Detecting rumors on social media is challenging when posts are semantically underspecified and discussion threads are noisy or polarized, which can encourage detectors to exploit spurious correlations. We propose CLEAR (Contextual Potential Alignment Capture Network), an evidence-grounded framework that models hierarchical comment dynamics and incorporates auxiliary LLM-based veracity assessments for credibility-aware prediction. CLEAR couples prototype-conditioned flow purification with Dirichlet evidential learning to derive geometry-grounded evidence for calibrated inference. We further introduce an entropy-adaptive Hard-Shift reweighting strategy to suppress noise-driven shortcuts. Experiments on Weibo-19 (2927 samples) and PHEME (2018 samples) show that CLEAR achieves 93.16% and 91.56% accuracy, outperforming the average strong recent baselines by 3.2 and 5.5 percentage points, respectively. To stress-test generalization under distribution shift, we curate VRDD with 4020 posts (2348 non-rumors and 1672 rumors), a boundary-dense benchmark that emphasizes vague content. Results confirm CLEAR’s robustness to evolving rumor patterns and highlight the curriculum-dependent effect of reweighting.

In large-scale Point-of-Interest (POI) recommendation, the conflict between accuracy and computational efficiency intensifies as POI catalogs grow. Traditional deep models struggle to balance quality with efficiency. To address this challenge, we propose a knowledge-distilled product quantization framework EffiPOI for efficient POI recommendation. EffiPOI jointly optimizes accuracy and efficiency by integrating product quantization with multi-modal knowledge distillation. Specifically, we first construct service-oriented multi-modal POI representations, which comprehensively capture each POI’s spatial coverage, temporal activity patterns, and semantic attributes. Based on these representations, we design a teacher-student distillation paradigm. The teacher model adopts a Mixture-of-Experts architecture to generate discriminative and semantically expressive POI representations, which serve as high-quality supervision signals for guiding the student model through knowledge distillation. The student model leverages product quantization to encode POIs into compact and computation-friendly representations, achieving a favorable tradeoff between representational compactness and predictive accuracy. To alleviate the performance degradation due to quantization, we develop a hybrid knowledge distillation strategy that transfers both response-aware and feature-aware knowledge from the teacher model to the student model. Experimental results on three real-world datasets show that the proposed method achieves 4.6%–12.1% improvements in accuracy and over 10× speedup in inference efficiency, outperforming existing POI recommendation models. Code is available at: https://github.com/pcm1217/EffiPOI .

Providing sequential recommendations along with easily comprehensible natural language explanations can significantly enhance users’ trust in the recommender systems. However, this approach presents two key challenges: (1) The different objectives of the two tasks make it challenging to achieve joint optimization and mutual enhancement. (2) The simultaneous generation of accurate sequential recommendations and high-quality natural language explanations presents serious challenges to the model’s time and space efficiency. To address these challenges, we propose a general and efficient multi-task self-prompt framework for explainable sequential recommendation (ARTS), which improves collaboration performance and time and space efficiency of multi-task modules based on the generated personalized semantic prompts. Specifically, we propose a self-prompt generator that transfers the user’s global behavior features into the continuous prompt, achieving efficient information sharing among multi-task modules. Additionally, we design a personalized prompt-based short sequence inputs strategy under the pre-training and prompt-tuning paradigm, which achieves mutual enhancement among the multi-task modules and significantly improves the model’s time and space efficiency. Extensive experiments have verified that the proposed ARTS outperforms the state-of-the-art methods in both sequential recommendation and explanation generation tasks. The generality, efficiency and effectiveness of each module of the framework have also been validated through various experiments 1 .

The abundance of heavy data on social media enables users to share opinions freely, leading to the rapid spread of misleading content. However, existing fake news detection methods exaggerate the influence of public opinions, making it challenging to combat misinformation since its early spreading state. To tackle this issue, we propose a novel fake news detection framework through news semantic environment perception (NSEP) to identify fake news content. The NSEP framework consists of three major steps. First, NSEP divides the news semantic environment with time-constrained intervals into macro and micro semantic environments using an in-depth distinguisher module. Second, graph convolutional networks are applied to perceive the semantic inconsistencies between intrinsic news content and extrinsic post tokens in the macro semantic environment. Third, a micro semantic detection module guided by multihead attention and sparse attention is utilized to capture the semantic contradictions between news content and posts in the micro semantic environment, providing explicit evidence for determining the authenticity of fake news candidates. Empirical experiments conducted on real-world Chinese and English datasets show that the NSEP framework on Chinese datasets achieved as high as 86.8% accuracy, performing at most 14.1% higher accuracy than that of other state-of-the-art baseline methods and confirming that detecting news content through both micro and macro semantic environments is an effective methodology for alleviating early propagation of fake news. The findings also comprehensively indicate that both news items and posts are critical for the early debunking of fake news and in theories concerning information science.

