CrossLoc3D: Aerial-Ground Cross-Source 3D Place Recognition

CrossLoc3D：空中-地面跨源 3D 地点识别

Segment Anything

分割任何东西

Unmasking Anomalies in Road-Scene Segmentation

揭示道路场景分割中的异常现象

High Quality Entity Segmentation

高质量实体分割

Towards Open-Vocabulary Video Instance Segmentation

迈向开放词汇视频实例分割

Beyond One-to-One: Rethinking the Referring Image Segmentation

超越一对一：重新思考参考图像分割

Multiple Instance Learning Framework with Masked Hard Instance Mining for whole Slide Image Classification

用于整个幻灯片图像分类的带有掩码硬实例挖掘的多实例学习框架

Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning

Scale-MAE：用于多尺度地理空间表示学习的尺度感知屏蔽自动编码器

Towards Deeply Unified Depth-Aware Panoptic Segmentation with Bi-Directional Guidance Learning

通过双向引导学习实现深度统一的深度感知全景分割

LogicSeg: Parsing Visual Semantics with Neural Logic Learning and Reasoning

LogicSeg：通过神经逻辑学习和推理解析视觉语义

ASIC: Aligning Sparse in-the-Wild Image Collections

ASIC：对齐稀疏的野外图像集合