Multi-Label Classification refers to the classification task where a data sample is associated with multiple labels simultaneously, which is widely used in text classification, image classification, and other fields. Different from the traditional single-label classification, each instance in Multi-Label Classification corresponds to multiple labels, and there is a correlation between these labels, which contains a wealth of information. Therefore, the ability to effectively mine and utilize the complex correlations between labels has become a key factor in Multi-Label Classification methods. In recent years, research on label correlations has shown a significant growth trend internationally, reflecting its importance. Given that, this paper presents a survey on the label correlations in Multi-Label Classification to provide valuable references and insights for future researchers. The paper introduces multi-label datasets across various fields, elucidates and categorizes the concept of label correlations, emphasizes their utilization in Multi-Label Classification and associated subproblems, and provides a prospect for future work on label correlations.

Multi-label text classification is a fundamental and important task in natural language processing, with widespread applications in specialized domains such as sentiment analysis, legal document classification, and medical coding. However, real-world applications often face challenges such as high annotation costs, data scarcity, and long-tailed label distributions. These issues are particularly pronounced in professional fields like healthcare and law, significantly limiting the performance of classification models. This paper focuses on the topic of few-shot multi-label text classification and provides a systematic survey of current research progress and mainstream techniques. From multiple perspectives, including modeling under few-shot settings, research status, technical approaches, commonly used datasets, and evaluation metrics, this study comprehensively reviews the existing literature and advances. At the technical level, the methods are broadly categorized into data augmentation and model training. The latter includes paradigms such as transfer learning, prompt learning, metric learning, meta-learning, graph neural networks, and attention mechanisms. In addition, this survey explores the research and progress of specific tasks under few-shot multi-label scenarios, such as multi-label aspect category detection, multi-label intent detection, and hierarchical multi-label text classification. In terms of experimental resources, this review compiles commonly used datasets along with their characteristics and categorizes evaluation metrics that are widely adopted in few-shot multi-label classification settings. Finally, it discusses the key research challenges and outlines future directions, offering insights to guide further investigation in this field.

With the rapid development of the Internet of Things (IoT), data centers are facing growing performance demands for flow deadline requirements, other to the low latency and high throughput. To address congestion issues that affect the performance of data center networks, this paper proposes D2C4, a deadline-aware data-credit coupled congestion control scheme. By tightly coupled data-credit integration using an ECN-based feedback loop, D2C4 minimizes credit waste while a credit-driven scheduler meets IoT applications’ flow deadlines. The key innovations of D2C4 include: 1) Data-credit coupling for performance gains; 2) ECN-based credit rate control reducing waste; 3) Deadline-sensitive credit-based flow scheduling to meet flow deadline demands. We conduct extensive experiments of D2C4 through small-scale DPDK-based tests and large-scale OMNeT++ simulations. Experimental results show that D2C4 outperforms existing protocols in flow completion time, throughput, deadline miss ratio, and packet drop.

Zero-shot text classification effectively alleviates the challenges of data scarcity and the high cost of manual annotation by eliminating the reliance on labeled training data. However, existing methods still face critical challenges in semantic integrity and cross-modal collaboration: the label mapping process suffers from semantic deviation due to the brevity and abstraction of label text; fixed label text embedding methods rely on manual design and are sensitive to embedding positions; matrix-weighted fusion approaches tend to lose deep semantic information; and automatically generated label descriptions lack precision. To address these issues, this paper proposes a CLIP-based framework for cross-modal information completion (CLIPCMIC) for zero-shot text classification. Specifically, this method designs a novel image-label mapping mechanism and utilizes context-based text generation to construct cross-modal information-completed images. Additionally, a dual-pathway enhancement strategy is introduced during the inference phase to improve text semantic perception. To mitigate the sensitivity to embedding positions, an automatic selection method for annotation placement is proposed. Furthermore, to enhance the precision of automatically generated label descriptions, a two-stage keyword automatic selection mechanism (Selection-CLIPCMIC) is introduced. To validate the effectiveness of the proposed method, this study conducts systematic experiments on seven publicly available benchmark datasets. The results show that CLIPCMIC outperforms the state-of-the-art baseline methods LABCLIP and CLIPMulti (MF) across multiple datasets, with performance gains ranging from 0.5% to 11.7%. In addition, we conduct extensive experiments for further verification.

Object detection in unmanned aerial vehicle (UAV)-based visual sensing is important for aerial monitoring and intelligent perception. However, it remains difficult because camera-captured aerial images often contain small targets, cluttered backgrounds, occlusion, and limited edge-computing resources. We propose LFC-YOLO, a lightweight feature-complementary detector for small objects in UAV imagery. The main component of LFC-YOLO is the Tiny Object-Specific Detection Architecture (TSD-Arch), which removes redundant computation from deep layers and builds a shallow high-resolution feature pyramid to preserve localization cues for small targets. To reduce the extra cost introduced by high-resolution feature fusion, lightweight GSConv is integrated into the reconstructed neck. In addition, we embed a Feature Complementary Mapping (FCM) block into the C2f backbone structure and form a C2f-based Feature Complementary Mapping (C2f-FCM) module. This module combines semantic and spatial information and reduces interference from complex backgrounds. Experiments on VisDrone2019 show that LFC-YOLO improves the mean average precision at an intersection-over-union threshold of 0.5 (${\mathrm{mAP}}_{50}$) by 4.0 percentage points over YOLOv8s while reducing the number of model parameters by 73.9%. Additional evaluation on UAVDT shows that the proposed design remains effective across different UAV scenarios.