Incomplete multi-view clustering has represented a significant role in grouping real images. In this study, a novel robust tensor subspace learning (RTSL) is proposed for incomplete multi-view clustering. Specifically, the missing samples within views are first recovered by matrix factorization. The recovered information is utilized for latent representations learning. And then, the obtained latent representations are organized from all views into a third-order tensor and the intrinsic sample relations are captured with tensor linear representation. Moreover, a low-rank sample coefficient tensor is sought to capture high-order connections among views by imposing the tensor nuclear norm. Compared with traditional learning paradigms in the vector space, the sample relations within each view as well as across views could be preserved with the aid of robust tensor subspace learning. As a result, our model can simultaneously handle the missing samples and exploit the intrinsic correlations, leading to enhanced representation capability and better quality of the recovered data. We design an efficient iterative optimization strategy to solve the proposed method. Experimental results on eight datasets show that our model outperforms other competing approaches.

Multimodal fake news detection methods based on semantic information have achieved great success. However, these methods only exploit the deep features of multimodal information, which leads to a large loss of valid information at the shallow level. To address this problem, we propose a progressive fusion network (MPFN) for multimodal disinformation detection, which captures the representational information of each modality at different levels and achieves fusion between modalities at the same level and at different levels by means of a mixer to establish a strong connection between the modalities. Specifically, we use a transformer structure, which is effective in computer vision tasks, as a visual feature extractor to gradually sample features at different levels and combine features obtained from a text feature extractor and image frequency domain information at different levels for fine-grained modeling. In addition, we design a feature fusion approach to better establish connections between modalities, which can further improve the performance and thus surpass other network structures in the literature. We conducted extensive experiments on two real datasets, Weibo and Twitter, where our method achieved 83.3% accuracy on the Twitter dataset, which has increased by at least 4.3% compared to other state-of-the-art methods. This demonstrates the effectiveness of MPFN for identifying fake news, and the method reaches a relatively advanced level by combining different levels of information from each modality and a powerful modality fusion method.

Hashing is an effective technique to improve the efficiency of large-scale recommender system by representing both users and items into binary codes. However, existing hashing-based recommendation methods still suffer from two important problems: 1) Cold-start. They employ the user-item interactions and single auxiliary information to learn the binary hash codes. But the full interaction history is not always available and the single auxiliary information may be missing. 2) Efficient optimization. They learn the hash codes with two-step relaxed optimization or one-step discrete hash optimization based on the cyclic coordinate descent, which results in significant quantization loss or still consumes considerable computation time. In this paper, we propose a Multi-modal Discrete Collaborative Filtering (MDCF) for efficient cold-start recommendation. We map the multi-modal features of users and items to a consensus Hamming space based on the matrix factorization framework. Specifically, a low-rank self-weighted multi-modal fusion module is designed to adaptively fuse the multi-modal features into binary hash codes. Additionally, to support large-scale recommendation, a fast discrete optimization method based on augmented Lagrangian multiplier is developed to directly compute the binary hash codes with simple operations. Experiments show the superior performance of the proposed method over state-of-the-art baselines.

Multi-modal hashing supports efficient multimedia retrieval well. However, existing methods still suffer from two problems: (1) Fixed multi-modal fusion. They collaborate the multi-modal features with fixed weights for hash learning, which cannot adaptively capture the variations of online streaming multimedia contents. (2) Binary optimization challenge. To generate binary hash codes, existing methods adopt either two-step relaxed optimization that causes significant quantization errors or direct discrete optimization that consumes considerable computation and storage cost. To address these problems, we first propose a Supervised Multi-modal Hashing with Online Query-adaption method. A self-weighted fusion strategy is designed to adaptively preserve the multi-modal features into hash codes by exploiting their complementarity. Besides, the hash codes are efficiently learned with the supervision of pair-wise semantic labels to enhance their discriminative capability while avoiding the challenging symmetric similarity matrix factorization. Further, we propose an efficient Unsupervised Multi-modal Hashing with Online Query-adaption method with an adaptive multi-modal quantization strategy. The hash codes are directly learned without the reliance on the specific objective formulations. Finally, in both methods, we design a parameter-free online hashing module to adaptively capture query variations at the online retrieval stage. Experiments validate the superiority of our proposed methods.

