The graph neural network (GNN) based approaches have attracted more and more attention in session-based recommendation tasks. However, most of the existing methods do not fully take advantage of context information in session when capturing user’s interest, and the research on context adaptation is even less. Furthermore, hypergraph has potential to express complex relations among items, but it has remained unexplored. Therefore, this paper proposes an adaptive context-embedded hypergraph convolutional network (AC-HCN) for session-based recommendation. At first, the data of sessions is constructed as session hypergraph. Then, the representation of each item in session hypergraph is learned using an adaptive context-embedded hypergraph convolution. In the convolution, different types of context information from both current item itself and the item’s neighborhoods are adaptively integrated into the representation updating of current item. Meanwhile, an adaptive transformation function is employed to effectively eliminate the effects of irrelevant items. Then, the learned item representations are combined with time interval embeddings and reversed position embeddings to fully reflect time interval information and sequential information between items in session. Finally, based on learned item representations in session, a soft attention mechanism is used to obtain user’s interest, and then a recommendation list is given. Extensive experiments on the real-world datasets show that the proposed model has significantly improvement compared with the state-of-arts methods.

Eliminating geometric distortion in semantically important regions remains an intractable challenge in image retargeting. This paper presents Object-IR, a self-supervised architecture that reformulates image retargeting as a learning-based mesh warping optimization problem, where the mesh deformation is guided by object appearance consistency and geometric-preserving constraints. Given an input image and a target aspect ratio, we initialize a uniform rigid mesh at the output resolution and use a convolutional neural network to predict the motion of each mesh grid and obtain the deformed mesh. The retargeted result is generated by warping the input image according to the rigid mesh in the input image and the deformed mesh in the output resolution. To mitigate geometric distortion, we design a comprehensive objective function incorporating a) object-consistent loss to ensure that the important semantic objects retain their appearance, b) geometric-preserving loss to constrain simple scale transform of the important meshes, and c) boundary loss to enforce a clean rectangular output. Notably, our self-supervised paradigm eliminates the need for manually annotated retargeting datasets by deriving supervision directly from the input's geometric and semantic properties. Extensive evaluations on the RetargetMe benchmark demonstrate that our Object-IR achieves state-of-the-art performance, outperforming existing methods in quantitative metrics and subjective visual quality assessments. The framework efficiently processes arbitrary input resolutions (average inference time: 0.009s for 1024x683 resolution) while maintaining real-time performance on consumer-grade GPUs. The source code will soon be available at https://github.com/tlliao/Object-IR.