Xiaobo Wang

EAAI Journal 2026 Journal Article

A multispectral feature framework for predicting soybean high temperature resistance grades based on masked autoencoding and supervised contrastive learning with dual-branch pretraining

• Youhui Deng
• Weizhi Yang
• Haoran Chen
• Xiaodan Zhang
• Jiajia Li
• Xiaobo Wang
• Xiu Jin

Global climate change has led to increasingly frequent heat stress, posing a serious threat to soybean yield and quality. Accurately evaluating soybean heat resistance is of great significance for enhancing crop adaptability and advancing stress-resilient breeding. However, conventional deep learning approaches for field crop phenotyping are often constrained by data scarcity and the difficulty of labeling, underscoring the need for more effective modeling strategies. To address this challenge, we propose the soybean multispectral self-supervised fusion framework (SoyMSF), a dual-branch learning architecture that integrates masked autoencoding (MAE) and supervised contrastive learning (SCL) to predict soybean high-temperature resistance grades. The multispectral image data in this study were all derived from the samples of the high-temperature stress (HT) group and the control (CK) group of soybeans in the experimental field. In the framework, the MAE module performs structure-aware unsupervised pretraining to extract latent spatial features from multispectral images, while the SCL module constructs contrastive tasks using HT and CK labels to strengthen class-discriminative feature representation. Experimental results demonstrate that SoyMSF achieves a prediction accuracy of 86. 61 % and an F1-score of 85. 49 % on the test set, significantly outperforming any single-model baseline. These findings highlight the importance of combining label strategies with feature fusion in contrastive learning, and demonstrate the potential of SoyMSF for high-throughput phenotyping and stress-resilient breeding. Overall, SoyMSF not only supports high-throughput phenotyping and stress-resilient breeding in soybeans, but also provides a generalizable paradigm for self-supervised multispectral modeling with potential applications in broader agricultural image analysis tasks.

EAAI Journal 2026 Journal Article

Corrigendum to “A multispectral feature framework for predicting soybean high temperature resistance grades based on masked autoencoding and supervised contrastive learning with dual-branch pretraining” [Eng. Appl. Artif. Intell. 165 (2026) 113487]

• Youhui Deng
• Weizhi Yang
• Haoran Chen
• Xiaodan Zhang
• Jiajia Li
• Xiaobo Wang
• Xiu Jin

EAAI Journal 2025 Journal Article

Practical framework for generative on-branch soybean pod detection in occlusion and class imbalance scenes

• Kanglei Wu
• Tan Wang
• Yuan Rao
• Xiu Jin
• Xiaobo Wang
• Jiajia Li
• Zhe Zhang
• Zhaohui Jiang

The number of pods per plant can serve as an effective indicator of soybean yield, and accurately determining this is essential for evaluating high-quality soybean varieties. However, traditional manual pod counting is time-consuming and laborious. Although deep learning-based pod detection methods have attracted much attention, there are still considerable challenges for the effective detection of pods in occlusion and class imbalance scenes. As a remedy, this study proposes a framework that leverages synthetic pod image generation and multi-stage transfer learning to generate detection model of on-branch soybean pods in complex scenes. This framework employs a novel pipeline: initially separating individual pods from non-occluded pod images in an off-branch pod training set, then using these to generate synthetic datasets with diverse pod features. Next, a multi-stage transfer learning method is employed to train an on-branch pod detection model, leveraging both real and synthetic datasets to enhance pod feature extraction in complex scenes. The detection model of proposed framework, YOLOv7-tiny (tiny version of You Only Look Once v7), integrates an angle prediction module based on Circular Smooth Label for rotated object detection, Coordinate Attention modules for enhanced feature extraction and Minimum Point Distance Intersection over Union Loss for precise bounding box perception. Experimental results show that proposed framework achieves an 81. 1% mAP (mean Average Precision) for detecting on-branch pods in complex scenes, surpassing the best-performing model by 23. 7%. This proposed method presents an effective solution for complex on-branch pod detection, having great potential of serving as robust pipeline for similar agricultural tasks.

