Photovoltaic (PV) power forecasting is critical for the operation of solar power plants and the coordination of energy within power grids. This work aims to predict future PV power time series by leveraging multimodal data. While recent studies have incorporated numerical modalities such as satellite image sequences and numerical weather prediction (NWP) time series, they often overlook textual modalities—such as the spatio-temporal context of PV plants—and the potential of pretrained large language models (LLMs). In this paper, we build upon existing numerical inputs and further explore the use of spatio-temporal text prompts, generated based on plant coordinates and forecast start time, to enhance the forecasting process. We propose PV-LLM, a satellite-text-prompted framework that integrates a pretrained LLM to improve PV power forecasting. The framework consists of three key components: Text Prompt Construction, Modality-Specific Encoding, and Adaptive Prompt Tuning. First, the Text Prompt Construction module generates spatio-temporal prompts that offer high-level semantic guidance. Next, the Modality-Specific Encoding module encodes each modality according to its unique characteristics, capturing modality-specific patterns while managing varying context lengths. Finally, the Adaptive Prompt Tuning module fine-tunes the LLM to integrate multimodal embeddings, while an adaptive gating mechanism retains its pretrained knowledge. We validate the effectiveness of the proposed framework on a real-world dataset containing multiple PV plants. Experimental results demonstrate that our approach outperforms existing state-of-the-art methods.

The sparsity of user–item interactions remains a fundamental obstacle in collaborative filtering, limiting the ability of Graph Neural Network (GNN)-based recommender systems to capture high-order user relationships without incurring over-smoothing and computational overhead. Existing social recommendation approaches mitigate this by incorporating social networks, yet most rely on explicit ties and fail to construct informative links in their absence. Meanwhile, contrastive learning (CL) has shown promise in improving representation quality, but current view generation strategies, augmentation-based for robustness and nonaugmentation-based for semantic fidelity, are seldom combined, leaving their complementary potential underexplored. We propose Social Generating with Multiview-guided Tuning (SGMT), a unified framework that addresses both challenges. First, an interest-aware social generation mechanism constructs synthetic user–user links from shared interaction patterns, theoretically shown to compress collaborative paths and uncover latent high-order relations. Second, we present two complementary CL modules, Noise-augmented View and Semantic-explored View, which we theoretically prove to preferentially enhance uniformity and alignment, respectively, two fundamental objectives in CL. Experiments on three real-world datasets show that SGMT outperforms state-of-the-art baselines, validating both the theoretical analysis and the practical efficacy of our model.

Beyond user-item modeling, item-to-item relationships are increasingly used to enhance recommendation. However, common methods largely rely on co-occurrence, making them prone to item popularity bias and user attributes, which degrades embedding quality and performance. Meanwhile, although diversity is acknowledged as a key aspect of recommendation quality, existing research offers limited attention to it, with a notable lack of causal perspectives and theoretical grounding. To address these challenges, we propose Cadence: Diversity Recommendation via Causal Deconfounding of Co-purchase Relations and Counterfactual Exposure—a plug-and-play framework built upon LightGCN as the backbone, primarily designed to enhance recommendation diversity while preserving accuracy. First, we compute the Unbiased Asymmetric Co-purchase Relationship (UACR) between items—excluding item popularity and user attributes—to construct a deconfounded directed item graph, with an aggregation mechanism to refine embeddings. Second, we leverage UACR to identify diverse categories of items that exhibit strong causal relevance to a user's interacted items but have not yet been engaged with. We then simulate their behavior under high-exposure scenarios, thereby significantly enhancing recommendation diversity while preserving relevance. Extensive experiments on real-world datasets demonstrate that our method consistently outperforms state-of-the-art diversity models in both diversity and accuracy, and further validates its effectiveness, transferability, and efficiency over baselines.

Interleaved-Modal Chain-of-Thought (I-MCoT) advances vision-language reasoning, such as Visual Question Answering (VQA).This paradigm integrates specially selected visual evidence from the input image into the context of Vision-Language Models (VLMs), enabling them to ground their reasoning logic in these details.Accordingly, the efficacy of an I-MCoT framework relies on identifying what to see (evidence selection) and when to see it (triggering of insertions).However, existing methods fall short in both aspects.First, for selection, they rely on attention signals, which are unreliable-particularly under severe granularity imbalance between the brief textual query and the informative image.Second, for triggering, they adopt static triggers, which fail to capture the VLMs' dynamic needs for visual evidence.To this end, we propose a novel I-MCoT framework, Active Information-driven Multi-modal Chain-of-Thought (AIM-CoT), which aims to improve both evidence selection and insertion triggering via: (1) Context-enhanced Attention-map Generation (CAG) to mitigate granularity imbalance via textual context enhancement; (2) Active Visual Probing (AVP) to proactively select the most informative evidence via an information foraging process; and (3) Dynamic Attention-shift Trigger (DAT) to precisely activate insertions when VLM's attention shifts from text to visual context.Experiments across three benchmarks and four backbones demonstrate AIM-CoT's consistent superiority.Our code is available at https: //anonymous.4open.science/r/AIMCoT.

