S. Gong, M. Walter, A. Psarrou, Recognition of temporal structures: learning prior and propagating observation augmented densities via hidden markov states, Proceedings of the IEEE International Conference on Computer Vision, 1999, pp. 157 -- 162. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Detecting lameness using `Re-sampling Condensation' and.. - Roger (Correct)
....the field of temporal modelling (prediction and classification) of objects. Johnson and Hogg [12] use condensation to propagate multiple prediction hypothesis for pedestrian trajectory classification. In this method, object tracking is performed by a separate (deterministic) module. Walter et al. [13,14] show that incorporating current observation information into this scheme gives improved classification results for human trajectory and gesture classification applications. Again, object tracking is performed by a separate module. Black and Jepson [15] use a similar scheme with multiple temporal ....
S. Gong, M. Walter, A. Psarrou, Recognition of temporal structures: learning prior and propagating observation augmented densities via hidden markov states, Proceedings of the IEEE International Conference on Computer Vision, 1999, pp. 157 -- 162.
Learning Pixel-Wise Signal Energy - Understanding Semantics Jeffrey Self-citation (Gong) (Correct)
....can detect non fitting fast change which are subsequently modelled with energy histories in the next section. 3 Recognising Meaningful Change Rapidly changing visual phenomena exhibited by the motion of animated objects typically involve both non rigid deformations [9] and purposeful trajectories [5, 12, 8]. Illumination specularities further complicate the task of understanding scenes from purely visual data. Without higher level knowledge provided in the form of pre learnt object and trajectory models, it is very difficult to interpret framewise data. Indeed, semantics used for understanding ....
....are used as models for classifying new activities as normal(known) or abnormal(unknown) Essentially, semantics are being tied to specific energy histories through supervised learning. Probabilistic trajectory matching provides the mechanism for matching new observations to pre learnt models [7, 2, 5]. Multiple hypotheses are generated to match a backward window on the signal against template windows in the models. The propagation of random samples allows for concurrent hypotheses to be maintained while providing temporal and amplitude scaling for signal matching cross correlation ....
S. Gong, M. Walter, and A. Psarrou. Recognition of temporal structures: Learning prior and propagating observation augmented densities via hidden markov states. In I''V, pages 157-162, Corfu, 1999.
On the Semantics of Visual Behaviour, Structured Events and.. - Gong, Ng, Sherrah Self-citation (Gong) (Correct)
.... as a set of discrete events, each event can be regarded as a sparse state in a factorised state space, for example, in the form of a Hidden Markov Model (HMM) The notion of state transition is then regarded as the temporal structure of relating temporally ordered visual events in space and time [19,21]. Such temporal structures are often only considered to be first order for convenience. State transitions are learned from example sequences of visual events often manually clustered and labelled [20,31,4,6,21,15] Methods for automatic temporal clustering of HMM states have also been proposed ....
....as the temporal structure of relating temporally ordered visual events in space and time [19,21] Such temporal structures are often only considered to be first order for convenience. State transitions are learned from example sequences of visual events often manually clustered and labelled [20,31,4,6,21,15]. Methods for automatic temporal clustering of HMM states have also been proposed [5,30,54,55] Unfortunately, any process which operates on a representation has little, if any, effect on its semantic properties [56] However, a general assumption is often made such that the knowledge of a ....
[Article contains additional citation context not shown here]
S. Gong, M. Walter, and A. Psarrou. Recognition of temporal structures: Learning prior and propagating observation augmented densities via hidden markov states. In IEEE International Conference on Computer Vision, volume 1, pages 157-162, Corfu, Greece, September 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC