Cross-view localization aims to estimate the precise position and orientation of a ground-view image by aligning it with satellite imagery. However, existing homography-based methods are typically evaluated under limited orientation noise (±45°) and exhibit limited refinement capability, as their local correlation-based refinement relies on a reasonably good initial orientation estimate. To address these limitations, we propose a fine-grained cross-view localization method based on orientation-guided homography (OGH-Net), whose core idea is to predict an initial orientation prior that explicitly guides subsequent homography refinement. Specifically, we first design a hybrid bird's-eye-view (BEV) transformation to generate BEV images with preserved central geometry and expanded coverage. Then, we introduce a lightweight orientation-prior module that provides a coarse yaw estimate across the full ±180° range. Finally, we develop a multiscale iterative homography module that progressively refines the projection matrix through hierarchical iterations across multiple feature resolutions. Under cross-area, unknown-orientation conditions, it reduces mean localization error by 11% and mean orientation error by 27% on VIGOR, and further reduces mean localization error by 27% on KITTI compared with previous state-of-the-art methods. Moreover, OGH-Net runs in real time at up to 107 FPS on a single RTX 3090 GPU, offering a favorable trade-off between accuracy and efficiency. The code and trained models will be released at https://github.com/YC-Zhang2025/OGH-Net.

Generative Adversarial Imitation Learning (GAIL) stands as a cornerstone approach in imitation learning. This paper investigates the gradient explosion in two types of GAIL: GAIL with deterministic policy (DE-GAIL) and GAIL with stochastic policy (ST-GAIL). We begin with the observation that the training can be highly unstable for DE-GAIL at the beginning of the training phase and end up divergence. Conversely, the ST-GAIL training trajectory remains consistent, reliably converging. To shed light on these disparities, we provide an explanation from a theoretical perspective. By establishing a probabilistic lower bound for GAIL, we demonstrate that gradient explosion is an inevitable outcome for DE-GAIL due to occasionally large expert-imitator policy disparity, whereas ST-GAIL does not have the issue with it. To substantiate our assertion, we illustrate how modifications in the reward function can mitigate the gradient explosion challenge. Finally, we propose CREDO, a simple yet effective strategy that clips the reward function during the training phase, allowing the GAIL to enjoy high data efficiency and stable trainability.

Cross-domain recommendation (CDR) leverages knowledge from the source domain to make recommendations for the cold-start users in the target domain. On account of fully utilizing information, various relationships among users and items are taken into account, i.e., the interaction relationship between users and their corresponding items; the relationship among users or items; and the indirect relationship between the user and items related to other users. In order to process these relationships, we propose a novel framework named Memory Pool Variational AutoEncoder (MPVAE). The main advantages of the MPVAE model lie in three aspects: (1) it generates the embedding representations that incorporate more information by a memory pool mechanism in the source and target domains; (2) it involves the relationship among users or items efficiently by the similarity measurement, further, the indirect relationship can be explicitly described, which makes full use of information in the source domain; and (3) it leverages the superiority of the probability model from the perspective of the VAE structure, which ensures generation and robustness. Comprehensive experiments on three real datasets show that the proposed model achieves remarkable superiority over several competitive CDR models.