Accurate localization of oriented objects in remote sensing images (RSI) faces complex challenges, particularly the difficulty of feature modeling arising from the geometric complexity of oriented targets, manifested as arbitrary orientations and scale variations. Existing paradigms, primarily based on Convolutional Neural Networks (CNNs) or Transformers, which struggle to capture robust rotation-invariant features due to inherent structural deficiencies (feature confusion due to fixed grid sampling in CNNs, spatial misalignment due to inadequate orientation encoding in attention mechanism). Graph-based feature modeling displays robustness against geometric complexity, prompting several studies to explore the incorporation of graph structures. However, these methods primarily focus on region proposals or pixel-level rotation correlations, struggling to effectively model the rotation-invariant features of targets. In this paper, we propose the Graph-based Semantic Rerouting Interaction (GSRI), shifting the modeling of rotated semantic representation for objects from tilted spatial-domain pixel recognition to the exploration of consistent channel-level semantic responses, thereby achieving robust rotation semantic feature modeling. Specifically, GSRI introduces a dynamic dilated KNN based graph structure to enhance the rotation-invariant feature modeling through capturing the consistent activation relationships of similar targets in high-dimensional feature space. By incorporating a cross-attention mechanism with dual positional encoding supervision, GSRI facilitates the alignment and propagation of robust rotational semantics across cross-scale feature maps, thereby mitigating background noise and bolstering the perceptibility of rotated objects in complex RSI scenarios. Extensive experiments on the DOTA-v1.0 and DIOR-R datasets demonstrate the superior effectiveness of our method.

Generative retrieval enhances retrieval effectiveness by generating natural language represented document identifiers. However, current methods often struggle with two major challenges: limited identifier quality and insufficient query-document interaction, leading to limited retrieval performance. To tackle these challenges, we propose a novel generative retrieval framework integrated with semantic-aligned multi-layer identifiers and reinforcement learning. To improve identifier quality, we design a prompt-driven multi-task learning strategy to generate three types of hierarchical identifiers: summary, keyword, and pseudo-query, to capture multi-granularity document semantics. Furthermore, we adopt supervised fine-tuning to integrate these identifiers. To improve query-document interaction, we devise a multi-view ranking fusion mechanism that combines retrieval results across multi-layer identifiers. We further employ a GRPO-based reinforcement learning based on dense similarity rewards and a difficulty-aware negative sampling strategy to optimize the generated identifiers. Experiments on multiple benchmark datasets show that our framework significantly outperforms existing generative retrieval methods, offering a promising solution for building more effective and semantically aligned retrieval systems. The code for our model is publicly available at https://github.com/yicentian02/GRAM-RL.

Relation reasoning in temporal knowledge graph infers unknown or emerging relational dependencies from historical structured data. Traditional approaches face inherent limitations in capturing complex semantic correlations and structural patterns among relations. To tackle this problem, we propose the Relational Multi-path Enhancement network (RME), which primarily focuses on relation modeling to enrich relation representations through comprehensive multi-path analysis. RME consists of five key components: (1) Controlled random walk module creates multi-hop head-to-tail paths using an adaptive stopping rule that balances short- and long-term connections. (2) Shared path extraction module identifies both shared-head paths and shared-tail paths. (3) Time-decayed path encoding module processes these paths differently. (4) Gated information aggregation module combines path information to determine which parts matter most. (5) Attention decoding module makes the final prediction by focusing on the most relevant path features. Experiments on multiple TKG benchmark datasets demonstrate that RME outperforms the state-of-the-art methods in relation multi-path reasoning.

Current large vision-language models (VLMs) exhibit remarkable performance in basic video understanding tasks. However, existing VLMs are still limited to surface-level perception and lack fine-grained spatio-temporal understanding and combinatorial reasoning capabilities. Existing methods typically rely on expensive human annotations or subtitle extraction, yet they struggle to effectively model temporal relations between frames. This paper proposes a structured representation based on temporal triplets to address two major challenges in traditional approaches: temporal fragmentation and entity reference ambiguity. By modeling objects, attributes, and relationships within the video and incorporating temporal information, we convert semantic content from keyframes into a sequence of temporal triplets. This structured representation is then used as input for zero-shot video question answering (VideoQA). Experiments were conducted on four benchmark VideoQA datasets: NExT-QA, STAR, MSVD-QA, and MSRVTT-QA, showing that our method achieves competitive performance without requiring fine-tuning, validating its generality and effectiveness.

