Sciweavers

292 search results - page 15 / 59
» Dead-End Driven Learning
Sort
View

Publication
335views
13 years 2 months ago
Person Re-Identification: What Features are Important?
State-of-the-art person re-identi cation methods seek robust person matching through combining various feature types. Often, these features are implicitly assigned with a single ve...
Chunxiao Liu, Shaogang Gong, Chen Change Loy, Xing...
102
Voted
MLDM
2009
Springer
15 years 7 months ago
An Evidence-Driven Probabilistic Inference Framework for Semantic Image Understanding
This work presents an image analysis framework driven by emerging evidence and constrained by the semantics expressed in an ontology. Human perception, apart from visual stimulus a...
Spiros Nikolopoulos, Georgios Th. Papadopoulos, Io...
92
Voted
AUSDM
2007
Springer
112views Data Mining» more  AUSDM 2007»
15 years 6 months ago
Measuring Data-Driven Ontology Changes using Text Mining
Most current ontology management systems concentrate on detecting usage-driven changes and representing changes formally in order to maintain the consistency. In this paper, we pr...
Majigsuren Enkhsaikhan, Wilson Wong, Wei Liu, Mark...
133
Voted
EMNLP
2004
15 years 1 months ago
Instance-Based Question Answering: A Data-Driven Approach
Anticipating the availability of large questionanswer datasets, we propose a principled, datadriven Instance-Based approach to Question Answering. Most question answering systems ...
Lucian Vlad Lita, Jaime G. Carbonell
TCSV
2008
175views more  TCSV 2008»
15 years 10 days ago
Expandable Data-Driven Graphical Modeling of Human Actions Based on Salient Postures
This paper presents a graphical model for learning and recognizing human actions. Specifically, we propose to encode actions in a weighted directed graph, referred to as action gra...
Wanqing Li, Zhengyou Zhang, Zicheng Liu