The rapid expansion of gaming industry requires advanced recommender systems tailored to its dynamic landscape. Existing Graph Neural Network (GNN)-based methods primarily prioritize accuracy over diversity, overlooking their inherent tradeoff. To address this, we previously proposed CPGRec, a balance-oriented gaming recommender system. However, CPGRec fails to account for critical disparities in player–game interactions, which carry varying significance in reflecting players’ personal preferences and may exacerbate over-smoothness issues inherent in GNN-based models. Moreover, existing approaches underutilize the reasoning capabilities and extensive knowledge of large language models (LLMs) in addressing these limitations. To bridge this gap, we propose two new modules. First, Preference-informed Edge Reweighting (PER) module assigns signed edge weights to qualitatively distinguish significant player interests and disinterests while then quantitatively measuring preference strength to mitigate over-smoothing in graph convolutions. Second, Preference-informed Representation Generation (PRG) module leverages LLMs to generate contextualized descriptions of games and players by reasoning personal preferences from comparing global and personal interests, thereby refining representations of players and games. Experiments on two Steam datasets demonstrate CPGRec+’s superior accuracy and diversity over state-of-the-art models. The code is accessible at https://github.com/HsipingLi/CPGRec-Plus .

Sequential recommendation aims to predict users’ next interactions by analyzing historical behavioral data. Traditional methods typically focus on learning fine-grained feature representations or extracting high-level user preferences to enhance recommendation accuracy. However, they often overlook the dynamic nature of user demand, which can shift over short periods and may resemble random noise. In our previous work, we introduced CoDeR, a framework that captures demand shifts and mitigates confounding biases through backdoor adjustment. Despite its effectiveness, CoDeR has limitations in its causal relation modeling, particularly in neglecting the role of user interest as a confounder. In this work, we propose CoDeR+, an enhanced framework that refines key components of CoDeR. First, we extend the original User Demand Extraction module into Interest-aware User Demand Modeling, introducing two submodules that explicitly model user interest and integrate it into demand representations. Second, we introduce a new Robust Counterfactual Demand Reasoning module, where user interest is treated as an additional confounder alongside demand drift, improving the causal correction process. Additionally, we provide a rigorous theoretical analysis of the updated backdoor adjustment and propose a simplified probability estimation method that reduces computational complexity. Extensive experiments on four real-world datasets demonstrate the effectiveness of CoDeR+. The source code for both CoDeR and CoDeR+ is publicly available at https://github.com/hellolst23/CoDeR .

Graph neural networks (GNNs) have demonstrated significant success in solving real-world problems using both static and dynamic graph data. While static graphs remain constant, dynamic graphs evolve over time, presenting unique challenges that necessitate integrating GNN computations with sequential models. Despite advancements, existing research has primarily focused on static graphs, with dynamic graphs receiving comparatively less attention. This study extends the investigation of over-squashing—a phenomenon where excessive information compression leads to the loss of distant node information—from static to dynamic graphs. Over-squashing is exacerbated in dynamic graphs due to the combined compression of spatial and temporal information into narrow time windows. To address this issue, we propose the spatial and temporal compensation model for dynamic graphs, which is theoretically validated and incorporates two key modules: the structural similarity-based spatial compensation (SSSC) module and the representation and trend similarity-based temporal compensation (RTSTC) module. The former module mitigates spatial information loss by leveraging structural similarities among nodes, while the latter module addresses temporal information loss by integrating historical data and trends. The extensive experiments on real-world dynamic graph datasets demonstrate that our approach achieves state-of-the-art performance. The datasets and source codes are released at:https://github.com/wuchaokai/STCDG/

The garment structure serves as a crucial medium for expressing the designer's creative vision and showcasing the distinctive character of clothing items. Effective editing of garment structure in fashion images allows for an advanced preview of the design, accelerating the process of garment customization to meet individualized requirements. Although large-scale diffusion models have demonstrated impressive image generation and editing capabilities, no efforts have been made to exploit their potential in part-level editing of images. Unlike previous research, we define a clothing structure editing (CSE) task aimed at accurately editing the local structure of human-centered clothing images through simple instruction-based prompts while maintaining the consistency of clothing appearance. Specifically, this paper develops a new controllable triple-flow framework for structure editing named FashionTailor. An additional network called ClothingNet is proposed to extract the clothing details to address the rigid constraints of the original garment structure. Then, we propose a semantic-refined module to extract the semantic understanding of the source image and adaptively focus on the part to be edited. We also design a cross-blend attention mechanism to integrate fine-grained clothing features to guarantee precise alignment between appearance and target structure features. In addition, a garment structure dataset called StructureFashion has been collated, wherein each item of clothing is represented by multiple photos with diverse structure characteristics, containing over six million pairs. Finally, our method supports editing the structure of multiple parts on a garment simultaneously. Extensive experiments validate the effectiveness of our method for editing part-level human images in StructureFashion dataset and real-scenarios.

