Visual query localization (VQL) is pivotal for constructing episodic memory from egocentric videos. However, current methods often rely on computationally intensive attention mechanisms and rigid one-shot regression, which inherently struggle to model uncertainty and exhibit limited adaptability to degraded query appearances. This contrasts sharply with the human brain’s selective encoding and iterative hypothesis verification processes for episodic memory. Inspired by the human brain’s ability to selectively filter irrelevant information and reconstruct vague memory fragments through generative inference, we propose BiOVQL, a brain-inspired one-stage VQL framework. First, inspired by the hippocampus’s selective retention mechanism, we propose the Hippocampus-like Query-guided Spatio-Temporal Compression (HQSTC) module. By leveraging a selective state space model, visual queries are treated as neuromodulators, dynamically gating the video stream to maintain a compact latent state. This guides the model to consistently focus on query-relevant visual cues, enabling query-conditioned feature compression and efficient spatio-temporal memory encoding. Second, inspired by the prefrontal cortex’s re-localization mechanisms, we propose the Prefrontal-like Generative Refinement Localization (PGRL) module. We leverage a diffusion model to reconstruct the localization process as iterative denoising from noise to certainty, which aligns well with the human visual system’s coarse-to-fine perceptual reasoning. This enhances the model’s robustness in handling spatial ambiguities and achieving precise spatio-temporal retrieval. We conducted extensive experiments on the Ego4D-VQ benchmark, demonstrating that BiOVQL achieves state-of-the-art performance with comparable computational efficiency, thus offering an efficient and brain-inspired paradigm for VQL.

Although vision-based tiny ball tracking has advanced in specific sports, existing methods remain heavily coupled to domain-specific distributions, severely constraining cross-domain generalization. Concurrently, lightweight designs sacrifice representational capacity, while high-performance models incur prohibitive computational costs. To address these challenges, we propose TrackNetV6, a unified fast-moving tiny ball tracking framework that reconciles efficiency with accuracy. Central to our framework is a novel and compact decoding paradigm rooted in the Linear Multistep Method (LMM), designed to supersede conventional single-step feature fusion. This paradigm orchestrates two core components: a Cross-Scale Semantic Consensus Predictor (CSCP) that distills multi-scale features into semantic-correlation location priors, and a Prior-guided Context Corrector (PCC) that injects these priors into current-scale mappings for stable refinement. By iteratively alternating between these components, the model progressively strengthens feature representation for precise tracking. Furthermore, we introduce a Direction-aware Dynamic Fusion (DDF) module as the bottleneck layer, which explicitly models the direction-sensitive feature relationships of the fast-moving ball by synergizing the dynamic interaction between wavelet-based high-frequency cues and deep semantics. Extensive experiments across badminton, table tennis, and tennis benchmarks demonstrate that TrackNetV6 not only sets a new state-of-the-art (SOTA) but also delivers exceptional real-time inference at 183 FPS. Code will be available at https://github.com/Gi-gigi/TrackNetV6.

Referring video object segmentation (RVOS) aims to dynamically segment a target object across video sequences based on a given natural language expression. Although recent decoupled methods surpass end-to-end models, they suffer from a critical trade-off: relying on fine-tuned large language models for key frame selection incurs high computational costs, whereas employing sparse sampling risks missing optimal reference frames. Furthermore, the subsequent mask propagation lacks self-correction mechanisms, leading to irreversible cumulative errors over time. In this work, we propose LCRP, a training-free framework driven by two novel components. The Hybrid Candidate Sampling (HCS) module significantly improves frame selection by integrating lightweight semantic parsing with CLIP-based filtering. Meanwhile, the Multi-Anchor Refinement (MAR) module utilizes anchor frames as dynamic checkpoints to detect temporal drift and execute localized re-propagation. Extensive experiments indicate that our proposed method achieves state-of-the-art results. Code is available at https://github.com/Crystal535/Locate-Core-Refine-Path.

