Learning Latent Temporal Structure for Complex Event Detection pdf

... Learning Latent Temporal Structure for Complex Event Detection ∗ Kevin Tang Li Fei-Fei Daphne Koller Computer Science Department, Stanford University {kdtang,feifeili,koller}@cs.stanford.edu Abstract In ... account for this by representing videos as sequences of fixed length temporal segments. Weakly-labeled complex events that are not temporally localized. Our model is flex...

Ngày tải lên: 30/03/2014, 16:20

... subevents across multiple complex events, we generated two complex events with a common subevent tree and compared the performance with and without shared optimization. Each complex event has 3 and op- erators, ... generated the event. • event id is an identifier assigned to each event instance. It can be made unique for every event instance or set to a function of event at...

Ngày tải lên: 19/02/2014, 18:20

... that there is no need for unusual event training data for our approach. For the un- supervised HMM, there is no need for training data. The percentage of frames for unusual events in the test sequence is ... Two standard HMM models, one for usual events and one for unusual events, are trained using manually labeled training data according to E quation 1. For testing, the ev...

Ngày tải lên: 19/02/2014, 18:20

... that were used to tag raw text corpus for DLM training: (1) a method for headword detection, and (2) an unsu- pervised learning method for dependency structure acquisition. In order to classify ... 0. For both DLM_1 and DLM_2, models with the parsing weight achieve better performance; we 7 For a detailed description of the baseline trigram model, see Gao et al. (2002...

Ngày tải lên: 17/03/2014, 06:20

... although general terms correspond to events in different periods (i.e., November 2004 and November 2008). Temporal information has to be taken into consideration for event detection. Another important ... developped an online Chi- nese large-scale event search engine based on this work, visit http://sewm.pku.edu.cn/eventsearch for more details. 8 For each event in our golden sta...

Ngày tải lên: 23/03/2014, 14:20

... in Fig.2(B). For GAE, we select the spatial basis covering the whole frame. For LAE, we extract the temporal or spatio -temporal basis that contains spatio -temporal contextual information, such as ... spatio -temporal 3D bricks, then extract MHOF from each unit. To handle different local abnormal events (LAE) and global abnormal events (GAE), we propose several bases with various sp...

Ngày tải lên: 30/03/2014, 16:20

... 2008. c 2008 Association for Computational Linguistics A Discriminative Latent Variable Model for Statistical Machine Translation Phil Blunsom, Trevor Cohn and Miles Osborne School of Informatics, University ... accounts for spurious ambiguity without altering the model structure or ar- bitrarily selecting one derivation. Instead we model the translation distribution with a latent...

Ngày tải lên: 23/03/2014, 17:20

... data. Finally we compared our co-training perfor- mance with supervised learning. For supervised learning, all labeled utterances except for the test set are used for training. We used most confi- dent ... co-training is how to select informative samples. Active learning ap- proaches, such as Muslea et al. (2000), can gener- ally select more informative samples, for example, sample...

Ngày tải lên: 23/03/2014, 16:21

... describes multiple events. language text, extract the relevant arguments of the event, and represent the extracted information into a structured form (Grishman, 1997). The types of events to extract ... document that refer to the event in question. Sec- ond, extract event arguments from these sentences and finally represent the extracted information of the event in a structured form. Pa...

Ngày tải lên: 20/02/2014, 12:20

... of the Association for Computational Linguistics, pages 69–72, Avignon, France, April 23 - 27 2012. c 2012 Association for Computational Linguistics A Support Platform for Event Detection using ... ripe for mining. As such, or- ganisations are increasingly targeting micro-blogs for monitoring purposes, whether it is to gauge product acceptance, detect events such as traffic jams,...

Ngày tải lên: 08/03/2014, 21:20