Sequential recommendation systems aim to predict the next item based on users' historical interactions. While traditional methods focus on learning feature representations or user preferences, they often struggle with detecting subtle demand shifts in short sequences, especially when these shifts are obscured by noise or biases. To address these issues, we propose CoDeR (Counterfactual Demand Reasoning), a novel framework designed to handle demand shifts in sequential recommendations with greater precision. CoDeR features two key modules: (1) the User Demand Extraction module, which utilizes self-attention mechanisms and demand graphs to identify and model demand shifts from minimal user interactions; and (2) the Counterfactual Demand Reasoning module, which employs causal effect analysis and backdoor adjustment techniques to distinguish true demand shifts from noisy or biased signals. Our approach represents the first application of counterfactual reasoning to sequential recommendation systems. Comprehensive experiments on three real-world datasets demonstrate that CoDeR significantly outperforms existing baselines.

Evaluating large language models (LLMs) in diverse and challenging scenarios is essential to align them with human preferences. To mitigate the prohibitive costs associated with human evaluations, utilizing a powerful LLM as a judge has emerged as a favored approach. Nevertheless, this methodology encounters several challenges, including substantial expenses, concerns regarding privacy and security, and reproducibility. In this paper, we propose a straightforward, replicable, and accurate automated evaluation method by leveraging a lightweight LLM as the judge, named RocketEval. Initially, we identify that the performance disparity between lightweight and powerful LLMs in evaluation tasks primarily stems from their ability to conduct comprehensive analyses, which is not easily enhanced through techniques such as chain-of-thought reasoning. By reframing the evaluation task as a multi-faceted Q\&A using an instance-specific checklist, we demonstrate that the limited judgment accuracy of lightweight LLMs is largely attributes to high uncertainty and positional bias. To address these challenges, we introduce an automated evaluation process grounded in checklist grading, which is designed to accommodate a variety of scenarios and questions. This process encompasses the creation of checklists, the grading of these checklists by lightweight LLMs, and the reweighting of checklist items to align with the supervised annotations. Our experiments carried out on the automated evaluation benchmarks, MT-Bench and WildBench datasets, reveal that RocketEval, when using $\textit{Gemma-2-2B}$ as the judge, achieves a high correlation (0.965) with human preferences, which is comparable to $\textit{GPT-4o}$. Moreover, RocketEval provides a cost reduction exceeding 50-fold for large-scale evaluation and comparison scenarios. Our code is available at https://github.com/Joinn99/RocketEval-ICLR.

Multimodal Large Language Models have advanced AI in applications like text-to-video generation and visual question answering. These models rely on visual encoders to convert non-text data into vectors, but current encoders either lack semantic alignment or overlook non-salient objects. We propose the Guiding Visual Encoder to Perceive Overlooked Information (GiVE) approach. GiVE enhances visual representation with an Attention-Guided Adapter (AG-Adapter) module and an Object-focused Visual Semantic Learning module. These incorporate three novel loss terms: Object-focused Image-Text Contrast (OITC) loss, Object-focused Image-Image Contrast (OIIC) loss, and Object-focused Image Discrimination (OID) loss, improving object consideration, retrieval accuracy, and comprehensiveness. Our contributions include dynamic visual focus adjustment, novel loss functions to enhance object retrieval, and the Multi-Object Instruction (MOInst) dataset. Experiments show our approach achieves state-of-the-art performance.

The explosive growth of the video game industry has created an urgent need for recommendation systems that can scale with expanding catalogs and maintain user engagement. While prior work has explored accuracy and diversity in recommendations, existing models underutilize playtime, a rich behavioral signal unique to gaming platforms, and overlook the potential of multimodal information to enhance diversity. In this paper, we propose DP 2 Rec, a novel Dual-Phase Playtime-guided Recommendation model designed to jointly optimize accuracy and diversity. First, we introduce a playtime-guided interest intensity exploration module that separates strong and weak preferences via dual-beta modeling, enabling fine-grained user profiling and more accurate recommendations. Second, we present a playtime-guided multimodal random walks module that simulates player exploration using transitions guided by both playtime-derived interest similarity and multimodal semantic similarity. This mechanism preserves core preferences while promoting cross-category discovery through latent semantic associations and adaptive category balancing. Extensive experiments on a real-world game dataset show that DP 2 Rec outperforms existing methods in both recommendation accuracy and diversity. The dataset and source code are released at https://github.com/zqxwcevrtyui/DP2Rec

The evolution of individuals' living standards has transformed clothing preferences, elevating fashion beyond mere utility to a potent means of self-expression. However, the intricate task of outfit selection persists as a challenge, marked by traditional methods facing challenges such as the oversight of combined factors of scene and body shape, insufficient emphasis on detail-oriented matching, and overreliance on rigid hierarchical structures. To tackle these challenges, this article introduces a novel model, termedGlobal-Local matching network towardsOutfit recommendation for diverse bodyShapes andScenes (GLOSS). Specifically, we first introduce a newly compiled fashion dataset, StreetFashion, to capture the combined factors of body shapes and scene characteristics. Additionally, we develop innovative multi-level globality- and locality-aware matching methods to enhance the accuracy of outfit recommendations by comprehensively considering both global and local relationships among clothing items, outfits, users, and scenes. Furthermore, we develop a personalized outfit heterogeneous graph that incorporates historical interactions among fashion entities, enabling effective modeling of nonstrict hierarchical relationships. Evaluation conducted on both our collected dataset and an adapted existing dataset demonstrates the effectiveness of our proposed approach in outfit recommendation. Our codes are released at:https://github.com/ChenrMa/GLOSS.

