The rapid advancement of Artificial Intelligence Generated Content (AIGC) techniques has unlocked opportunities in generating diverse and compelling advertising images based on referenced product images and textual scene descriptions. This capability substantially reduces human labor and production costs in traditional marketing workflows. However, existing AIGC techniques either demand extensive fine-tuning for each referenced image to achieve high fidelity, or they struggle to maintain fidelity across diverse products, making them impractical for e-commerce and marketing industries. To tackle this limitation, we first construct AdProd-100K, a large-scale advertising image generation dataset. A key innovation in its construction is our dual data augmentation strategy, which fosters robust, 3D-aware representations crucial for realistic and high-fidelity image synthesis. Leveraging this dataset, we propose RefAdGen, a generation framework that achieves high fidelity through a decoupled design. The framework enforces precise spatial control by injecting a product mask at the U-Net input, and employs an efficient Attention Fusion Module (AFM) to integrate product features. This design effectively resolves the fidelity-efficiency dilemma present in existing methods. Extensive experiments demonstrate that RefAdGen achieves state-of-the-art performance, showcasing robust generalization by maintaining high fidelity and remarkable visual results for both unseen products and challenging real-world, in-the-wild images. This offers a scalable and cost-effective alternative to traditional workflows.

Zhihao Shuai, Yiyun Chen, Maolin Ma, Yutong Chen, Hanjia Qiu, Jing Xu, Ziye Chen, Weikai Yang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Effective monitoring of unusual transportation behaviors, such as wrong-way cycling (i.e., riding a bicycle or e-bike against designated traffic flow), is crucial for optimizing law enforcement deployment and traffic planning. However, accurately recording all wrong-way cycling events is both unnecessary and infeasible in resource-constrained environments, as it requires high-resolution cameras for evidence collection and event detection. To address this challenge, we propose WWC-Predictor, a novel method for efficiently estimating the wrong-way cycling ratio, defined as the proportion of wrong-way cycling events relative to the total number of cycling movements over a given time period. The core innovation of our method lies in accurately detecting wrong-way cycling events in sparsely sampled frames using a light-weight detector, then estimating the overall ratio using an autoregressive moving average model. To evaluate the effectiveness of our method, we construct a benchmark dataset consisting of 35 minutes of video sequences with minute-level annotations. Our method achieves an average error rate of a mere 1.475% while consuming only 19.12% GPU time required by conventional tracking methods, validating its effectiveness in estimating the wrong-way cycling ratio. Our source code is publicly available at:https://github.com/VICA-Lab-HKUST-GZ/WWC-Predictor

Bias in machine learning datasets occurs when certain attributes are unfairly associated, e.g., serious males being mostly linked with law enforcement officers in job-related image datasets. Training models on biased datasets will degrade model performance and lead to fairness issues, particularly for underrepresented groups. Existing bias detection methods mainly focus on explicit biases associated with predefined attributes (e.g., gender and ethnicity) while overlooking implicit biases associated with subtler, dataset-specific attributes (e.g., facial expressions and attire). To address this gap, we present BiasField, an interactive tool that offers a closed-loop workflow for detecting, analyzing, and mitigating bias. Central to BiasField is the adaptive detection of both explicit and implicit biases, a process facilitated by the automatic extraction of the dataset-specific attributes. It then employs a plant-growth metaphor to visualize these biases, enabling structured analysis to identify similar biases and track how they strengthen with additional attributes. Finally, confirmed biases are mitigated through targeted generative data augmentation. A user study, two case studies, and an expert study are conducted to demonstrate its capability to detect, analyze, and mitigate complex biases.

Although data visualization is powerful for revealing patterns and communicating insights, creating effective visualizations requires familiarity with authoring tools and often disrupts the analysis flow. While large language models show promise for automatically converting analysis intent into visualizations, existing methods function as black boxes without transparent reasoning processes, which prevents users from understanding design rationales and refining suboptimal outputs. To bridge this gap, we propose integrating Chain-of-Thought (CoT) reasoning into the Natural Language to Visualization (NL2VIS) pipeline. First, we design a comprehensive CoT reasoning process for NL2VIS and develop an automatic pipeline to equip existing datasets with structured reasoning steps. Second, we introduce nvBench-CoT, a specialized dataset capturing detailed step-by-step reasoning from ambiguous natural language descriptions to finalized visualizations, which enables state-of-the-art performance when used for model fine-tuning. Third, we develop DeepVIS, an interactive visual interface that tightly integrates with the CoT reasoning process, allowing users to inspect reasoning steps, identify errors, and make targeted adjustments to improve visualization outcomes. Quantitative benchmark evaluations, two use cases, and a user study collectively demonstrate that our CoT framework effectively enhances NL2VIS quality while providing insightful reasoning steps to users.

