With the large amounts of video data available, it has become increasingly important to have the ability to quickly search through and browse through these videos. With that in mind, the objective of this project is to facilitate the process of searching through videos for specific content by creating a video search tool, with an immediate goal of automatically performing a hierarchical segment...

Gesture is a non-verbal modality that can contribute crucial information to the understanding of natural language. But not all gestures are informative, and non-communicative hand motions may confuse natural language processing (NLP) and impede learning. People have little difficulty ignoring irrelevant hand movements and focusing on meaningful gestures, suggesting that an automatic system coul...

While physically based approaches have been shown to be eeective for creating graceful and realistic motions, keyframing systems are still the predominant tool for animation. This is due primarily to the control provided to the animator, as well as to the simple fast computation of in-between frames. In contrast, physical simulation systems automate the creation of realistic motion sequences, b...

We describe a robust new approach to extract semantic concept information based on explicitly encoding static image appearance features together with motion information. For high-level semantic concept identification detection in broadcast video, we trained multi-modality classifiers which combine the traditional static image features and a new motion feature analysis method (MoSIFT). The exper...

A s video use expands from entertainment to other domains—such as business, education , and personal applications—these new uses demand new forms of access. For entertainment, the typical user will happily view video linearly, making current access methods— such as fast forward and rewind—sufficient. However, in other applications, users may need to skip around to seek specific video segments. ...

In this paper, we present RKD-SLAM, a robust keyframe-based dense SLAM approach for an RGB-D camera that can robustly handle fast motion and dense loop closure, and run without time limitation in a moderate size scene. It not only can be used to scan high-quality 3D models, but also can satisfy the demand of VR and AR applications. First, we combine color and depth information to construct a ve...