In this work, we propose a deep learning-based adaptive quantization method to promote video coding performance. Due to inter-prediction and reference mechanism, the block-level quantization parameter (QP) not only influences current block distortion but also has complex temporal propagation effects on subsequent coding frames. Our idea is to utilize a deep network to model the complex temporal propagation relationship of quantization. As shown in Fig. 1, the deep network directly predicts all block-level QPs of the frame for the traditional encoder without changing the standard decoder. Since our network deploys only on the encoder side and has low inference complexity, it can be easily applied in practice. In addition, we use a learned coding network as a proxy of the traditional codec to train our network.

Video coding achieves efficient compression by exploiting the spatial and temporal correlations within the video signal. However, the noise in the source signal corrupts such correlation and impairs the coding performance. Motion compensated temporal filter (MCTF) [1] is a pre-processing tool that removes certain noise from the source signal, thereby enhancing temporal correlations among adjacent frames. Although numerous efforts have been made to optimize MCTF, MCTF still lacks flexibility in filtering for diverse video content, and its filtering efficiency is still limited. In this paper, we propose the Content-Aware MCTF method (CAMCTF) to enhance the filtering adaptability of MCTF for diverse video contents. The CAMCTF adaptively adjusts the filtering block sizes based on the Sum of Square Error (SSE) and Motion Vector (MV) information calculated during the motion estimation (ME) process in MCTF, and offset weighting method is applied to improve the prediction quality of filtering blocks. Performance was evaluated on top of Versatile Video Coding (VVC) reference software VTM-23.4. The VVC Common Test Conditions (CTC) [2] with QPs 22, 27, 32, 37 are used. As shown in Table 1, CAMCTF achieves an overall of 1.07% and 0.79% luma BD-rate gains in Random Access (RA) and Low Delay (LD) configurations, respectively. The encoder complexity is 112% and 110% for RA and LD configurations, respectively, without decoder complexity increasing.

With the proliferation of Large Language Models (LLMs) in Business Intelligence (BI), existing solutions face critical challenges in industrial deployments: functionality deficiencies from legacy systems failing to meet evolving LLM-era user demands, interaction limitations from single-round SQL generation paradigms inadequate for multi-round clarification, and cost for domain adaptation arising from cross-domain methods migration. We present SiriusBI, a practical LLM-powered BI system addressing the challenges of industrial deployments through three key innovations: (a) An end-to-end architecture integrating multi-module coordination to overcome functionality gaps in legacy systems; (b) A multi-round dialogue with querying mechanism, consisting of semantic completion, knowledge-guided clarification, and proactive querying processes, to resolve interaction constraints in SQL generation; (c) A data-conditioned SQL generation method selection strategy that supports both an efficient one-step Fine-Tuning approach and a two-step method leveraging Semantic Intermediate Representation for low-cost cross-domain applications. Experiments on both real-world datasets and public benchmarks demonstrate the effectiveness of SiriusBI. User studies further confirm that SiriusBI enhances both productivity and user experience. As an independent service on Tencent's data platform, SiriusBI is deployed across finance, advertising, and cloud sectors, serving dozens of enterprise clients. It achieves over 93% accuracy in SQL generation and reduces data analysts' query time from minutes to seconds in real-world applications.

Efficiently improving the accuracy of motion vector (MV) in merge candidate list is a critical issue in terms of the advanced inter coding technologies. The decoder side motion vector refinement (DMVR) and merge mode with motion vector differences (MMVD) are utilized to refine the MV obtained from merge mode in Versatile Video Coding (VVC). Nevertheless, both DMVR and MMVD operate under the assumption of symmetric motion when adjusting bi-prediction MV. This assumption may result in inaccuracies adjusting where the motion is asymmetric, leading to imprecise MV. To address this issue, we propose the asymmetric motion vector refinement (ASMVR) approach to refine asymmetric motion more accurately for future video coding in this paper. Specifically, ASMVR is formulated by the asymmetric MMVD (asy-MMVD) and asymmetric DMVR (asy-DMVR) schemes, which are compatible with MMVD and DMVR in VVC respectively. Four asymmetric MV refinement templates are devised to capture varying motion scenes, and the optimal one is derived through bilateral matching and rate-distortion optimization. Moreover, meticulously designed fast algorithms are implemented to bypass unnecessary candidate evaluations, thereby effectively reducing both encoding and decoding complexities. The simulation result shows that on top of the VVC Test Model (VTM-22.1), ASMVR achieves 1.52% BD-rate saving for random access (RA).

Recently many efforts have been devoted to learning non-linear predictions from neighboring samples with deep neural networks. However, existing methods mainly generate predictions with local reference samples, regardless of nonlocal self-similarity. In this paper, we aim to incorporate local and nonlocal correlations for intra prediction and propose a two-stage coarse-to-fine network (CTFN), which is integrated into VVC codec as an optional intra prediction mode. The prediction process of CTFN is decomposed into two stages. In the first stage, we train a set of networks to generate a coarse result with local reference samples. In the second stage, we extract sufficient features from nonlocal region using the coarse result as priors and transform the features into a fine prediction result. In particular, a patch-wise attention layer (PAL) is designed in the second stage that can fully explore nonlocal correlations in feature domain and assign weights to each nonlocal feature adaptively, as shown in Fig. 1. As such, the proposed CTFN can not only learn a non-linear mapping from local context, but also explicitly borrow similar features from nonlocal region in a weighted form. Different from image inpainting tasks, the patch synthesis problem is converted to patch matching problem with the CTFN, yielding more reliable predictions. More-over, we construct a classified dataset based on Pearson Correlation Coefficient for network training to better handle contents that are highly correlated. Experiments on VTM-11.0 show that the proposed network achieves 1.77% ED-rate reductions under all intra configuration, which outperforms the state-of-the-art methods.

In-loop filter has been comprehensively explored during the development of video coding standards to suppress compression artifacts. However, the existing in-loop filters in Versatile Video Coding (VVC) mainly take advantage of the image local similarity. Although some non-local based in-loop filters can make up for this short-coming, the unsupervised parameter selection scheme, which is widely used by non-local filters, limits the content adaptability. Given this, we propose a parametric non-local in-loop filter (PNLF) that fully considers the non-local characteristics and trains the filter coefficients based on the video content. In the filtering process, the reference samples based on the non-local similarity are first derived for each to-be-filtered sample. Then to-be-filtered samples are grouped into specific classes based on multiple features. For each class, filter coefficients are online trained in the encoder and transmitted to the decoder. Finally, the filtering process is conducted using the online-selected coefficients. Simulation results reveal that the proposed approach achieves 0.70%, 1.43%, and 2.09% bit-rate savings on average compared to VTM-11.0 under All Intra (AI), Random Access (RA), and Low-Delay B (LDB) configurations, respectively. The sequences used in the experiment include Class AI, A2, B, C, D, E, F, and SCC. Compared to the non-local structure-based filter (NLSF) [1], our proposed PNLF with fast block matching scheme [2] applied on B-frames and P-frames can achieve better performance gain with lower software and hardware complexity under RA and LDB configurations.