TMLR Journal 2025 Journal Article

The AI Hippocampus: How Far are We From Human Memory?

• Zixia Jia
• Jiaqi Li
• Yipeng Kang
• Yuxuan Wang
• Tong Wu
• Quansen Wang
• Xiaobo Wang
• Shuyi Zhang

Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models (LLMs) and Multi-Modal LLMs (MLLMs). As these models transition from static predictors to interactive systems capable of continual learning and personalized inference, the incorporation of memory mechanisms has emerged as a central theme in their architectural and functional evolution. This survey presents a comprehensive and structured synthesis of memory in LLMs and MLLMs, organizing the literature into a cohesive taxonomy comprising implicit, explicit, and agentic memory paradigms. Specifically, the survey delineates three primary memory frameworks. \textit{Implicit memory} refers to the knowledge embedded within the internal parameters of pre-trained transformers, encompassing their capacity for memorization, associative retrieval, and contextual reasoning. Recent work has explored methods to interpret, manipulate, and reconfigure this latent memory. \textit{Explicit memory} involves external storage and retrieval components designed to augment model outputs with dynamic, queryable knowledge representations—such as textual corpora, dense vectors, and graph-based structures—thereby enabling scalable and updatable interaction with information sources. \textit{Agentic memory} introduces persistent, temporally extended memory structures within autonomous agents, facilitating long-term planning, self-consistency, and collaborative behavior in multi-agent systems, with relevance to embodied and interactive AI. Extending beyond text, the survey examines the integration of memory within multi-modal settings, where coherence across vision, language, audio, and action modalities is essential. Key architectural advances, benchmark tasks, and open challenges are discussed, including issues related to memory capacity, alignment, factual consistency, and cross-system interoperability. By charting the current landscape and identifying critical research directions, this survey aims to inform the development of memory-augmented (M)LLMs that are more flexible, context-sensitive, and aligned with the requirements of real-world intelligent systems. The survey’s website is available at \url{https://github.com/bigai-nlco/LLM-Memory-Survey}.

IROS Conference 2023 Conference Paper

Lightweight Real-Time Detection Model for Multi-Sheep Abnormal Behaviour Based on Yolov7-Tiny

• Haotian Zhang
• Yuan Ma
• Xiaobo Wang
• Rui Mao 0012
• Meili Wang 0001

Animal behaviour can reflect the health and physiological stage of the animal. Animal behaviour recognition is a vital part of automated farming systems. Although image-based deep learning algorithms can accurately identify animal behaviour, the lack of data on animal abnormal behaviour makes the practical deployment of models of limited significance. At the same time, the ageing of farm monitoring equipment is also a key factor hindering automated farming. This paper constructs a sheep abnormal behaviour dataset ABSB to address these issues and proposes a lightweight real-time multi-sheep abnormal behaviour detection model YOLOv7-Lrab based on the YOLOv7-tiny network. The abnormal behaviour dataset includes four normal behaviours: standing, lying, eating and drinking, and three abnormal behaviours: lameness, attack and death. In the proposed YOLOv7-Lrab model, the small target detection layer, Coordinate attention module, SPD-Conv and Mobileone module are added compared to YOLOv7-tiny. The experimental results show that with a 7: 3 ratio of training data to test data, 96. 5% recognition accuracy and 95. 5% recall can be achieved, and the model size is only 4. 5MB with fps of 156. The model is compressed to a minimum without loss of accuracy, providing a new idea for deploying deep learning model in practical application scenarios.

