High-level event recognition in unconstrained videos

Abstract

The goal of high-level event recognition is to automatically detect complex high-level events in a given video sequence. This is a difficult task especially when videos are captured under unconstrained conditions by nonprofessionals. Such videos depicting complex events have limited quality control, and therefore, may include severe camera motion, poor lighting, heavy background clutter, and occlusion. However, due to the fast growing popularity of such videos, especially on the Web, solutions to this problem are in high demands and have attracted great interest from researchers. In this paper, we review current technologies for complex event recognition in unconstrained videos. While the existing solutions vary, we identify common key modules and provide detailed descriptions along with some insights for each of them, including extraction and representation of low-level features across different modalities, classification strategies, fusion techniques, etc. Publicly available benchmark datasets, performance metrics, and related research forums are also described. Finally, we discuss promising directions for future research.

Latent topics-based relevance feedback for video retrieval

“…The CBVR problem itself has an unconstrained nature [9,12] because the concept to retrieve is a priori unknown. Moreover, the performance of these methods highly depends on the used training data but in the CBVR application the initialisation and feedback are often too limited to provide a consistent training set.…”

Knowledge based query expansion in complex multimedia event detection

“…Complex or high-level events are defined as 'long-term spatially and temporally dynamic object interactions that happen under certain scene settings' [20] or 'something happening at a given time and in a given location' [3]. Research regarding complex event detection and the semantic gap increased with the benchmark TRECVID.…”

“…Typically, such visual search engines use metadata information such as tags provided with the video, but the information within the video itself can also be extracted by making use of concept detectors. Concepts that can be detected include objects, scenes and actions [20]. Concept detectors are trained by exploiting the commonality between large amounts of training images.…”

“…Our research focuses on which type of knowledge base is best to use in the domain of complex or high-level events, defined as 'long-term spatially and temporally dynamic object interactions that happen under certain scene settings' [20]. Examples of complex events are birthday party, doing homework and doing a bike trick.…”

Wearable Cameras for Real-Time Activity Annotation

“…Event detection has been intensively studied in recent decades and many methods depend on building classifiers of specific instances to infer the events [3]. For example, Lai [5] learns an instance-level event detection model based on video-level labels, and Aarflot [1] applies face detection to reduce the need of ever deleting digital objects from a digital library.…”