Learn More
As compared to the conventional RGB or gray-scale images , multispectral images (MSI) can deliver more faithful representation for real scenes, and enhance the performance of many computer vision tasks. In practice, however, an MSI is always corrupted by various noises. In this paper we propose an effective MSI denoising approach by combi-natorially(More)
The robust detection of small targets is one of the key techniques in infrared search and tracking applications. A novel small target detection method in a single infrared image is proposed in this paper. Initially, the traditional infrared image model is generalized to a new infrared patch-image model using local patch construction. Then, because of the(More)
Event detection from real surveillance videos with complicated background environment is always a very hard task. Different from the traditional retrospective and interactive systems designed on this task, which are mainly executed on video fragments located within the event-occurrence time, in this paper we propose a new interactive system constructed on(More)
In the first part of this three-part report we describe our system and novel approaches used in the TRECVID 2013 Multimedia Event Detection (MED) and Multimedia Event Recounting (MER) tasks. A separate section of the report (SIN) details methods and results for the Semantic Indexing task. The final section (SED) describes our approaches and results on the(More)
Interaction recognition is an important part of action recognition and has various applications such as surveillance systems, human computer interface, and machine intelligence. In this paper, we propose a novel group-sparsity-optimization-based feature selection model for complex interaction recognition. Firstly multiple local and global features are(More)
Low-rank tensor factorization (LRTF) provides a useful mathematical tool to reveal and analyze multi-factor structures underlying data in a wide range of practical applications. One challenging issue in LRTF is how to recover a low-rank higher-order representation of the given high dimensional data in the presence of outliers and missing entries, i.e., the(More)
Multimedia event detection (MED) is a retrieval task with the goal of finding videos of a particular event in a large scale internet video archive, given example videos and text descriptions. Nowadays, different multimodal fusion schemes of low-level and high-level features are extensively investigated and evaluated for MED. For most of events in MED,(More)
Detecting complex events in a large video collection crawled from video web-sites is a challenging task. When applying directly good image-based feature representation, e.g., HOG, SIFT, to videos, we have to face the problem of how to pool multiple frame feature representations into one feature representation. In this paper, we propose a novel(More)