In this paper we propose an efficient and robust method to automatically discover unknown short video repeats with arbitrary lengths, from a few seconds to a few minutes, from large video databases or streams. The proposed method consists of non-uniform video segmentation, self-similarity analysis, locality sensitive hashing, and video repeat boundary refinement. In order to achieve efficient and accurate processing feature extraction and similarity measure are performed at two levels: video frame level and video segment level. Experiments are conducted on 12 hour CNN/ABC news, and 12 hour documentaries (Discovery and National Geography), high recall and precision of 98% - 99% have been achieved. Video repeats' boundaries can be located within several frames. Applying the proposed method for video structure analysis is also briefly discussed.

This paper aims at repeat clip mining and knowledge discovery from video data. A unified approach is proposed to detect both unknown video repeats and known video clips of arbitrary length. Two detectors in a cascade structure are employed to achieve fast and accurate detection, and a reinforcement learning approach is adopted to efficiently maximize detection accuracy. In this approach very short video repeats (<1 s) and long ones can be detected by a single process, while overall accuracy remains high. Since video segmentation is essential for repeat detection, performance analysis is also conducted for several segmentation methods. Furthermore we propose a method to analyze video syntactical structure based on short video repeats detection. Experimental results on news videos demonstrate that identifying short video repeats is an effective way for video structure discovery and syntactical segmentation

Identifying short repeated video clips, such as news program logo, station logo, TV commercials, etc., from broadcasting video databases or streams is important for video content indexing, personalization as well as monitoring. In this demo system we present the following two functions: 1) automatically identifying variable length unknown repeated clips and known reference clips from video collections or steams; 2) visualize temporal distribution of repeated short video clips and analyze video structure based them. Experiment has been conducted on 12 hour CNN and ABC news videos, and excellent results have been achieved in both short repeated video clip identification and news video structure analysis.

Scale estimation is important in image and vision computing. We propose in this paper an invariant salient region selection and scale normalization method which is robust to rotation, scaling, translation and cropping. This new method is based on the first and second order invariant geometric moments calculated from an intensity difference map. The first-order moments are used to obtain invariant circular regions for different scale hypotheses, while a second-order moment is chosen as region descriptor to select the most salient scale. The image is normalized by scale of the selected salient region. Experiments demonstrate effectiveness of this method

In this paper we propose a novel space-time color feature representation for video shot and apply it to content identification. In this representation the shot is cut into k equal size segments, and each segment is represented by a blending image formed through averaging the pixels' values of each frame in this segment along time direction. Each blending image is then divided into equal size blocks, and two color patterns named major and minor colors among mean R,G,B are extracted for each block. Hence each shot can be represented by a fixed-length string. The experiment shows this representation is not only robust to image quality reduction, frame size and frame rate change, but also to color distortion such as brightness/contrast adjustment. We also give a video similarity measure based on this color feature to identify shot chunks. We conducted experiment on 100 video clips, and quite low error rates can be achieved when identifying small size shot chunks with significant color distortion. From the experiment we believe that this color feature is a compact and robust representation for video content, and effective for content identification.