AAAI Conference 2021 Conference Paper

Teacher Guided Neural Architecture Search for Face Recognition

• Xiaobo Wang

Knowledge distillation is an effective tool to compress large pre-trained convolutional neural networks (CNNs) or their ensembles into models applicable to mobile and embedded devices. However, with expected flops or latency, existing methods are hand-crafted heuristics. They propose to predefine the target student network for knowledge distillation, which may be sub-optimal because it requires much effort to explore a powerful student from the large design space. In this paper, we develop a novel teacher guided neural architecture search method to directly search the student network with flexible channel and layer sizes. Specifically, we define the search space as the number of the channels/layers, which is sampled based on the probability distribution and is learned by minimizing the search objective of the student network. The maximum probability for the size in each distribution serves as the final searched width and depth of the target student network. Extensive experiments on a variety of face recognition benchmarks have demonstrated the superiority of our method over the state-of-the-art alternatives.

AAAI Conference 2020 Conference Paper

A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing

• Yinglu Liu
• Hailin Shi
• Hao Shen
• Yue Si
• Xiaobo Wang
• Tao Mei

Face parsing has recently attracted increasing interest due to its numerous application potentials, such as facial make up and facial image generation. In this paper, we make contributions on face parsing task from two aspects. First, we develop a high-efficiency framework for pixel-level face parsing annotating and construct a new large-scale Landmark guided face Parsing dataset (LaPa). It consists of more than 22, 000 facial images with abundant variations in expression, pose and occlusion, and each image of LaPa is provided with an 11-category pixel-level label map and 106-point landmarks. The dataset is publicly accessible to the community for boosting the advance of face parsing. 1 Second, a simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a threebranch network with elaborately developed loss functions to fully exploit the boundary information. Extensive experiments on our LaPa benchmark and the public Helen dataset show the superiority of our proposed method.

AAAI Conference 2020 Conference Paper

Mis-Classified Vector Guided Softmax Loss for Face Recognition

• Xiaobo Wang
• Shifeng Zhang
• Shuo Wang
• Tianyu Fu
• Hailin Shi
• Tao Mei

Face recognition has witnessed significant progress due to the advances of deep convolutional neural networks (CNNs), the central task of which is how to improve the feature discrimination. To this end, several margin-based (e. g. , angular, additive and additive angular margins) softmax loss functions have been proposed to increase the feature margin between different classes. However, despite great achievements have been made, they mainly suffer from three issues: 1) Obviously, they ignore the importance of informative features mining for discriminative learning; 2) They encourage the feature margin only from the ground truth class, without realizing the discriminability from other non-ground truth classes; 3) The feature margin between different classes is set to be same and fixed, which may not adapt the situations very well. To cope with these issues, this paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning. Thus we can address all the above issues and achieve more discriminative face features. To the best of our knowledge, this is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function. Experimental results on several benchmarks have demonstrated the effectiveness of our method over state-of-the-art alternatives. Our code is available at http: //www. cbsr. ia. ac. cn/users/xiaobowang/.

IJCAI Conference 2019 Conference Paper

Multi-View Active Learning for Video Recommendation

• Jia-Jia Cai
• Jun Tang
• Qing-Guo Chen
• Yao Hu
• Xiaobo Wang
• Sheng-Jun Huang

On many video websites, the recommendation is implemented as a prediction problem of video-user pairs, where the videos are represented by text features extracted from the metadata. However, the metadata is manually annotated by users and is usually missing for online videos. To train an effective recommender system with lower annotation cost, we propose an active learning approach to fully exploit the visual view of videos, while querying as few annotations as possible from the text view. On one hand, a joint model is proposed to learn the mapping from visual view to text view by simultaneously aligning the two views and minimizing the classification loss. On the other hand, a novel strategy based on prediction inconsistency and watching frequency is proposed to actively select the most important videos for metadata querying. Experiments on both classification datasets and real video recommendation tasks validate that the proposed approach can significantly reduce the annotation cost.

