In video action recognition, motion is a very crucial clue, which is usually represented by optical flow. However, optical flow is computationally expensive to obtain, which becomes the bottleneck for the efficiency of traditional action recognition ...

This paper presents a novel application of the local ternary patterns to the zoom motion detection problem and its further classification into zoom-in and zoom-out for compressed domain video sequences. The premise of the proposed method is based on ...

With the wide adoption in surveillance video analysis, some pixel-domain analysis methods are not only used in academia but are also garnering the attention of industry. However, because of the increasing data volume of video, how to analyze and browse ...

In this paper, a low complexity video watermarking scheme for H.264 has been presented. Our contribution is to attain lower complexity in embedding procedure and extracting watermark. At the same time, we avoid a bit-rate increase and improve the ...

Many tracking methods often suffer from the drift problems caused by appearance change. Therefore developing a robust online tracker is still a challenging test. Recently, a simple yet effective and efficient tracking algorithm has been proposed by ...

Reducing MP3/AAC bit rate in compressed domain is computationally more efficient than direct transcoding. To compute rate distortion (R-D) table of an audio signal in compressed domain, we propose a new method for estimating the distortion vs. scale ...

With the wide-spread use of digital videos, quality considerations have become essential, and industry demand for video quality measurement standards is rising. In this paper, we proposed a no reference estimation of the coding PSNR for 4K-UHD videos in ...

A small number of randomly generated linear measurements can preserve most of the salient information of one compressible image according to compress sensing theory. Using these measurements as features can greatly improve the speed of detection based ...

With the rapid development of image retrieval technology, personalized image retrieval has attracted widespread attention. On the Internet, a great deal of images are stored and transmitted in a compressed format. In order to improve the accuracy and ...

Saliency detection is widely used to extract the regions of interest in images. Many saliency detection models have been proposed for videos in the uncompressed domain. However, videos are always stored in the compressed domain such as MPEG2, H.264, ...

A new efficient algorithm using the compressed domain features of H.264 INTRA frames is proposed for moving object extraction on huge video surveillance archives. To achieve searching efficiency, we propose to locate moving objects by scrutinizing only ...

In this paper, we propose a novel image retargeting algorithm to resize images based on the extracted saliency information from the compressed domain. Firstly, we utilize DCT coefficients in JPEG bitstream to perform saliency detection with the ...

The temporal segmentation of a video sequence is one of the most important aspects for video processing, analysis, indexing, and retrieval. Most of existing techniques to address the problem of identifying the boundary between consecutive shots have ...

An objective quality assessment method for H.264 high definition (HD) video streams in the compressed domain is presented in this paper. Based on the H.264 open-source codec project JM12.4, we design an efficient system to extract two video features as ...

In this paper, a novel technique for shot boundary detection operating on H.264/AVC-compressed sequences is presented. Due to new and improved coding tools in H.264/AVC, the characteristics of the obtained sequences differ from former video coding ...

This paper proposes a novel scheme that integrates quality access control and tracking of illicit distribution of digital images in a single platform. The goal is achieved by 1 modulating some of the valuable Discrete Cosine Transform DCT coefficients ...

Recent advances in technology have increased the availability of video data, creating a strong requirement for efficient systems to manage those materials. Making efficient use of video information requires that data be accessed in a user-friendly way. ...

A novel semi-fragile watermarking scheme of JPEG image in compressed domain is proposed. A chaotic map model based an authentication generating model is introduced. The DCT-transformed matrix of luminance plane in YCbCr color space is quantized by a ...

A new technique for controlling the bitrate of H.264 encoded sequences is presented. Bitrate control is achieved by dropping frames directly in the compressed domain. The dropped frames are carefully selected so as to either eliminate or cause non ...

A new technique for controlling the bit-rate of H.264 encoded sequences is presented. The technique achieves bit-rate control by dropping frames directly in the compressed domain. The dropped frames are carefully selected so as to either eliminate or ...