Sample selection improves the efficiency and effectiveness of machine learning models by providing informative and representative samples. Typically, samples can be modeled as a sample graph, where nodes are samples and edges represent their similarities. Most existing methods are based on local information, such as the training difficulty of samples, thereby overlooking global information, such as connectivity patterns. This oversight can result in suboptimal selection because global information is crucial for ensuring that the selected samples well represent the structural properties of the graph. To address this issue, we employ structural entropy to quantify global information and losslessly decompose it from the whole graph to individual nodes using the Shapley value. Based on the decomposition, we present $\textbf{S}$tructural-$\textbf{E}$ntropy-based sample $\textbf{S}$election ($\textbf{SES}$), a method that integrates both global and local information to select informative and representative samples. SES begins by constructing a $k$NN-graph among samples based on their similarities. It then measures sample importance by combining structural entropy (global metric) with training difficulty (local metric). Finally, SES applies importance-biased blue noise sampling to select a set of diverse and representative samples. Comprehensive experiments on three learning scenarios --- supervised learning, active learning, and continual learning --- clearly demonstrate the effectiveness of our method.

Assigning discriminable and harmonic colors to samples according to their class labels and spatial distribution can generate attractive visualizations and facilitate data exploration. However, as the number of classes increases, it is challenging to generate a high-quality color assignment result that accommodates all classes simultaneously. A practical solution is to organize classes into a hierarchy and then dynamically assign colors during exploration. However, existing color assignment methods fall short in generating high-quality color assignment results and dynamically aligning them with hierarchical structures. To address this issue, we develop a dynamic color assignment method for hierarchical data, which is formulated as a multi-objective optimization problem. This method simultaneously considers color discriminability, color harmony, and spatial distribution at each hierarchical level. By using the colors of parent classes to guide the color assignment of their child classes, our method further promotes both consistency and clarity across hierarchical levels. We demonstrate the effectiveness of our method in generating dynamic color assignment results with quantitative experiments and a user study.

The high performance of tree ensemble classifiers benefits from a large set of rules, which, in turn, makes the models hard to understand. To improve interpretability, existing methods extract a subset of rules for approximation using model reduction techniques. However, by focusing on the reduced rule set, these methods often lose fidelity and ignore anomalous rules that, despite their infrequency, play crucial roles in real-world applications. This paper introduces a scalable visual analysis method to explain tree ensemble classifiers that contain tens of thousands of rules. The key idea is to address the issue of losing fidelity by adaptively organizing the rules as a hierarchy rather than reducing them. To ensure the inclusion of anomalous rules, we develop an anomaly-biased model reduction method to prioritize these rules at each hierarchical level. Synergized with this hierarchical organization of rules, we develop a matrix-based hierarchical visualization to support exploration at different levels of detail. Our quantitative experiments and case studies demonstrate how our method fosters a deeper understanding of both common and anomalous rules, thereby enhancing interpretability without sacrificing comprehensiveness.

Fuzzy clusters, where ambiguous samples belong to multiple clusters, are common in real-world applications. Analyzing such ambiguous samples in large-scale datasets is crucial for practical applications, such as diagnosing machine learning models. A promising method to support such analysis is through hierarchical cluster-aware grid visualizations, which offer high space efficiency and clear cluster perception. However, existing cluster-aware grid layout methods cannot clarify ambiguity among fuzzy clusters, which limits their effectiveness in fuzzy cluster analysis. To tackle this issue, we introduce a hierarchical fuzzy-cluster-aware grid layout method that supports hierarchical exploration of large-scale datasets. Throughout the hierarchical exploration, it is crucial to facilitate fuzzy cluster analysis while maintaining visual continuity for users. To achieve this, we propose a two-step optimization strategy for enhancing cluster perception, clarifying ambiguity, and preserving stability during the exploration. The first step is to create cluster-aware partitions, where each partition corresponds to a cluster. This step focuses on enhancing cluster perception and maintaining the previous shapes and positions of clusters to preserve stability at the cluster level. The second step is to generate a grid layout for each partition. In addition to placing similar samples together, this step also places ambiguous samples near the boundaries to clarify ambiguity and reveal the root causes of their occurrences and maintains the relative positions of the samples in the same cluster to preserve stability at the sample level. Several quantitative experiments and a use case are conducted to demonstrate the effectiveness and usefulness of our method in analyzing large-scale datasets, especially in fuzzy cluster analysis.