Recommender systems are essential in the ever-evolving landscape of e-commerce and social media platforms, delivering personalized recommendations by predicting user preferences. However, the growing need for explainable recommendation has arisen to enhance transparency and persuasiveness. In response, we present correlation-driven explainable recommendation with aspect and rating boosted representation learning (CER-ARRL), a unified joint-ranking framework that capitalizes on the robust capabilities of neural collaborative filtering to model the intricate dynamics among users, items, and explanations. By extracting information from explicit and implicit user emotional reviews, our framework enriches the representations of users and items. This integration yields simultaneous improvements in both item recommendation and explanation ranking tasks. In addition, CER-ARRL effectively exploits the structural correlation between phrases as well as the structural and semantic correlations between emojis to facilitate explanation ranking. This work represents the pioneering work to address the item-explanation joint recommendation task by integrating both interpretative phrases and illustrative emojis. Through extensive experiments on various datasets, including our collected dataset, we demonstrate the superiority of the proposed method over existing baselines.

Collocated clothing synthesis (CCS) has emerged as a pivotal topic in fashion technology, primarily concerned with the generation of a clothing item that harmoniously matches a given item. However, previous investigations have relied on using paired outfits, such as a pair of matching upper and lower clothing, to train a generative model for achieving this task. This reliance on the expertise of fashion professionals in the construction of such paired outfits has engendered a laborious and time-intensive process. In this paper, we introduce a new self-driven framework, named style- and texture-guided generative network (ST-Net), to synthesize collocated clothing without the necessity for paired outfits, leveraging self-supervised learning. ST-Net is designed to extrapolate fashion compatibility rules from the style and texture attributes of clothing, using a generative adversarial network. To facilitate the training and evaluation of our model, we have constructed a large-scale dataset specifically tailored for unsupervised CCS. Extensive experiments substantiate that our proposed method outperforms the state-of-the-art baselines in terms of both visual authenticity and fashion compatibility.

Long-term time series forecasting (LTSF) aims to predict future values for a long time based on historical data. The period term is an essential component of the time series, which is complex yet important for LTSF. Although existing studies have achieved promising results, they still have limitations in modeling dynamic complicated periods. Most studies only focus on static periods with fixed time steps, while very few studies attempt to capture dynamic periods in the time domain. In this paper, we dissect the original time series in time and frequency domains and empirically find that changes in periods are more easily captured and quantified in the frequency domain. Based on this observation, we propose to explore dynamic period features using rotation in the frequency domain. To this end, we develop the frequency-based rotation network (FRNet), a novel LTSF method to effectively capture the features of the dynamic complicated periods. FRNet decomposes the original time series into period and trend components. Based on the complex-valued linear networks, it leverages a period frequency rotation module to predict the period component and a patch frequency rotation module to predict the trend component, respectively. Extensive experiments on seven real-world datasets consistently demonstrate the superiority of FRNet over various state-of-the-art methods. The source code is available at https://github.com/SiriZhang45/FRNet.

In recent years, the video game industry has experienced substantial growth, presenting players with a vast array of game choices. This surge in options has spurred the need for a specialized recommender system tailored for video games. However, current video game recommendation approaches tend to prioritize accuracy over diversity, potentially leading to unvaried game suggestions. In addition, the existing game recommendation methods commonly lack the ability to establish strict connections between games to enhance accuracy. Furthermore, many existing diversity-focused methods fail to leverage crucial item information, such as item category and popularity during neighbor modeling and message propagation. To address these challenges, we introduce a novel framework, called CPGRec, comprising three modules, namely accuracy-driven, diversity-driven, and comprehensive modules. The first module extends the state-of-the-art accuracy-focused game recommendation method by connecting games in a more stringent manner to enhance recommendation accuracy. The second module connects neighbors with diverse categories within the proposed game graph and harnesses the advantages of popular game nodes to amplify the influence of long-tail games within the player-game bipartite graph, thereby enriching recommendation diversity. The third module combines the above two modules and employs a new negative-sample rating score reweighting method to balance accuracy and diversity. Experimental results on the Steam dataset demonstrate the effectiveness of our proposed method in improving game recommendations. The dataset and source codes are anonymously released at: https://github.com/CPGRec2024/CPGRec.git.

Collocated clothing synthesis using generative networks has become an emerging topic in the field of fashion intelligence, as it has significant potential economic value to increase revenue in the fashion industry. In previous studies, several works have attempted to synthesize visually-collocated clothing based on a given clothing item using generative adversarial networks (GANs) with promising results. These works, however, can only accomplish the synthesis of one collocated clothing item each time. Nevertheless, users may require different clothing items to meet their multiple choices due to their personal tastes and different dressing scenarios. To address this limitation, we introduce a novel batch clothing generation framework, named BC-GAN, which is able to synthesize multiple visually-collocated clothing images simultaneously. In particular, to further improve the fashion compatibility of synthetic results, BC-GAN proposes a new fashion compatibility discriminator in a contrastive learning perspective by fully exploiting the collocation relationship among all clothing items. Our model was examined in a large-scale dataset with compatible outfits constructed by ourselves. Extensive experiment results confirmed the effectiveness of our proposed BC-GAN in comparison to state-of-the-art methods in terms of diversity, visual authenticity, and fashion compatibility.

