We aim to understand how actions are performed and identify subtle differences, such as 'fold firmly' vs. 'fold gently'. To this end, we propose a method which recognizes adverbs across different actions. However, such fine-grained annotations are difficult to obtain and their long-tailed nature makes it challenging to recognize adverbs in rare action-adverb compositions. Our approach therefore uses semi-supervised learning with multiple adverb pseudo-labels to leverage videos with only action labels. Combined with adaptive thresholding of these pseudo-adverbs we are able to make efficient use of the available data while tackling the long-tailed distribution. Additionally, we gather adverb annotations for three existing video retrieval datasets, which allows us to introduce the new tasks of recognizing adverbs in unseen action-adverb compositions and unseen domains. Experiments demonstrate the effectiveness of our method, which outperforms prior work in recognizing adverbs and semi-supervised works adapted for adverb recognition. We also show how adverbs can relate fine-grained actions.
PEPL: Precision-Enhanced Pseudo-Labeling for Fine-Grained Image Classification in Semi-Supervised Learning
HKUST(GZ)(香港科技大学(广州));Institute of Deep Perception Technology, JITRI(感知技术研究所,JITRI);University of Liverpool(利物浦大学);Nanchang University(南昌大学);DI^2 Lab(DI²实验室)
Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels
Computer Vision Lab Delft University of Technology(代尔夫特理工大学计算机视觉实验室);Delft University of Technology(代尔夫特理工大学);The Netherlands(荷兰(注:原文本中The Netherlands为国家名,根据提取规则,国家不属于机构,此处仅为完整显示原机构相关信息));Computer Vision Lab(计算机视觉实验室)
Adapting Fine-Grained Cross-View Localization to Areas without Fine Ground Truth
École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院);ShanghaiTech University(上海科技大学);Australian National University(澳大利亚国立大学);Delft University of Technology(代尔夫特理工大学)
Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Tencent AI Lab(腾讯人工智能实验室);The Chinese University of Hong Kong(香港中文大学)
FGU3R: Fine-Grained Fusion via Unified 3D Representation for Multimodal 3D Object Detection
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(北京邮电大学网络与交换技术国家重点实验室);School of Computer Science and Technology, Beijing Jiaotong University(北京交通大学计算机科学与技术学院)
FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation
University of Science and Technology of China(中国科学技术大学);Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究院(TeleAI));School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University(西北工业大学人工智能、光学与电子学院(iOPEN))
Fine-Grained Building Function Recognition from Street-View Images via Geometry-Aware Semi-Supervised Learning
School of Geospatial Engineering and Science, Sun Yat-sen University(中山大学地理空间工程与科学学院);Tsinghua University(清华大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);SenseTime Research(商汤科技研究院);Tsinghua Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院)
High-Precision Dichotomous Image Segmentation via Depth Integrity-Prior and Fine-Grained Patch Strategy
College of Computer Science, Sichuan University(四川大学计算机学院);National Key Lab of Fundamental Science on Synthetic Vision, Sichuan University(合成视觉基础科学国家实验室)
Fine-grained Context and Multi-modal Alignment for Freehand 3D Ultrasound Reconstruction
Shenzhen University(深圳大学);School of Biomedical Engineering, Shenzhen University Medical School(深圳大学医学院生物医学工程学院);National-Regional Key Technology Engineering Laboratory for Medical Ultrasound(国家区域医学超声关键技术工程实验室);Marshall Laboratory of Biomedical Engineering, Shenzhen University(深圳大学马歇尔生物医学工程实验室)
Improved Pillar with Fine-grained Feature for 3D Object Detection
Beihang University(北京航空航天大学);YiGo Robotics(易控机器人)
基于LiDAR点云的三维目标检测在自动驾驶感知模块中具有重要的作用,对检测速度、稳定性和准确性有较高的要求。然而,现有的基于点的方法由于原始点太多而难以达到速度要求,而基于体素的方法由于3D稀疏卷积而无法保证稳定的速度。相比之下,基于二维网格的方法,如PointPillar,可以很容易地实现一个稳定的和高效的速度基于简单的二维卷积,但它很难得到竞争力的精度受到粗粒度的点云表示。因此,本文在PointPillar的基础上提出了一种具有细粒度特征的改进型柱子,可以显著提高柱子的检测精度。该模型由高度子柱和稀疏微柱两个模块组成,分别在三维空间的垂直和水平方向上实现了细粒度的表示。对于高度敏感的子柱,我们引入了高度位置编码,以保持每个子柱的高度信息,在投影到一个2D伪图像。对于稀疏型微柱模型,我们引入了基于稀疏的CNN骨干,由密集特征和稀疏注意力模块堆叠而成,以有效地提取具有更大感受野的特征。实验结果表明,我们提出的方法在Waymo Open Dataset上的性能明显优于以前最先进的3D检测方法。相关规范将发布,以方便学术界和工业界的研究。
GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control
École Polytechnique Fédérale de Lausanne (EPFL)(洛桑联邦理工学院(EPFL));University of Bern(伯尔尼大学);Swiss Data Science Center(瑞士数据科学中心);University of Zurich(苏黎世大学);ETH Zurich(苏黎世联邦理工学院)
DRAFE: Domain-Robust Asymmetric Fusion of Heterogeneous Detection Transformers for Cross-City Fine-Grained Traffic Object Detection
Iowa State University(爱荷华州立大学);University of Arkansas(阿肯色大学);Parsons Corporation(帕森斯公司);Jacobs(雅各布斯公司);University of South Florida(南佛罗里达大学);Neel-Schaffer, Inc.(尼尔-沙弗公司)
针对跨城市细粒度交通目标检测中细粒度识别与域泛化难兼顾的问题,提出 DRAFE 模型,通过两阶段训练及多模块融合策略,在 AI City Challenge 2026 Track 6 任务中取得 0.4022 mAP 排名第六的成绩,性能优于初步集成模型。
Static Segmentation by Tracking: A Label-Efficient Approach for Fine-Grained Specimen Image Segmentation
The Ohio State University(俄亥俄州立大学);Princeton University(普林斯顿大学);University of Maine(缅因大学);University of Miami(迈阿密大学);Virginia Tech(弗吉尼亚理工大学);Duke University(杜克大学);Rensselaer Polytechnic Institute(拉特格斯理工学院)
Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection
National Engineering Research Center for Multimedia Software, Institute of Artificial Intelligence, School of Computer Science, Wuhan University, China(国家多媒体软件工程研究中心、人工智能研究院、计算机科学学院、武汉大学,中国);Hubei Key Laboratory of Multimedia(湖北省多媒体关键实验室);The University of Tokyo, Japan(东京大学,日本);National Institute of Informatics, Japan(日本信息处理学会);School of Computer Science(计算机科学学院);Technology, Wuhan University of Science(科技,武汉科技大学)
Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
Korea Advanced Institute of Science and Technology(韩国科学技术院);Ewha Womans University(梨花女子大学);Zhejiang University(浙江大学);Zhejiang Lab(之江实验室);University of Michigan(密歇根大学)