DASH, the Dynamic adaptive video streaming over hypertext transfer protocol (HTTP), has become the de-facto video delivery mechanism nowadays, which takes advantage of the existing low cost and wide-spread HTTP platforms. Standards like MPEG-DASH defines the bitstreams conformance and decoding process, while leaving the bitrate adaptive algorithm open for research. So far, most DASH researches focus on the constant bitrate video delivery. In this paper, various bitrate (VBR) video delivery is investigated in the on-demand streaming scenario. Detailed instant bitrates of future segments are exploited in the proposed adaptation method to grasp the fluctuation traits of the VBR video. Meanwhile, the adaptation problem is formulated as an optimization process with the proposed internal QoE goal function, which keeps a good balance between various requirements. Besides, the parameters within the internal QoE function can be tuned to guarantee the flexibility of meeting different preferences. The experimental results demonstrate that our proposed QoE-based video adaptation method outperforms the state-of-the-art method with a good margin.

No-Reference Image Quality Assessment aims to evaluate the perceptual quality of an image, according to human perception. Many recent studies use Transformers to assign different self-attention mechanisms to distinguish regions of an image, simulating the perception of the human visual system (HVS). However, the quadratic computational complexity caused by the self-attention mechanism is time-consuming and expensive. Meanwhile, the image resizing in the feature extraction stage loses the full-size image quality. To address these issues, we propose a lightweight attention mechanism using decomposed large-kernel convolutions to extract multiscale features, and a novel feature enhancement module to simulate HVS. We also propose to compensate the information loss caused by image resizing, with supplementary features from natural scene statistics. Experimental results on five standard datasets show that the proposed method surpasses the SOTA, while significantly reducing the computational costs.

Convolutional neural networks have achieved excellent results in compressed video quality enhancement task in recent years. State-of-the-art methods explore the spatio-temporal information of adjacent frames mainly by deformable convolution. However, the CNN-based methods can only exploit local information, thus lacking the exploration of global information. Moreover, current methods enhance the video quality at a single scale, ignoring the multi-scale information, which corresponds to information at different receptive fields and is crucial for correlation modeling. Therefore, in this work, we propose a Transformer-based compressed video quality enhancement ( TVQE ) method, consisting of Transformer based Spatio-Temporal feature Fusion ( TSTF ) module and Multi-scale Channel-wise Attention based Quality Enhancement ( MCQE ) module. The proposed TSTF module learns both local and global features for correlation modeling, in which window-based Transformer and the encoder-decoder structure greatly improve the execution efficiency. The proposed MCQE module calculates the multi-scale channel attention, which aggregates the temporal information between channels in the feature map at multiple scales, achieving efficient fusion of inter-frame information. Extensive experiments on the JCT-VT test sequences show that the proposed method increases PSNR by up to 0.98 dB when QP $=$ 37. Meanwhile, the inference speed is improved by up to 9.4%, and the number of Flops is reduced by up to 84.4% compared to competing methods at 720p resolution. Moreover, the proposed method achieves the BD-rate reduction up to 23.04%.

Multiview video streaming continues to gain popularity due to the great viewing experience it offers, as well as its availability that has been enabled by increased network throughput and other recent technical developments. User demand for interactive multiview video streaming that provides seamless view switching upon request is also increasing. However, it is a highly challenging task to stream stable and high quality videos that allow real-time scene navigation within the bandwidth constraint. In this paper, a convolutional neural network (ConvNet)-assisted seamless multiview video streaming system is proposed to tackle the challenge. The proposed method solves the problem from two perspectives. First, a ConvNet-assisted multiview representation method is proposed, which provides flexible interactivity without compromising on multiview video compression efficiency. Second, a bit allocation mechanism guided by a navigation model is developed to provide seamless navigation and adapt to network bandwidth fluctuations at the same time. These two blocks work closely to provide an optimized viewing experience to users. They can be integrated into any existing multiview video streaming framework to enhance overall performance. Experimental results demonstrate the effectiveness of the proposed method for seamless multiview streaming.

Spatio-temporal information plays an important role in compressed video quality enhancement. Most advanced studies use deformable convolution or Swin transformer to explore spatio-temporal information. However, deformable convolution based methods may incur inaccurate motion compensation due to the compression artifacts and limited receptive fields. The Swin transformer based approaches are unable to fully explore the spatio-temporal information, limited by its rigid window-based mechanism. To solve the above problems, we propose a novel multi-Swin transformer-based network for compressed video quality enhancement to better explore spatio-temporal information. The whole workflow consists of the Local Alignment (LA) Module, the Global Refinement Fusion (GRF) Module, and the Quality Enhancement (QE) Module. The LA module roughly perceives the local motion through the deformable fusion. Subsequently, the GRF module employs the proposed multi-Swin transformer to enhance the spatio-temporal perception. Finally, the QE module effectively restores the texture details across various scales. Extensive experimental results prove the effectiveness of the proposed method.

Inspired by the dual-stream (dorsal and ventral streams) theory of the human visual system (HVS), recent Video Quality Assessment (VQA) methods have integrated Contrastive Language-Image Pretraining (CLIP) to enhance semantic understanding. However, as CLIP is originally designed for images, it lacks the ability to adequately capture the temporal dynamics and motion perception (dorsal stream) inherent in videos. To address this limitation, we propose DVLTA-VQA (Decoupled Vision-Language Modeling with Text-Guided Adaptation), which decouples CLIP’s visual and textual components to better align with the NR-VQA pipeline. Specifically, we introduce a Video-Based Temporal CLIP module and a Temporal Context Module to explicitly model motion dynamics, effectively enhancing the dorsal stream representation. Complementing this, a Basic Visual Feature Extraction Module is employed to strengthen spatial detail analysis in the ventral stream. Furthermore, we propose a text-guided adaptive fusion strategy that leverages textual semantics to dynamically weight visual features, facilitating effective spatiotemporal integration. Extensive experiments on multiple public datasets demonstrate that the proposed method achieves state-of-the-art performance, significantly improving prediction accuracy and generalization capability.