Fashion recommendation has become a prominent focus in the realm of online shopping, with various tasks being explored to enhance the customer experience. Recent research has particularly emphasized fashion recommendation based on body shapes, yet a critical aspect of incorporating multimodal data relevance has been overlooked. In this paper, we present the Contrastive Multimodal Cross-Attention Network, a novel approach specifically designed for fashion recommendation catering to diverse body shapes. By incorporating multimodal representation learning and leveraging contrastive learning techniques, our method effectively captures both inter- and intra-sample relationships, resulting in improved accuracy in fashion recommendations tailored to individual body types. Additionally, we propose a locality-aware cross-attention module to align and understand the local preferences between body shapes and clothing items, thus enhancing the matching process. Experimental results conducted on a diverse dataset demonstrate the state-of-the-art performance achieved by our approach, reinforcing its potential to significantly enhance the personalized online shopping experience for consumers with varying body shapes and preferences.

Collaborative filtering (CF) has been extensively studied in recommendation, spawning various solutions. While graph convolution networks (GCNs) are effective at representation learning, their efficiency is lacking. Comparatively, item similarity model efficiently establishes direct relationships between items. In spite of this, the modeling problem grows quadratically as the number of items increases. This poses critical scalability issues. In this paper, through an investigation of the latest GCN model, we reveal the feasibility of optimizing the process of similarity modeling using the underlying group structure in the item set. Based on these findings, we propose a novel model which introduces graph partitioning to reduce the scale of similarity modeling problem, dubbed FPSR+. Specifically, we divide similarity modeling of items into sub-problems within each partition, and incorporate global and local prior knowledge to alleviate information loss. Following an analysis of the properties of different items in partitioning, we propose a new hub set selection strategy that improves the robustness of FPSR+ in the small partition case. Extensive experiments on four real-world datasets demonstrate the superior performance of FPSR+ compared with state-of-the-art GCN models and item similarity models, as well as several-fold speedups and reductions in parameter storage.

In this article, we propose a new cross locality relation network (CLRNet) to generate high-quality crowd density maps for crowd counting in videos. Specifically, a cross locality relation module (CLRM) is proposed to enhance feature representations by modeling local dependencies of pixels between adjacent frames with an adapted local self-attention mechanism. First, different from the existing methods which measure similarity between pixels by dot product, a new adaptive cosine similarity is advanced to measure the relationship between two positions. Second, the traditional self-attention modules usually integrate the reconstructed features with the same weights for all the positions. However, crowd movement and background changes in a video sequence are uneven in real-life applications. As a consequence, it is inappropriate to treat all the positions in reconstructed features equally. To address this issue, a scene consistency attention map (SCAM) is developed to make CLRM pay more attention to the positions with strong correlations in adjacent frames. Furthermore, CLRM is incorporated into the network in a coarse-to-fine way to further enhance the representational capability of features. Experimental results demonstrate the effectiveness of our proposed CLRNet in comparison to the state-of-the-art methods on four public video datasets. The codes are available at: https://github.com/Amelie01/CLRNet.

The large amount of data available in the modern big data era opens new opportunities to expand our knowledge by integrating information from heterogeneous sources. Multiview learning has recently achieved tremendous success in deriving complementary information from multiple data modalities. This article proposes a framework called multiview latent space projection (MVLSP) to integrate features extracted from multiple sources in a discriminative way to facilitate binary and multiclass classifications. Our approach is associated with three innovations. First, most existing multiview learning algorithms promote pairwise consistency between two views and do not have a natural extension to applications with more than two views. MVLSP finds optimum mappings from a common latent space to match the feature space in each of the views. As the matching is performed on a view-by-view basis, the framework can be readily extended to multiview applications. Second, feature selection in the common latent space can be readily achieved by adding a class view, which matches the latent space representations of training samples with their corresponding labels. Then, high-order view correlations are extracted by considering feature-label correlations. Third, a technique is proposed to optimize the integration of different latent patterns based on their correlations. The experimental results on the prostate image dataset demonstrate the effectiveness of the proposed method.

Synthesizing realistic images of fashion items which are compatible with given clothing images, as well as conditioning on multiple modalities, brings novel and exciting applications together with enormous economic potential. In this work, we propose a multi-modal collocation framework based on generative adversarial network (GAN) for synthesizing compatible clothing images. Given an input clothing item that consists of an image and a text description, our model works on synthesizing a clothing image which is compatible with the input clothing, as well as being guided by a given text description from the target domain. Specifically, a generator aims to synthesize realistic and collocated clothing images relying on image- and text-based latent representations learned from the source domain. An auxiliary text representation from the target domain is added for supervising the generation results. In addition, a multi-discriminator framework is carried out to determine compatibility between the generated clothing images and the input clothing images, as well as visual-semantic matching between the generated clothing images and the targeted textual information. Extensive quantitative and qualitative results demonstrate that our model substantially outperforms state-of-the-art methods in terms of authenticity, diversity, and visual-semantic similarity between image and text.

