays a crucial role in Anti-Unmanned Aerial Vehicle (Anti-UAV) applications. Existing trackers often depend on cropped template regions and have limited m…
A Vision for Auto Research with LLM Agents
Chengwei Liu, Chong Wang, Jiayue Cao +16
This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Levera…