Few-Shot Open-Set Recognition (FSOSR) targets a critical real-world challenge, aiming to categorize inputs into known categories, termed closed-set classes, while identifying open-set inputs that fall outside these classes. Although transfer learning where a model is tuned to a given few-shot task has become a prominent paradigm in closed-world, we observe that it fails to expand to open-world. To unlock this challenge, we propose a two-stage method which consists of open-set aware meta-learning with open-set free transfer learning. In the open-set aware meta-learning stage, a model is trained to establish a metric space that serves as a beneficial starting point for the subsequent stage. During the open-set free transfer learning stage, the model is further adapted to a specific target task through transfer learning. Additionally, we introduce a strategy to simulate open-set examples by modifying the training dataset or generating pseudo open-set examples. The proposed method achieves state-of-the-art performance on two widely recognized benchmarks, miniImageNet and tieredImageNet, with only a 1.5\% increase in training effort. Our work demonstrates the effectiveness of transfer learning in FSOSR.
BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models
Department of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程系）；School of Artificial Intelligence, Shenzhen University（深圳大学人工智能学院）；Michigan State University（密歇根州立大学）
TPCap: Unlocking Zero-Shot Image Captioning with Trigger-Augmented and Multi-Modal Purification Modules
Faculty of Information Engineering and Automation, Kunming University of Science and Technology（昆明理工大学信息工程与自动化学院）；Yunnan Key Laboratory of Computer Technologies Application（云南省计算机技术应用重点实验室）；Hongyun Honghe Group Honghe Cigarette Factory（红云红河集团红河卷烟厂）
Supervised Classification Heads as Semantic Prototypes: Unlocking Vision-Language Alignment via Weight Recycling
Department of Computer Science and Artificial Intelligence, DaSCI Institute, University of Granada, Granada, Spain（计算机科学与人工智能系，DaSCI研究所，格拉纳达大学，格拉纳达，西班牙）；Department of Mathematics ``Tullio Levi-Civita'', University of Padova, Padova, Italy（托里利-西维塔数学系，帕多瓦大学，帕多瓦，意大利）
Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning
School of Computer Science, Nanjing University of Information Science（南京信息工程大学计算机科学学院）；School of Computing, Macquarie University（麦考瑞大学计算机学院）；School of Cybersecurity, Northwestern Polytechnical University（西北工业大学网络安全学院）；School of Computer Science, Nanjing University of Posts（南京邮电大学计算机科学学院）；University of California at Merced（加州大学默塞德分校）
Unlocking the power of partnership: How humans and machines can work together to improve face recognition
National Institute of Standards and Technology（美国国家标准与技术研究院）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；School of Behavioral and Brain Sciences（行为与脑科学学院）
Unlocking Compositional Generalization in Continual Few-Shot Learning
Faculty of Information Technology, University of Science, Vietnam National University（信息科技学院，科学大学，越南国家大学）；Department of Computer Science, University of Warwick（计算机科学系，沃里克大学）
Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis
Institute of Artificial Intelligence, University of Central Florida（中佛罗里达大学人工智能研究所）；Department of Clinical Sciences, College of Medicine, University of Central Florida（中佛罗里达大学医学院临床科学系）；Department of Computer Science, University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校计算机科学系）；Department of Computer Science, Northern Illinois University（北伊利诺伊大学计算机科学系）；Industrial and Systems Engineering, Northern Illinois University（北伊利诺伊大学工业与系统工程系）
Skeleton-DML: Deep Metric Learning for Skeleton-Based One-Shot Action Recognition
University of Koblenz-Landau（科布伦茨-兰道大学）
单次动作识别允许仅用单个训练样本来识别人类执行的动作。这可以通过使机器人能够对以前看不见的行为做出反应来积极影响人机交互。我们将一次性动作识别问题表述为深度度量学习问题，并提出了一种新的基于图像的骨架表示，该表示在度量学习设置中表现良好。因此，我们训练一个模型，将图像表示投影到嵌入空间中。在嵌入空间中，相似的动作具有较低的欧氏距离，而不相似的动作具有较高的距离。一次性动作识别问题变成了一组活动参考样本中的最近邻搜索。我们评估我们提出的表示对其他各种基于图像的图像表示的性能。此外，我们提出了一个消融研究，显示了不同的嵌入向量的大小，损失和扩增的影响。我们的方法在相当的训练设置下，将NTU RGB + D 120数据集上的一次性动作识别协议的最先进水平提高了3.3%。通过额外的增强，我们的结果提高了7.7%以上。
One-shot action recognition in challenging therapy scenarios
Instituto Superior Técnico, Universidade de Lisboa（里斯本大学高等理工学院）；Universidad de Zaragoza（萨拉戈萨大学）；Bitbrain Technologies（Bitbrain技术公司）；Politecnico di Milano（米兰理工大学）
Can Large Language Models Grasp Event Signals? Exploring Pure Zero-Shot Event-based Recognition
School of Computer and Artificial Intelligence（计算机与人工智能学院）；Beijing Technology and Business University（北京工商大学）；School of Computer Science（计算机科学学院）；The University of Sydney（悉尼大学）
From Objects to Events: Unlocking Complex Visual Understanding in Object Detectors via LLM-guided Symbolic Reasoning
Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（中国教育部多媒体可信感知与高效计算重点实验室，厦门大学）；Peking University（北京大学）；Tencent Youtu Lab（腾讯优图实验室）
Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
ICG, TU Graz（格拉茨工业大学ICG研究所）；CDL-EML（CDL-EML中心）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；JKU（约翰内斯开普勒大学）；IBM Research（IBM研究院）；Weizmann Institute of Science（魏茨曼科学研究所）；University of Bonn（波恩大学）
UC, San Diego（加州大学圣地亚哥分校）；Wormpex AI Research（Wormpex人工智能研究院）
研究了开集识别问题。虽然以前的方法只在大规模分类器训练的背景下考虑这个问题，但我们寻求一个统一的解决方案来解决这个问题和低拍摄分类设置。有人认为，经典的softmax分类器是开集识别的一个糟糕的解决方案，因为它往往过拟合的训练类。随机化，然后提出作为解决这个问题。这表明使用元学习技术，通常用于Few-Shot分类，用于开集识别的解决方案。然后引入一种新的oPen sEt Meta LEaRning（PEELER）算法。这结合了随机选择一组新的类每集，损失，最大化后验熵的例子，这些类，和一个新的度量学习公式的基础上的马氏距离。实验结果表明，PEELER实现了最先进的开集识别性能的Few-Shot和大规模的识别。在CIFAR和miniImageNet上，对于给定的可见类分类精度，它在可见/不可见类检测AUROC中实现了实质性的增益。