The fusion of multiview data sets, in which features of each sample are categorized into distinct groups, is increasingly important in the big data era. Successful multiview learning approaches have mechanisms to enforce consensus and/or complementarity among views. This article introduces a framework called the consensus and complementarity-based multiview latent space projection (MVLSP-2C) that enforces both principles simultaneously. Consensus is established by extracting and representing information shared by all views in a shared latent space, whereas complementarity among views is achieved by the representation in view-specific spaces. As the diversity of the multiview feature representation benefits classification performance, MVLSP-2C minimizes the similarity between the shared and view-specific representations, thereby improving diversity. The driving principle of MVLSP-2C is that the latent space representation is obtained by optimally projecting it to match the original feature space representation on a view-by-view basis. Unlike pairwise consensus methods that enforce consistency between two views, matching on a view-by-view basis allows extensions to settings with more than two views. A related and important advantage of this per-view matching design is that a class view can be readily incorporated to learn a supervised representation that facilitates subsequent classification. As the class view is added without an assumption on the exclusivity of classes, MVLSP-2C is equally applicable to multiclass single-label and multilabel classifications. MVLSP-2C further optimizes the integration of latent variables based on their correlation. Extensive experiments in multiclass and multiview image datasets show that MVLSP-2C produces more accurate classification results as compared to state-of-the-art methods.

Outfit generation is a challenging task in the field of fashion technology, in which the aim is to create a collocated set of fashion items that complement a given set of items. Previous studies in this area have been limited to generating a unique set of fashion items based on a given set of items, without providing additional options to users. This lack of a diverse range of choices necessitates the development of a more versatile framework. However, when the task of generating collocated and diversified outfits is approached with multimodal image-to-image translation methods, it poses a challenging problem in terms of non-aligned image translation, which is hard to address with existing methods. In this research, we present FCBoost-Net, a new framework for outfit generation that leverages the power of pre-trained generative models to produce multiple collocated and diversified outfits. Initially, FCBoost-Net randomly synthesizes multiple sets of fashion items, and the compatibility of the synthesized sets is then improved in several rounds using a novel fashion compatibility booster. This approach was inspired by boosting algorithms and allows the performance to be gradually improved in multiple steps. Empirical evidence indicates that the proposed strategy can improve the fashion compatibility of randomly synthesized fashion items as well as maintain their diversity. Extensive experiments confirm the effectiveness of our proposed framework with respect to visual authenticity, diversity, and fashion compatibility.

In collaborative filtering, distance metric learning has been applied to matrix factorization techniques with promising results. However, matrix factorization lacks the ability of capturing collaborative information, which has been remarked by recent works and improved by interpreting user interactions as signals. This paper aims to find out how metric learning connect to these signal-based models. By adopting a generalized distance metric, we discovered that in signal-based models, it is easier to estimate the residual of distances, which refers to the difference between the distances from a user to a target item and another item, rather than estimating the distances themselves. Further analysis also uncovers a link between the normalization strength of interaction signals and the novelty of recommendation, which has been overlooked by existing studies. Based on the above findings, we propose a novel model to learn a generalized distance user-item distance metric to capture user preference in interaction signals by modeling the residuals of distance. The proposed CoRML model is then further improved in training efficiency by a newly introduced approximated ranking weight. Extensive experiments conducted on 4 public datasets demonstrate the superior performance of CoRML compared to the state-of-the-art baselines in collaborative filtering, along with high efficiency and the ability of providing novelty-promoted recommendations, shedding new light on the study of metric learning-based recommender systems.

Collaborative filtering (CF) is widely searched in recommendation with various types of solutions. Recent success of Graph Convolution Networks (GCN) in CF demonstrates the effectiveness of modeling high-order relationships through graphs, while repetitive graph convolution and iterative batch optimization limit their efficiency. Instead, item similarity models attempt to construct direct relationships through efficient interaction encoding. Despite their great performance, the growing item numbers result in quadratic growth in similarity modeling process, posing critical scalability problems. In this paper, we investigate the graph sampling strategy adopted in latest GCN model for efficiency improving, and identify the potential item group structure in the sampled graph. Based on this, we propose a novel item similarity model which introduces graph partitioning to restrict the item similarity modeling within each partition. Specifically, we show that the spectral information of the original graph is well in preserving global-level information. Then, it is added to fine-tune local item similarities with a new data augmentation strategy acted as partition-aware prior knowledge, jointly to cope with the information loss brought by partitioning. Experiments carried out on 4 datasets show that the proposed model outperforms state-of-the-art GCN models with 10x speed-up and item similarity models with 95% parameter storage savings.

Automatically accomplishing intelligent fashion design with certain ‘inspiration’ images can greatly facilitate a designer’s design process, as well as allow users to interactively participate in the process. In this research, we propose a generative adversarial network with heatmap-guided semantic disentanglement (HSD-GAN) to perform an ‘intelligent’ design with ‘inspiration’ transfer. Our model aims to learn how to integrate the feature representations, from the styles of both source fashion items and target fashion items, in an unsupervised manner. Specifically, a semantic disentanglement attention-based encoder is proposed to capture the most discriminative regions of different input fashion items and disentangle the features into two key factors: attribute and texture. A generator is then developed to synthesize mixed-style fashion items by utilizing the two factors. In addition, a heatmap-based patch loss is introduced to evaluate the visual-semantic matching degree between the texture of the generated fashion items and the input texture information. Extensive experimental results show that our proposed HSD-GAN consistently achieves superior performance, compared to other state-of-the-art methods.