IJCAI Conference 2019 Conference Paper

Multi-View Multi-Label Learning with View-Specific Information Extraction

• Xuan Wu
• Qing-Guo Chen
• Yao Hu
• Dengbao Wang
• Xiaodong Chang
• Xiaobo Wang
• Min-Ling Zhang

Multi-view multi-label learning serves an important framework to learn from objects with diverse representations and rich semantics. Existing multi-view multi-label learning techniques focus on exploiting shared subspace for fusing multi-view representations, where helpful view-specific information for discriminative modeling is usually ignored. In this paper, a novel multi-view multi-label learning approach named SIMM is proposed which leverages shared subspace exploitation and view-specific information extraction. For shared subspace exploitation, SIMM jointly minimizes confusion adversarial loss and multi-label loss to utilize shared information from all views. For view-specific information extraction, SIMM enforces an orthogonal constraint w. r. t. the shared subspace to utilize view-specific discriminative information. Extensive experiments on real-world data sets clearly show the favorable performance of SIMM against other state-of-the-art multi-view multi-label learning approaches.

IJCAI Conference 2018 Conference Paper

Ensemble Soft-Margin Softmax Loss for Image Classification

• Xiaobo Wang
• Shifeng Zhang
• Zhen Lei
• Si Liu
• Xiaojie Guo
• Stan Z. Li

Softmax loss is arguably one of the most popular losses to train CNN models for image classification. However, recent works have exposed its limitation on feature discriminability. This paper casts a new viewpoint on the weakness of softmax loss. On the one hand, the CNN features learned using the softmax loss are often inadequately discriminative. We hence introduce a soft-margin softmax function to explicitly encourage the discrmination between different classes. On the other hand, the learned classifier of softmax loss is weak. We propose to assemble multiple these weak classifiers to a strong one, inspired by the recognition that the diversity among weak classifiers is critical to a good ensemble. To achieve the diversity, we adopt the Hilbert-Schmidt Independence Criterion (HSIC). Considering these two aspects in one framework, we design a novel loss, named as Ensemble Soft-Margin Softmax (EM-Softmax). Extensive experiments on benchmark datasets are conducted to show the superiority of our design over the baseline softmax loss and several state-of-the-art alternatives.

AAAI Conference 2018 Conference Paper

Latent Semantic Aware Multi-View Multi-Label Classification

• Changqing Zhang
• Ziwei Yu
• Qinghua Hu
• Pengfei Zhu
• Xinwang Liu
• Xiaobo Wang

For real-world applications, data are often associated with multiple labels and represented with multiple views. Most existing multi-label learning methods do not sufficiently consider the complementary information among multiple views, leading to unsatisfying performance. To address this issue, we propose a novel approach for multi-view multi-label learning based on matrix factorization to exploit complementarity among different views. Specifically, under the assumption that there exists a common representation across different views, the uncovered latent patterns are enforced to be aligned across different views in kernel spaces. In this way, the latent semantic patterns underlying in data could be well uncovered and this enhances the reasonability of the common representation of multiple views. As a result, the consensus multi-view representation is obtained which encodes the complementarity and consistence of different views in latent semantic space. We provide theoretical guarantee for the strict convexity for our method by properly setting parameters. Empirical evidence shows the clear advantages of our method over the state-of-the-art ones.

IJCAI Conference 2017 Conference Paper

Exclusivity Regularized Machine: A New Ensemble SVM Classifier

• Xiaojie Guo
• Xiaobo Wang
• Haibin Ling

The diversity of base learners is of utmost importance to a good ensemble. This paper defines a novel measurement of diversity, termed as exclusivity. With the designed exclusivity, we further propose an ensemble SVM classifier, namely Exclusivity Regularized Machine (ExRM), to jointly suppress the training error of ensemble and enhance the diversity between bases. Moreover, an Augmented Lagrange Multiplier based algorithm is customized to effectively and efficiently seek the optimal solution of ExRM. Theoretical analysis on convergence, global optimality and linear complexity of the proposed algorithm, as well as experiments are provided to reveal the efficacy of our method and show its superiority over state-of-the-arts in terms of accuracy and efficiency.