Recent studies have indicated that foundation models, such as BERT and GPT, excel at adapting to various downstream tasks. This adaptability has made them a dominant force in building artificial intelligence (AI) systems. Moreover, a new research paradigm has emerged as visualization techniques are incorporated into these models. This study divides these intersections into two research areas: visualization for foundation model (VIS4FM) and foundation model for visualization (FM4VIS). In terms of VIS4FM, we explore the primary role of visualizations in understanding, refining, and evaluating these intricate foundation models. VIS4FM addresses the pressing need for transparency, explainability, fairness, and robustness. Conversely, in terms of FM4VIS, we highlight how foundation models can be used to advance the visualization field itself. The intersection of foundation models with visualizations is promising but also introduces a set of challenges. By highlighting these challenges and promising opportunities, this study aims to provide a starting point for the continued exploration of this research avenue.

Temporal action localization aims to identify the boundaries and categories of actions in videos, such as scoring a goal in a football match. Single-frame supervision has emerged as a labor-efficient way to train action localizers as it requires only one annotated frame per action. However, it often suffers from poor performance due to the lack of precise boundary annotations. To address this issue, we propose a visual analysis method that aligns similar actions and then propagates a few user-provided annotations (e.g., boundaries, category labels) to similar actions via the generated alignments. Our method models the alignment between actions as a heaviest path problem and the annotation propagation as a quadratic optimization problem. As the automatically generated alignments may not accurately match the associated actions and could produce inaccurate localization results, we develop a storyline visualization to explain the localization results of actions and their alignments. This visualization facilitates users in correcting wrong localization results and misalignments. The corrections are then used to improve the localization results of other actions. The effectiveness of our method in improving localization performance is demonstrated through quantitative evaluation and a case study.

Existing model evaluation tools mainly focus on evaluating classification models, leaving a gap in evaluating more complex models, such as object detection. In this paper, we develop an open-source visual analysis tool, Uni-Evaluator, to support a unified model evaluation for classification, object detection, and instance segmentation in computer vision. The key idea behind our method is to formulate both discrete and continuous predictions in different tasks as unified probability distributions. Based on these distributions, we develop 1) a matrix-based visualization to provide an overview of model performance; 2) a table visualization to identify the problematic data subsets where the model performs poorly; 3) a grid visualization to display the samples of interest. These visualizations work together to facilitate the model evaluation from a global overview to individual samples. Two case studies demonstrate the effectiveness of Uni-Evaluator in evaluating model performance and making informed improvements.

Label quality issues, such as noisy labels and imbalanced class distributions, have negative effects on model performance. Automatic reweighting methods identify problematic samples with label quality issues by recognizing their negative effects on validation samples and assigning lower weights to them. However, these methods fail to achieve satisfactory performance when the validation samples are of low quality. To tackle this, we develop Reweighter, a visual analysis tool for sample reweighting. The reweighting relationships between validation samples and training samples are modeled as a bipartite graph. Based on this graph, a validation sample improvement method is developed to improve the quality of validation samples. Since the automatic improvement may not always be perfect, a co-cluster-based bipartite graph visualization is developed to illustrate the reweighting relationships and support the interactive adjustments to validation samples and reweighting results. The adjustments are converted into the constraints of the validation sample improvement method to further improve validation samples. We demonstrate the effectiveness of Reweighter in improving reweighting results through quantitative evaluation and two case studies.

Grid visualizations are widely used in many applications to visually explain a set of data and their proximity relationships. However, existing layout methods face difficulties when dealing with the inherent cluster structures within the data. To address this issue, we propose a cluster-aware grid layout method that aims to better preserve cluster structures by simultaneously considering proximity, compactness, and convexity in the optimization process. Our method utilizes a hybrid optimization strategy that consists of two phases. The global phase aims to balance proximity and compactness within each cluster, while the local phase ensures the convexity of cluster shapes. We evaluate the proposed grid layout method through a series of quantitative experiments and two use cases, demonstrating its effectiveness in preserving cluster structures and facilitating analysis tasks.