How to recommend outfits has gained considerable attention in both academia and industry in recent years. Many studies have been carried out regarding fashion compatibility learning, to determine whether the fashion items in an outfit are compatible or not. These methods mainly focus on evaluating the compatibility of existing outfits and rarely consider applying such knowledge to ‘design’ new fashion items. We propose the new task of generating complementary and compatible fashion items based on an arbitrary number of given fashion items. In particular, given some fashion items that can make up an outfit, the aim of this paper is to synthesize photo-realistic images of other, complementary, fashion items that are compatible with the given ones. To achieve this, we propose an outfit generation framework, referred to as COutfitGAN, which includes a pyramid style extractor, an outfit generator, a UNet-based real/fake discriminator, and a collocation discriminator. To train and evaluate this framework, we collected a large-scale fashion outfit dataset with over 200 K outfits and 800 K fashion items from the Internet. Extensive experiments show that COutfitGAN outperforms other baselines in terms of similarity, authenticity, and compatibility measurements.

The rapid development of Internet services and social platforms encourages users to share their opinions. To help users give valuable comments, content providers expect the recommender system to offer appropriate suggestions, including specific features of the item described in texts and emojis, which are all considered aspects of the user reviews. Hence, the review aspect recommendation task has become significant, where the key lies in handling personal preferences and semantic correlations between suggested items. This article proposes a correlation-aware review aspect recommender (CARAR) system model by constructing self-representation correlations between different views of review aspects, including textual aspects and emojis to make a personalized recommendation. The dependencies between different textual aspects and emojis can be identified and utilized to facilitate the factorization process to learn user and item latent factors. The cross-view correlation mapping between textual aspects and emojis can be built to enhance the recommendation performance. Moreover, the additional information in the real-world environment is also applied to our model to adjust the recommendation results. We constructed experiments on five self-collected and public datasets and compared with six existing models. The results show that our model can outperform the existing models on review aspects recommendation tasks, validating the effectiveness of our approach.

Texture and shape in fashion, constituting essential elements of garments, characterize the body and surface of the fabric and outline the silhouette of clothing, respectively. The selection of texture and shape plays a critical role in the design process, as they largely determine the success of a new design for fashion items. In this research, we propose a texture and shape disentangled generative adversarial network (TSD-GAN) to perform “intelligent” design with the transformation of texture and shape in fashion items. Our TSD-GAN aims to learn how to disentangle the features of texture and shape of different fashion items in an unsupervised manner. Specifically, a fashion attribute encoder is developed to decompose the input fashion items into independent representations of texture and shape. Then, to learn the coarse or fine styles hidden in the features of texture and shape, a texture mapping network and a shape mapping network are proposed to disentangle the features into different hierarchical representations. The different hierarchical representations of texture and shape are then fed into a multi-factor-based generator to generate mixed-style fashion items. In addition, a multi-discriminator framework is developed to distinguish the authenticity and texture similarity between the generated images and the real images. Experimental results on different fashion categories demonstrate that our proposed TSD-GAN may be useful for assisting designers to accomplish the design process by transforming the texture and shape of fashion items.

Multioutput learning targeting predicting multiple outputs for each input has attracted increasing attention due to its ability to handle diverse data types in outputs. Most feature extraction-based methods for tackling multioutput problems neglect the local correlation between different outputs, while most sample extraction-based methods overlook the gap between inputs and outputs. To overcome these two major limitations, in this article, we propose a topic-aware method where we assume inputs and outputs can be jointly embedded in a topic space. Both feature and sample extraction are performed in a latent topic space that encodes output correlation at a topic level and aligns inputs and outputs in an explainable manner. Different from current topic models, we extract independent and interdependent topics based on informative topics. These two components are verified as useful in performance improvement in an ablation study. The proposed method can also be easily extended and applied in multiview learning. The experimental results of the proposed topic-aware model on multiple benchmarks for different multioutput tasks in single-/multi-views with$p$-values less than 0.05 indicate that the improvement achieved by the proposed method over compared baselines is statistically significant.

Multilabel learning, which handles instances associated with multiple labels, has attracted much attention in recent years. Many extant multilabel feature selection methods target global feature selection, which means feature selection weights for each label are shared by all instances. Also, many extant multilabel classification methods exploit global label selection, which means labels correlations are shared by all instances. In real-world objects, however, different subsets of instances may share different feature selection weights and different label correlations. In this article, we propose a novel framework with local feature selection and local label correlation, where we assume instances can be clustered into different groups, and the feature selection weights and label correlations can only be shared by instances in the same group. The proposed framework includes a group-specific feature selection process and a label-specific group selection process. The former process projects instances into different groups by extracting the instance-group correlation. The latter process selects labels for each instance based on its related groups by extracting the group-label correlation. In addition, we also exploit the intergroup correlation. These three kinds of group-based correlations are combined to perform effective multilabel classification. The experimental results on various datasets validate the effectiveness of our approach.

