A particle filter for bid estimation in ad auctions with periodic ranking observations.
David PardoePeter StonePublished in: AAMAS (2011)
Keyphrases
- particle filter
- state estimation
- importance sampling
- extended kalman filter
- estimation problems
- visual tracking
- bidding strategies
- auction protocol
- object tracking
- particle filtering
- kalman filter
- state space
- appearance model
- sponsored search
- multiple hypotheses
- display advertising
- contextual advertising
- motion model
- monte carlo
- likelihood function
- multi attribute
- mean shift
- observation model
- target tracking
- face tracking
- data association
- sequential monte carlo
- sponsored search auctions
- online auctions
- moving object tracking
- auction mechanisms
- image segmentation
- multiple hypothesis
- estimation accuracy
- robust tracking
- multiple objects
- robust visual tracking
- resource allocation
- abrupt motion
- estimation process
- markov chain monte carlo
- estimation algorithm
- probability distribution
- video sequences
- computer vision
- sealed bid auctions
- rao blackwellized particle filter