The objective of non-reference video quality assessment is to evaluate the
quality of distorted video without access to reference high-definition
references. In this study, we introduce an enhanced spatial perception module,
pre-trained on multiple image quality assessment datasets, and a lightweight
temporal fusion module to address the no-reference visual quality assessment
(NR-VQA) task. This model implements Swin Transformer V2 as a local-level
spatial feature extractor and fuses these multi-stage representations through a
series of transformer layers. Furthermore, a temporal transformer is utilized
for spatiotemporal feature fusion across the video. To accommodate compressed
videos of varying bitrates, we incorporate a coarse-to-fine contrastive
strategy to enrich the model's capability to discriminate features from videos
of different bitrates. This is an expanded version of the one-page abstract.

非参考视频质量评估中，通过引入经过多个图像质量评估数据集预训练的增强空间感知模块和轻量级的时域融合模块，本研究实现了使用 Swin Transformer V2 作为本地级别空间特征提取器，并通过一系列 Transformer 层融合这些多阶段表示。此外，还利用时域 Transformer 在视频中进行时空特征融合。为了适应不同比特率的压缩视频，我们采用粗到精的对比策略，以增强模型区分来自不同比特率视频的特征的能力。这是一篇扩展版的一页摘要。

基于 Swin TransformerV2 和粗糙到精细策略的视频质量评估

Video Quality Assessment Based on Swin TransformerV2 and Coarse to Fine  Strategy

3D object detection is a core component of automated driving systems.
State-of-the-art methods fuse RGB imagery and LiDAR point cloud data
frame-by-frame for 3D bounding box regression. However, frame-by-frame 3D
object detection suffers from noise, field-of-view obstruction, and sparsity.
We propose a novel Temporal Fusion Module (TFM) to use information from
previous time-steps to mitigate these problems. First, a state-of-the-art
frustum network extracts point cloud features from raw RGB and LiDAR point
cloud data frame-by-frame. Then, our TFM module fuses these features with a
recurrent neural network. As a result, 3D object detection becomes robust
against single frame failures and transient occlusions. Experiments on the
KITTI object tracking dataset show the efficiency of the proposed TFM, where we
obtain ~6%, ~4%, and ~6% improvements on Car, Pedestrian, and Cyclist classes,
respectively, compared to frame-by-frame baselines. Furthermore, ablation
studies reinforce that the subject of improvement is temporal fusion and show
the effects of different placements of TFM in the object detection pipeline.
Our code is open-source and available at
this https URL

本研究提出了一种新颖的 Temporal Fusion 模块（TFM）用于三维物体的检测，它结合了先前时间步骤中的信息以减轻单帧噪声、场景视野阻塞和稀疏性对三维物体检测的影响，实验结果表明，相较于基线方法的帧间检测，我们在 KITTI 目标跟踪数据集上分别实现了 6％，4％和 6％的改进。