Multilabel learning focuses on assigning instances with different labels. In essence, the multilabel learning aims at learning a predictive function from feature space to a label space. The predictive function learning procedure can be regarded as a feature selection procedure and as a classifier construction procedure. For feature selection, we extract features for each label based on the learned positive and negative feature-label correlations. The positive and negative relationships can illustrate which labels can and cannot be well presented by the corresponding features, respectively, due to the semantic gap. For classifier construction, we perform sample-specific and label-specific classifications. The interlabel and interinstance correlations are combined in these two kinds of classifications. These two correlations are learned from both input features and output labels when the output labels are too sparse to reveal the informative correlation. However, there exists the semantic gap when combining input and output spaces to mine the labelwise relationship. The semantic gap can be bridged by the learned feature-label correlation. Finally, extensive experimental results on several benchmarks under four domains are presented to show the effectiveness of the proposed framework.

Multilabel learning has been extensively studied in the past years, as it has many applications in different domains. It aims at annotating the labels for unseen data according to training data, which are often high dimensional in both instance and feature levels. The training data often have noisy and redundant information on these two levels. As an effective data preprocessing step, instance and feature selection should both be performed to find relevant training instances for each testing instance and relevant features for each label, respectively. However, most of the existing methods overlook the input-output correlation in each kind of selection. It will lead to the performance degradation. This article presents a formulation for multilabel learning from a topic view that exploits the dependence between features and labels in a topic space. We can perform effective instance and feature selection in the latent topic space, as the relationship between the input and output spaces is well captured in this space. The results from intensive experiments on various benchmarks demonstrate the effectiveness of the proposed framework.

Multilabel classification deals with instances assigned with multiple labels simultaneously. It focuses on learning a mapping from feature space to label a space for out-of-sample extrapolation. The mapping can be seen as a feature selection process in the feature domain or as a classifier training process in the classifier domain. The existing methods do not effectively learn the mapping when combining these two domains together. In this article, we derive a mechanism to extract label-specific features in local and global levels. We also derive a mechanism to train label-specific classifiers in individual and joint levels. Extracting features globally and training classifiers jointly can be seen as a dual process of learning the mapping function on two domains in a coarse-tuned way, while extracting features locally and training classifiers individually can be seen as a dual process of learning the mapping function on two domains in a fine-tuned way. The two-level feature selection and the two-level classifier training are derived to make the entire mapping learning process robust. Finally, extensive experimental results on several benchmarks under four domains are presented to demonstrate the effectiveness of the proposed approach.

In multilabel learning (MLL), each instance can be assigned by several concepts simultaneously from a class dictionary. Usually, labels in the class dictionary have semantic correlations and semantic hierarchy. Instances can be categorized into different topics. Each topic has its own label candidates, and some topics have overlapped label candidates. In this paper, we propose a novel MLL method to deal with missing labels. The proposed algorithm can recover the label matrix according to local, topic-wise, and global semantic properties. Specifically, in the global level, label consistency, label-wise semantic correlations, and semantic hierarchy are exploited; in the local level, label importance and instance-wise semantic correlations in each topic are extracted; and in the topic level, label importance similarities and instance-wise semantic similarities between topics are mined. The experimental results on five image data sets in different applications demonstrate the effectiveness of the proposed approach.

Object-based change detection (CD) is an effective method of identifying detailed changes in land features by contrastively observing the same areas of high-resolution remote sensing images at different times. Binarization is the important step in partitioning changed and unchanged classes in the unsupervised domain. We formulate a novel binarization technique based on the Weibull mixture model, where generated similarity measure images are modeled using a mixture of nonnormal Weibull distributions. The parameters in the model are further globally estimated by employing a genetic algorithm. Two data sets with high-resolution remote sensing images are used to evaluate the effectiveness of the proposed method. Experimental results demonstrate that the method allows better and more robust unsupervised object-based CD than do state-of-the-art threshold-based and clustering-based methods. Advantages of the proposed method are embodied in the modeling of relatively few data of the changed class with a skewed and long tail distribution.

Multi-label classification is a vital problem, as it has numerous applications in computer vision, such as automatic image annotation. The label set for each instance is always assumed to be in the original whole form. However, missing labels often occur because manual labelling is a time-consuming and label-intensive work in the case of large amount of data. The incompleteness of labels can certainly increase the difficulty of training the multi-label model. In this paper, a novel multi-label classification method is proposed that can learn the inductive classifier while explicitly dealing with missing labels. An individual sparsity inducing l1-norm is employed to capture the sparse label interdependencies. A group sparsity inducing l2,1-norm is utilized to select the discriminative input features. The semantic label hierarchy is included to diversify the label dependency. Meanwhile, the consistency between the predicted labels and the original labels as well as the regularization of smoothness on the predicted labels are also enforced to improve the classification performance. Furthermore, an efficient method based on the alternating direction method of multipliers is designed to facilitate classifier and label correlation learning process. Experiments on two widely used large-scale image datasets demonstrate that the efficacy of the proposed method on multi-label classification when only a limited number of labels are given for each training sample.