It is well known that high dynamic range (HDR) videos enhance immersive visual experiences compared to conventional standard dynamic range content. However, HDR content is typically more challenging to encode due to the increased detail associated with the wider dynamic range. In this work, we improve HDR compression performance using an Effective Bit Depth Adaptation approach (EBDA), which reduces the effective bit depth of the original video content before encoding and reconstructs the full bit depth using a CNN-based up-sampling method at the decoder. The up-sampling deep network is based on a new version of Multi-frame MFRNet, MF-MFRNet. This approach has been integrated into the EBDA framework with two Versatile Video Coding (VVC) reference models: VTM 16.2 and the Fraunhofer Versatile Video Encoder (VVenC 1.4.0). The proposed approach has been evaluated under the JVET HDR Common Test Conditions using the Random Access configuration. The results show evident coding gains over both the original VTM 16.2 and VVenC 1.4.0 on all JVET HDR tested sequences, with average bitrate savings of 3.1% and 4.8% based on PSNR and 7.8% and 9.6% based on VMAF against VTM and VVenC respectively. The source code of multi-frame MFRNet has been released at https://github.com/fan-aaron-zhang/MF-MFRNet.

When distribution shifts occur between testing and training graph data, out-of-distribution (OOD) samples undermine the performance of graph neural networks (GNNs). To improve adaptive OOD generalization of GNNs, this paper introduces a novel generative invariant graph learning framework, named GI-Graph. It consists of four modules: subgraph extractor, generative environment subgraph augmentation, generative invariant subgraph learning, and query feedback module. The subgraph extractor decomposes a graph sample into an environment subgraph and an invariant subgraph and improves extraction accuracy through query feedback. GI-Graph uses a diffusion model to generate diverse environment subgraphs, augmenting the OOD data. By combining diffusion models, contrastive learning, and attribute prediction networks, GI-Graph also generates augmented invariant subgraphs with significant identically distributed features and consistency of labels. Experimental results demonstrate that the controllable environment subgraph and invariant subgraph augmentation effectively improve the OOD generalization capability of GI-Graph, especially in capturing invariant features and maintaining category consistency across environments. Additionally, the contrastive learning-based finetuning method enables GI-Graph to quickly adapt to evolving environments. This paper verifies the effectiveness of the generative invariant graph learning scheme in graph OOD generalization.

Unlike video coding for professional content, the delivery pipeline of User Generated Content (UGC) involves transcoding where unpristine reference content needs to be compressed repeatedly. In this work, we observe that existing full-/no-reference quality metrics fail to accurately predict the perceptual quality difference between transcoded UGC content and the corresponding unpristine references. Therefore, they are unsuited for guiding the rate-distortion optimisation process in the transcoding process. In this context, we propose a bespoke full-reference deep video quality metric for UGC transcoding. The proposed method features a transcoding-specific weakly supervised training strategy employing a quality ranking-based Siamese structure. The proposed method is evaluated on the YouTube-UGC VP9 subset and the LIVE-Wild database, demonstrating state-of-the-art performance compared to existing VQA methods. The source code of the developed quality metric and the associated training data are available from https://zihaoq1:github/io/FRUGC/.

Many natural language questions are inherently subjective. They can not be answered properly if we do not know the personal preferences of the answerer. For example, "Do you like cats?" There is no "the only correct answer" to this question. To answer it, the model has to be able to capture the persona of the answerers. However, the users usually do not answer different questions with equal chance. Instead, while some are answered with a high frequency, others are hardly answered by anyone. To deal with this imbalanced sparsity in data, we first introduce a Siamese Network to capture the preferences patterns of the users. Then the model is ensembled with an additional dense layer to predict the answers of the users. Applying to an online dating dataset, our approach achieves a high accuracy of 78.7%.

Conventional linear precoding schemes in massive multiple-input-multiple-output (MIMO) systems, such as regularized zero-forcing (RZF) precoding, have near-optimal performance but suffer from high computational complexity due to the required matrix inversion of large size. To solve this problem, we propose a successive overrelaxation (SOR)-based precoding scheme to approximate the matrix inversion by exploiting the asymptotically orthogonal channel property in massive MIMO systems. The proposed SOR- based precoding can reduce the complexity by about one order of magnitude, and it can also approach the classical RZF precoding with negligible performance loss. We also prove that the proposed SOR-based precoding enjoys a faster convergence rate than the recently proposed Neumann-based precoding. In addition, to guarantee the performance of SOR-based precoding, we propose a simple way to choose the optimal relaxation parameter in practical massive MIMO systems. Simulation results verify the advantages of SOR-based precoding in convergence rate and computational complexity in typical massive MIMO configurations.