Most existing methods focus on improving the clarity and semantic consistency of the image with a given text, but do not pay attention to the multiple control of generated image content, such as the position of the object in generated image. In this paper, we introduce a novel position-based generative network (PBNet) which can generate fine-grained images with the object at the specified location. PBNet combines iterative structure with generative adversarial network (GAN). A location information embedding module (LIEM) is proposed to combine the location information extracted from the boundary block image with the semantic information extracted from the text. In addition, a silhouette generation module (SGM) is proposed to train the generator to generate object based on location information. The experimental results on CUB dataset demonstrate that PBNet effectively controls the location of the object in the generated image.

The flourishing of social media platforms requires techniques for understanding the content of media on a large scale. However, state-of-the art video event understanding approaches remain very limited in terms of their ability to deal with data sparsity, semantically unrepresentative event names, and lack of coherence between visual and textual concepts. Accordingly, in this paper, we propose a method of grounding visual concepts for large-scale Multimedia Event Detection (MED) and Multimedia Event Captioning (MEC) in zero-shot setting. More specifically, our framework composes the following: (1) deriving the novel semantic representations of events from their textual descriptions, rather than event names; (2) aggregating the ranks of grounded concepts for MED tasks. A statistical mean-shift outlier rejection model is proposed to remove the outlying concepts which are incorrectly grounded; and (3) defining MEC tasks and augmenting the MEC training set by the videos detected in MED in a zero-shot setting. To the best of our knowledge, this work is the first time to define and solve the MEC task, which is a further step towards understanding video events. We conduct extensive experiments and achieve state-of-the-art performance on the TRECVID MEDTest dataset, as well as our newly proposed TRECVID-MEC dataset.

Most existing text-to-image generation methods focus on synthesizing images using only text descriptions, but this cannot meet the requirement of generating desired objects with given backgrounds. In this paper, we propose a Background-induced Generative Network (BGNet) that combines attention mechanisms, background synthesis, and multi-level discriminator to generate realistic images with given backgrounds according to text descriptions. BGNet takes a multi-stage generation as the basic framework to generate fine-grained images and introduces a hybrid attention mechanism to capture the local semantic correlation between texts and images. To adjust the impact of the given backgrounds on the synthesized images, synthesis blocks are added at each stage of image generation, which appropriately combines the foreground objects generated by the text descriptions with the given background images. Besides, a multi-level discriminator and its corresponding loss function are proposed to optimize the synthesized images. The experimental results on the CUB bird dataset demonstrate the superiority of our method and its ability to generate realistic images with given backgrounds.

Multi-modal hashing methods could support efficient multimedia retrieval by combining multi-modal features for binary hash learning at the both offline training and online query stages. However, existing multi-modal methods cannot binarize the queries, when only one or part of modalities are provided. In this article, we propose a novel Flexible Multi-modal Hashing (FMH) method to address this problem. FMH learns multiple modality-specific hash codes and multi-modal collaborative hash codes simultaneously within a single model. The hash codes are flexibly generated according to the newly coming queries, which provide any one or combination of modality features. Besides, the hashing learning procedure is efficiently supervised by the pair-wise semantic matrix to enhance the discriminative capability. It could successfully avoid the challenging symmetric semantic matrix factorization and O ( n 2 ) storage cost of semantic matrix. Finally, we design a fast discrete optimization to learn hash codes directly with simple operations. Experiments validate the superiority of the proposed approach.

Multi-modal hashing is an effective technique to support large-scale multimedia retrieval, due to its capability of encoding heterogeneous multi-modal features into compact and similarity-preserving binary codes. Although great progress has been achieved so far, existing methods still suffer from several problems, including: 1) All existing methods simply adopt fixed modality combination weights in online hashing process to generate the query hash codes. This strategy cannot adaptively capture the variations of different queries. 2) They either suffer from insufficient semantics (for unsupervised methods) or require high computation and storage cost (for the supervised methods, which rely on pair-wise semantic matrix). 3) They solve the hash codes with relaxed optimization strategy or bit-by-bit discrete optimization, which results in significant quantization loss or consumes considerable computation time. To address the above limitations, in this paper, we propose an Online Multi-modal Hashing with Dynamic Query-adaption (OMH-DQ) method in a novel fashion. Specifically, a self-weighted fusion strategy is designed to adaptively preserve the multi-modal feature information into hash codes by exploiting their complementarity. The hash codes are learned with the supervision of pair-wise semantic labels to enhance their discriminative capability, while avoiding the challenging symmetric similarity matrix factorization. Under such learning framework, the binary hash codes can be directly obtained with efficient operations and without quantization errors. Accordingly, our method can benefit from the semantic labels, and simultaneously, avoid the high computation complexity. Moreover, to accurately capture the query variations, at the online retrieval stage, we design a parameter-free online hashing module which can adaptively learn the query hash codes according to the dynamic query contents. Extensive experiments demonstrate the state-of-the-art performance of the proposed approach from various aspects.