Knowledge graph (KG) is often introduced into recommendation systems because of its large amount of edge information. The method based on graph neural networks (GNNs) has gradually become the mainstream of KG-aware recommendation. However, traditional KG-aware recommendation models based on GNNs fail to utilize the dependencies of items and item attributes to model user preferences at a fine-grained level, which will result in a lack of interpretability in the model’s recommendations to users. In addition, traditional KG-aware recommendation models based on GNNs fail to mine supervision signals from the perspective of user preferences and item attributes, which will result in a lack of effective supervision signals in the model. In this study, we utilize a combination of items and attributes behind the items to model user preferences at a fine-grained level, so as to achieve independence between different user preferences. Furthermore, we utilize the KG and the user–item interaction graph (UIIG) to construct the user-specific preference similarity view and the item-specific attribute correlation views, respectively, and then apply the contrastive learning framework to effectively mine the association signals between users and between items. Based on this, we propose a novel model named Knowledge Graph Fine-grained Modeling Network with Contrastive Learning (KGFM-CL). Extensive experiments conducted on two real-world datasets demonstrate that KGFM-CL significantly outperforms state-of-the-art baseline models.

Knowledge graph embedding (KGE) has shown great potential in automatic knowledge graph (KG) completion and knowledge-driven tasks. However, recent KGE models suffer from high training cost and large storage space, thus limiting their practicality in real-world applications. To address this challenge, based on the latest findings in the field of Contrastive Learning, we propose a novel KGE training framework called Hardness-aware Low-dimensional Embedding (HaLE). Instead of the traditional Negative Sampling, we design a new loss function based on query sampling that can balance two important training targets, Alignment and Uniformity. Furthermore, we analyze the hardness-aware ability of recent low-dimensional hyperbolic models and propose a lightweight hardness-aware activation mechanism, which can help the KGE models focus on hard instances and speed up convergence. The experimental results show that in the limited training time, HaLE can effectively improve the performance and training speed of KGE models on five commonly-used datasets. After training just a few minutes, the HaLE-trained models are competitive compared to the state-of-the-art models in both low- and high-dimensional conditions.

Link prediction based on knowledge graph embeddings (KGE) aims to predict new triples to automatically construct knowledge graphs (KGs). However, recent KGE models achieve performance improvements by excessively increasing the embedding dimensions, which may cause enormous training costs and require more storage space. In this paper, instead of training high-dimensional models, we propose MulDE, a novel knowledge distillation framework, which includes multiple low-dimensional hyperbolic KGE models as teachers and two student components, namely Junior and Senior. Under a novel iterative distillation strategy, the Junior component, a low-dimensional KGE model, asks teachers actively based on its preliminary prediction results, and the Senior component integrates teachers’ knowledge adaptively to train the Junior component based on two mechanisms: relation-specific scaling and contrast attention. The experimental results show that MulDE can effectively improve the performance and training speed of low-dimensional KGE models. The distilled 32-dimensional model is competitive compared to the state-of-the-art high-dimensional methods on several widely-used datasets.

Name ambiguity in the context of bibliographic citation affects the quality of services in digital libraries. Previous methods are not widely applied in practice because of their high computational complexity and their strong dependency on excessive attributes, such as institutional affiliation, research area, address, etc., which are difficult to obtain in practice. To solve this problem, we propose a novel coarse‐to‐fine framework for name disambiguation which sequentially employs 3 common and easily accessible attributes (i.e., coauthor name, article title, and publication venue). Our proposed framework is based on multiple clustering and consists of 3 steps: (a) clustering articles by coauthorship and obtaining rough clusters, that is fragments; (b) clustering fragments obtained in step 1 by title information and getting bigger fragments; (c) and clustering fragments obtained in step 2 by the latent relations among venues. Experimental results on a Digital Bibliography and Library Project (DBLP) data set show that our method outperforms the existing state‐of‐the‐art methods by 2.4% to 22.7% on the average pairwise F1 score and is 10 to 100 times faster in terms of execution time.