Event processing under uncertainty
Proceedings of the 6th ACM International Conference on Distributed Event-Based Systems
Combining per-frame and per-track cues for multi-person action recognition
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
Modeling complex temporal composition of actionlets for activity prediction
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
A Markov logic framework for recognizing complex events from multimodal data
Proceedings of the 15th ACM on International conference on multimodal interaction
Learning and parsing video events with goal and intent prediction
Computer Vision and Image Understanding
| Hi-index | 0.00 |
This paper is about detecting and segmenting interrelated events which occur in challenging videos with motion blur, occlusions, dynamic backgrounds, and missing observations. We argue that holistic reasoning about time intervals of events, and their temporal constraints is critical in such domains to overcome the noise inherent to low-level video representations. For this purpose, our first contribution is the formulation of probabilistic event logic (PEL) for representing temporal constraints among events. A PEL knowledge base consists of confidence-weighted formulas from a temporal event logic, and specifies a joint distribution over the occurrence time intervals of all events. Our second contribution is a MAP inference algorithm for PEL that addresses the scalability issue of reasoning about an enormous number of time intervals and their constraints in a typical video. Specifically, our algorithm leverages the spanning-interval data structure for compactly representing and manipulating entire sets of time intervals without enumerating them. Our experiments on interpreting basketball videos show that PEL inference is able to jointly detect events and identify their time intervals, based on noisy input from primitive-event detectors.