Free-viewpoint video allows interactive control of the camera viewpoint in video playback using a three-dimensional (3D) scene representation. This paper describes the challenges and the state-of-the-art techniques adopted in developing a free-viewpoint renderer for 3D video production of people. The system requires video streams from a set of fixed or dynamic real-world video cameras and synth...

Video generation and manipulation is an important yet challenging task in computer vision. Existing methods usually lack ways to explicitly control the synthesized motion. In this work, we present a conditional video generation model that allows detailed control over the motion of the generated video. Given the first frame and sparse motion trajectories specified by users, our model can synthes...

Pop Art is the representative of a cultural identity that has been represented as a kind of art in the mid-twentieth century. It is based on the ordinary manifes‌tations of people’s lives, and by concentrating on media and propaganda it has become pervasive in a short time as if it is a newly emerged culture that has appeared not from the inside of community but from outside and by those sociol...

This paper investigates the effects of many parameters, which are crucial for performance of H.264 video coder .H.264 is the latest international video coding standard. It was jointly developed by the video coding expert group (VCEG) of the ITU-T and moving picture expert group (MPEG) of ISO/IEC. The main goals of the H.264 standardization effort have been enhanced compression performance. H.26...

This paper presents a new problem of unpaired face translation between images and videos, which can be applied to facial video prediction and enhancement. In this problem there exist two major technical challenges: 1) designing a robust translation model between static images and dynamic videos, and 2) preserving facial identity during image-video translation. To address such two problems, we g...

In the last third of the twentieth century, various cultural and technological developments have together rendered meaningless one of the key concepts of modern art – that of a medium. However, no new topology of art practice came to replace media-based typology which divides art into painting, works on paper, sculpture, film, video, and so on. The assumption that artistic practice can be neatl...

Image-space free-viewpoint video (FVV) is a framework for representation and coding of sparse multi-view video and subsequent re-rendering from arbitrary viewpoints. It is based on the fundamental concept of storing all information describing a scene’s visual appearance in multi-channel video images. Each pixel’s channels define different attributes of discrete point samples of observed surface...

Video captioning, the task of describing the content of a video, has seen some promising improvements in recent years with sequence-to-sequence models, but accurately learning the temporal and logical dynamics involved in the task still remains a challenge, especially given the lack of sufficient annotated data. We improve video captioning by sharing knowledge with two related directed-generati...

Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short video, it is still very challenging to caption a video containing multiple fine-grained actions with a detailed description. This paper aims to address the cha...

Content based video copy is the method of detecting illegally copied videos by analyzing them and comparing with original content. It extracts options from the original videos and verifies whether a duplication happens or not by looking at the extricated highlights. A state-of-the-art system of video copy detection is evaluated on VCDB to illustrate the limitations of existing techniques. The t...