Video compression is a fundamental topic in the visual intelligence, bridging visual signal sensing/capturing and high-level visual analytics. The broad success of artificial intelligence (AI) technology has enriched the horizon of video compression into novel paradigms by leveraging end-to-end optimized neural models. In this survey, we first provide a comprehensive and systematic overview of recent literature on end-to-end optimized learned video coding, covering the spectrum of pioneering efforts in both uni-directional and bi-directional prediction based compression model designation. We further delve into the optimization techniques employed in learned video compression (LVC), emphasizing their technical innovations, advantages. Some standardization progress is also reported. Furthermore, we investigate the system design and hardware implementation challenges of the LVC inclusively. Finally, we present the extensive simulation results to demonstrate the superior compression performance of LVC models, addressing the question that why learned codecs and AI-based video technology would have with broad impact on future visual intelligence research.

The rapid advancement of artificial intelligence (AI) technology has led to the prioritization of standardizing the processing, coding, and transmission of video using neural networks. To address this priority area, the Moving Picture, Audio, and Data Coding by Artificial Intelligence (MPAI) group is developing a suite of standards called MPAI-EEV for "end-to-end optimized neural video coding." The aim of this AI-based video standard project is to compress the number of bits required to represent high-fidelity video data by utilizing data-trained neural coding technologies. This approach is not constrained by how data coding has traditionally been applied in the context of a hybrid framework. This paper presents an overview of recent and ongoing standardization efforts in this area and highlights the key technologies and design philosophy of EEV. It also provides a comparison and report on some primary efforts such as the coding efficiency of the reference model. Additionally, it discusses emerging activities such as learned Unmanned-Aerial-Vehicles (UAVs) video coding which are currently planned, under development, or in the exploration phase. With a focus on UAV video signals, this paper addresses the current status of these preliminary efforts. It also indicates development timelines, summarizes the main technical details, and provides pointers to further points of reference. The exploration experiment shows that the EEV model performs better than the state-of-the-art video coding standard H.266/VVC in terms of perceptual evaluation metric.

Our world is becoming rapidly dependent on data of increasing complexity, diversity, and volume which calls for robust and powerful tools to process such big data. Probabilistic generative models fulfill this goal by learning latent characteristic data relations, especially for the recent emergence of large-scale deep generative models that are able to create realistic content, namely, artificial intelligence-generated content (AIGC). The applications of AIGC span across various domains, and witness rich potential in multimedia content creation, including dialog generation, text-to-speech conversion, image/video generation, and cross-modal content generation.

Abstract Face-based video retrieval (FBVR) is the task of retrieving videos that containing the same face shown in the query image. In this article, we present the first end-to-end FBVR pipeline that is able to operate on large datasets of unconstrained, multi-shot, multi-person videos. We adapt an existing audiovisual recognition dataset to the task of FBVR and use it to evaluate our proposed pipeline. We compare a number of deep learning models for shot detection, face detection, and face feature extraction as part of our pipeline on a validation dataset made of more than 4000 videos. We obtain 97.25% mean average precision on an independent test set, composed of more than 1000 videos. The pipeline is able to extract features from videos at $$\sim $$ ∼ 7 times the real-time speed, and it is able to perform a query on thousands of videos in less than 0.5 s.

Standardization is concerned with interfaces; industry is concerned with systems. This papers brings the evidence brought by the MPEG standardization group to show how, through the proper management of interface evolution, the constituent industries have been able to achieve product and service interoperability, room for differentiation, and opportunities for innovation in the context of the tectonics shift also known as convergence.

This paper gives a brief account of the four Moving Picture Experts Group (MPEG) standards. It includes a summary description of their functionalities and usage. For MPEG-1 and MPEG-2, this paper describes how they are being used to convert old analog applications into digital ones and how new applications are being created. For MPEG-4, the major application areas are recalled. For MPEG-7, the strategic rate for the development of multimedia industry is highlighted.

Digital television is a reality today, but multimedia communications, after years of hype, is still a catchword. Lack of suitable multi-industry standards supporting it is one reason for the unfulfilled promise. The MPEG committee which originated the MPEG-1 and MPEG-2 standards that made digital television possible is currently developing MPEG-4 with wide industry participation. This paper describes how the MPEG-4 standard, with its network-independent nature and application-level features, is poised to become the enabling technology for multimedia communications and will therefore contribute to solve the problems that are hindering multimedia communications.

These days companies from many industry segments are moving towards the adoption of digital technology for upgrading existing or introducing new services. This unstoppable movement prompted by technological progress could have produced the digital replica of the existing incompatible systems put in place in the analog world. It is the merit of MPEG to have provided an integrated audiovisual coding standard to implement this epochal conversion from one technology to another while supporting a universal syntax representing audiovisual information that makes the standard usable for a variety of interoperable applications. The paper presents the approach followed in the development of the MPEG-1 and MPEG-2 standards and explains some of the basic technical elements. An overview of the current MPEG work is also given.>

Demand for interpersonal video and audio communication at bit rates available on basic and subprimary ISDN accesses is growing and it is expected that service implementation will require large numbers of low-cost high-quality equipment. This paper describes the concept and simulation results of a coding scheme of the hybrid (intraframe transform and temporal DPCM) type whose main feature is the possibility of regaining high resolution for slowly changing pictures. Methods for controlling the spatio/temporal resolutions and simulation results are given. A byproduct of the algorithm allows the reduction of the transmission buffer to negligible values.

Several video codec applications are currently considered and there is a danger that digitisation will lead to more incompatibilities than experienced in the analogue era. A video codec architecture is thus proposed having the property to accomodate a wide range of coding algorithms (hybrid scheme), to operate on a wide bitrate range (by means of an adaptive prefilter) and able to deal with different video standards (by integration of postfilter with standards conversion).