Few-shot classification refers to recognizing several novel classes given only a few labeled samples. Many recent methods try to gain an adaptation benefit by learning prior knowledge from more base training domains, aka. multi-domain few-shot classification. However, with extensive empirical evidence, we find more is not always better: current models do not necessarily benefit from pre-training on more base classes and domains, since the pre-trained knowledge might be non-positive for a downstream task. In this work, we hypothesize that such redundant pre-training can be avoided without compromising the downstream performance. Inspired by the selective activating/silencing mechanism in the biological memory system, which enables the brain to learn a new concept from a few experiences both quickly and accurately, we propose to actively silence those redundant base classes and domains for efficient multi-domain few-shot classification. Then, a novel data-driven approach named Active Silencing with hierarchical Subset Selection (AS3) is developed to address two problems: 1) finding a subset of base classes that adequately represent novel classes for efficient positive transfer; and 2) finding a subset of base learners (i.e., domains) with confident accurate prediction in a new domain. Both problems are formulated as distance-based sparse subset selection. We extensively evaluate AS3 on the recent META-DATASET benchmark as well as MNIST, CIFAR10, and CIFAR100, where AS3 achieves over 100% acceleration while maintaining or even improving accuracy. Our code and Appendix are available at https://github.com/indussky8/AS3.

The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually. Existing methods cannot meet the need for understanding different models in one framework due to the lack of a unified measure for explaining both low-level (e.g., words) and high-level (e.g., phrases) features. We have developed a visual analysis tool, DeepNLPVis, to enable a unified understanding of NLP models for text classification. The key idea is a mutual information-based measure, which provides quantitative explanations on how each layer of a model maintains the information of input words in a sample. We model the intra- and inter-word information at each layer measuring the importance of a word to the final prediction as well as the relationships between words, such as the formation of phrases. A multi-level visualization, which consists of a corpus-level, a sample-level, and a word-level visualization, supports the analysis from the overall training set to individual samples. Two case studies on classification tasks and comparison between models demonstrate that DeepNLPVis can help users effectively identify potential problems caused by samples and model architectures and then make informed improvements.

The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes and make improvements. To tackle this issue, we propose a visual analysis method, FSLDiagnotor. Given a set of base learners and a collection of samples with a few shots, we consider two problems: 1) finding a subset of base learners that well predict the sample collections; and 2) replacing the low-quality shots with more representative ones to adequately represent the sample collections. We formulate both problems as sparse subset selection and develop two selection algorithms to recommend appropriate learners and shots, respectively. A matrix visualization and a scatterplot are combined to explain the recommended learners and shots in context and facilitate users in adjusting them. Based on the adjustment, the algorithm updates the recommendation results for another round of improvement. Two case studies are conducted to demonstrate that FSLDiagnotor helps build a few-shot classifier efficiently and increases the accuracy by 12% and 21%, respectively.

Visual analytics for machine learning has recently evolved as one of the most exciting areas in the field of visualization. To better identify which research topics are promising and to learn how to apply relevant techniques in visual analytics, we systematically review 259 papers published in the last ten years together with representative works before 2010. We build a taxonomy, which includes three first-level categories: techniques before model building, techniques during modeling building, and techniques after model building. Each category is further characterized by representative analysis tasks, and each task is exemplified by a set of recent influential works. We also discuss and highlight research challenges and promising potential future research opportunities useful for visual analytics researchers.

Hierarchical clustering is an important technique to organize big data for exploratory data analysis. However, existing one-size-fits-all hierarchical clustering methods often fail to meet the diverse needs of different users. To address this challenge, we present an interactive steering method to visually supervise constrained hierarchical clustering by utilizing both public knowledge (e.g., Wikipedia) and private knowledge from users. The novelty of our approach includes 1) automatically constructing constraints for hierarchical clustering using knowledge (knowledge-driven) and intrinsic data distribution (data-driven), and 2) enabling the interactive steering of clustering through a visual interface (user-driven). Our method first maps each data item to the most relevant items in a knowledge base. An initial constraint tree is then extracted using the ant colony optimization algorithm. The algorithm balances the tree width and depth and covers the data items with high confidence. Given the constraint tree, the data items are hierarchically clustered using evolutionary Bayesian rose tree. To clearly convey the hierarchical clustering results, an uncertainty-aware tree visualization has been developed to enable users to quickly locate the most uncertain sub-hierarchies and interactively improve them. The quantitative evaluation and case study demonstrate that the proposed approach facilitates the building of customized clustering trees in an efficient and effective manner.