Malevolence detection in dialogues aims to identify harmful or inappropriate utterances, significantly impacting dialogue quality and user satisfaction. Although existing studies have shown promising performance by modeling interaction patterns from dialogue history, various malevolence-invoking factors, such as fine-grained emotions, evolving topics and user profiles, are often overlooked. To comprehensively consider these factors, we propose a hypergraph fusion model by employing multi-view LLM-driven prompts for malevolence detection in dialogues. Our model integrates emotion context, topic context, user profile context and interaction context, utilizing hypergraphs to establish high-order contextual relationships from multi views for deducing malevolence-invoking semantics. Experimental results on two benchmark datasets demonstrate that our model achieves the state-of-the-art performance.

Deep cross-modal retrieval methods have shown their competitiveness among different cross-modal retrieval algorithms. Generally, these methods require a large amount of training data. However, aggregating large amounts of data will incur huge privacy risks and high maintenance costs. Inspired by the recent success of federated learning, we propose the federated cross-modal retrieval (FedCMR), which learns the model with decentralized multi-modal data. Specifically, we first train the cross-modal retrieval model and learn the common space across multiple modalities in each client using its local data. Then, we jointly learn the common subspace of multiple clients on the trusted central server. Finally, each client updates the common subspace of the local model based on the aggregated common subspace on the server, so that all clients participated in the training can benefit from federated learning. Experiment results on four benchmark datasets demonstrate the effectiveness proposed method.

Deep multimodal clustering have shown their competitiveness among different multimodal clustering algorithms. Existing algorithms usually boost the multimodal clustering by exploring the common knowledge among multiple modalities, which underutilizes the uniqueness of multiple modalities. In this paper, we enhance the mining of modality-common knowledge by extracting the modality-unique knowledge of each modality simultaneously. Specifically, we first utilize autoencoders to extract the modality-common and modality-unique features of each modality respectively. Meanwhile, the cross reconstruction is used to build latent connections among different modalities, i.e., maintain the consistency of modality-common features of each modality as well as heightening the diversity of modality-unique features of each modality. After that, modality-common features are fused to cluster the multimodal data. Experimental results on several benchmark datasets demonstrate that the proposed method outperforms state-of-art works obviously.

Sampling is the key aspect for Nyström extension based spectral clustering. Traditional sampling schemes select the set of landmark points on a whole and focus on how to lower the matrix approximation error. However, the matrix approximation error does not have direct impact on the clustering performance. In this article, we propose a sampling framework from an incremental perspective, i.e., the landmark points are selected one by one, and each next point to be sampled is determined by previously selected landmark points. Incremental sampling builds explicit relationships among landmark points; thus, they work together well and provide a theoretical guarantee on the clustering performance. We provide two novel analysis methods and propose two schemes for selecting-the-next-one of the framework. The first scheme is based on clusterability analysis, which provides a better guarantee on clustering performance than schemes based on matrix approximation error analysis. The second scheme is based on loss analysis, which provides maximized predictive ability of the landmark points on the (implicit) labels of the unsampled points. Experimental results on a wide range of benchmark datasets demonstrate the superiorities of our proposed incremental sampling schemes over existing sampling schemes.

Multi-view clustering integrates complementary information from multiple views to gain better clustering performance rather than relying on a single view. NMF based multi-view clustering algorithms have shown their competitiveness among different multi-view clustering algorithms. However, NMF fails to preserve the locally geometrical structure of the data space. In this paper, we propose a multi-manifold regularized nonnegative matrix factorization framework (MMNMF) which can preserve the locally geometrical structure of the manifolds for multi-view clustering. MMNMF regards that the intrinsic manifold of the dataset is embedded in a convex hull of all the views' manifolds, and incorporates such an intrinsic manifold and an intrinsic (consistent) coefficient matrix with a multi-manifold regularizer to preserve the locally geometrical structure of the multi-view data space. We use linear combination to construct the intrinsic manifold, and propose two strategies to find the intrinsic coefficient matrix, which lead to two instances of the framework. Experimental results show that the proposed algorithms outperform existing NMF based algorithms for multi-view clustering.