In this paper, we present a keyframe-based human motion capture data retrieval system which uses a wooden doll as the input device. A user inputs a keyframe by posing an artist’s doll with painted joints in front of a stereo camera rig. The system interactively gives real-time feedback on the results of the joint detection and 3D pose reconstruction as the user is positioning and rotating the d...

Our project attempts to create high quality animation that can be easily used by anyone. We use an artists doll to generate the keyframe poses combined with a motion capture database to generate the in-between frames for smoother, life-like motion. The doll has joints painted in different colors and a stereo camera rig is used to determine its joint positions, which in turn is used to calculate...

Bringing together keyframe and motion-timing can be very difficult to control especially when manipulating body parts of a character animation. Both seem are ‘detach’ in their event as keyframe is physically visible, while timing is imperceptible and merely appears as substance of a sequence of keyframes. This paper presents an overview of my doctoral research, which focuses on an approach to c...

Visual lifelogging is a new concept of recording one’s daily life by using wearable camera to automatically capture images of one’s surroundings. Keyframe selection is a crucial process for summarizing lifelog image sequences. In the visual lifelog domain, images are passively captured in predefined time intervals, e.g. one image every 30 seconds. This results in variable visual quality in the ...

In this paper, we present C-KLAM, a Maximum A Posteriori (MAP) estimator-based keyframe approach for SLAM. As opposed to many existing keyframe-based SLAM approaches, that discard information from non-keyframes in order to reduce the computational complexity, the proposed C-KLAM presents a novel and computationally-efficient technique for incorporating most of this information, resulting in imp...

Bag-of-words representation with visual keypoints has recently emerged as an attractive approach for video search. In this paper, we study the degree of improvement when point-to-point (P2P) constraint is imposed on the bag-of-words. We conduct investigation on two tasks: near-duplicate keyframe (NDK) retrieval, and high-level concept classification, covering parts of TRECVID 2003 and 2005 data...

This work presents a browser that supports two strategies for video browsing: the navigation through visual hierarchies and the retrieval of similar images and objects. The input videos are firstly processed by a keyframe extractor to reduce the temporal redundancy and decrease the number of elements to consider. These generated keyframes are hierarchically clustered with the Hierachical Cellul...

In this paper an interactive facial animation system is described The system is built on top of the facial animation system developed by Keith Waters which uses a muscle based face model We built an interactive facial animation system on top of it to produce keyframe animations of a synthetic face model The user creates keyframes interactively by either giving prede ned universal expressions to...

VideoCLEF is a new track for the CLEF 2008 campaign. This track aims to develop and evaluate tasks in analyzing multilingual video content. A pilot of a Vid2RSS task involving assigning thematic class labels to video kicks off the VideoCLEF track in 2008. Task participants deliver classification results in the form of a series of feeds, one for each thematic class. The data for the task are dua...

We present a framework for learning skills from novel types of demonstrations that have been shown to be desirable from a human-robot interaction perspective. Our approach –Keyframe-based Learning from Demonstration (KLfD)– takes demonstrations that consist of keyframes; a sparse set of points in the state space that produces the intended skill when visited in sequence. The conventional type of...