Nowadays the huge amount of video material stored in multimedia repositories makes the search and retrieval of such content a very slow and usually difficult task. The existing video abstraction systems aim to ease the multimedia access problem by providing short versions of the original content which ease the search and navigation process by reducing the time spent in content browsing. There a...

Human motion modeling for animation and VR has reached a level of capturing real motion data from people using various visual and non-visual sensors. However, most of the available systems require special devices and environment, or even attach extra things onto an actor. To realize a personal system, we developed a general type software to acquire arbitrary motion from a video sequence. A 3D a...

We propose a biologically motivated method for creating animations of opening flowers. We simulate the development of petals based on the observation that flower opening is mainly caused by cell expansion. We use an elastic triangular mesh to represent a petal and emulate its growth by developing each triangular region. Our simulation process consists of two steps. The system first grows each t...

In this paper, an interactive dynamic background scene generating and editing system is proposed based on improved motion graph. By analyzing the input motions with limited frame length and their metadata, our system could synthesize a large amount of various motions to yield a composing dynamic background scene with unlimited frame length by connecting the motion pieces through smooth transiti...

In this paper we present a system that can synthesise novel motion sequences from a database of motion capture examples. This is achieved through learning a statistical model from the captured data which enables realistic synthesis of new movements by sampling the original captured sequences. New movements are synthesised by specifying the start and end keyframes. The statistical model identifi...

As the multimedia data increasing exponentially, how to get the video data we need efficiently become so important and urgent. In this paper, a novel method for shot retrieval is proposed, which is based on fuzzy evolutionary aiNet and hybrid features. To begin with, the fuzzy evolutionary aiNet algorithm proposed in this paper is utilized to extract key-frames in a video sequence. Meanwhile, t...

Surveillance video camera captures a large amount of continuous video stream every day. To analyze or investigate any significant events from the huge video data, it is laborious and boring job to identify these events. To solve this problem, a video summarization technique combining foreground objects as well as motion information in spatial and frequency domain is proposed in this paper. We e...

In this paper, we proposed a effective but extensible residual one-dimensional convolution neural network as base network, based on the this network, we proposed four subnets to explore the features of skeleton sequences from each aspect. Given a skeleton sequences, the spatial information are encoded into the skeleton joints coordinate in a frame and the temporal information are present by mul...

In this paper, we present our expressive body-gestures animation synthesis model for our Embodied Conversational Agent(ECA) technology. Our implementation builds upon a full body reach model using a hybrid kinematics solution. We describe the full pipeline of our model that starts from a symbolic description of behaviors, to the construction of a set of keyframes till the generation of the whol...

This paper presents a new method for remote and interactive browsing of long video sequences. The solution is based on interactive navigation in a scalable mega image resulting from a JPEG2000 coded keyframe-based video summary. The presented system is compliant with the new JPEG2000 part 9 “JPIP – JPEG2000 Interactivity, API and Protocol,” which lends itself to working under varying channel co...