This paper deals with the semantic enrichment of automatic annotations of images. Since it partially tackles the Semantic Gap Problem, semantic image annotation has received a large attention in the recent years. Nevertheless, the results of existing image annotation approaches are still not sufficient. We propose an original approach combining a priori knowledge (in our case, the WordNet lexic...

Visual recognition (e.g., object, scene and action recognition) is an active area of research in computer vision due to its increasing number of real-world applications such as video (image) indexing and search, intelligent surveillance, human-machine interaction, robot navigation, etc. Effective modeling of the objects, scenes and actions is critical for visual recognition. Recently, bag of vi...

We address the problem of categorizing turn-taking interactions between individuals. Social interactions are characterized by turn-taking and arise frequently in real-world videos. Our approach is based on the use of temporal causal analysis to decompose a space-time visual word representation of video into co-occuring independent segments, called causal sets [1]. These causal sets then serves ...

Bayesian topic models have recently been shown to perform well in word sense induction (WSI) tasks. Such models have almost exclusively used bag-of-words features, and failed to attain improvement by including other feature types. In this paper, we investigate the impact of integrating syntactic and knowledge-based features and show that both parametric and non-parametric models consistently be...

We present a video copy detection system that detects video copy segments based on the task settings and dataset in TRECVID 2010. Contributions of this work are twofold. First, we extract feature-based trajectories from videos, and then model trajectories by a bag of word model. This representation effectively describes information of object movement, and is robust to various visual transformat...

Please cite this article in press as: Y.-G. Jia Vis. Image Understand. (2008), doi:10.101 Bag-of-visual-words (BoW) has recently become a popular representation to describe video and image content. Most existing approaches, nevertheless, neglect inter-word relatedness and measure similarity by bin-to-bin comparison of visual words in histograms. In this paper, we explore the linguistic and onto...

Topic modeling is an unsupervised learning task that discovers the hidden topics in a collection of documents. In turn, discovered can be used for summarizing, organizing, and understanding documents collection. Most existing techniques topic are derivatives Latent Dirichlet Allocation which uses bag-of-word assumption However, bag-of-words models completely dismiss relationships between words....

The Bag-Of-Word (BOW) model uses a fixed length vector of word counts to represent text. Although the model disregards word sequence information, it has been shown to be successful in capturing long range word-word correlations and topic information. In contrast, n-gram models have been shown to be an effective way to capture short term dependencies by modeling text as a Markovian sequence. In ...

Domestic photography has been booming since the introduction of personal devices equipped with cameras like smartphones. As a consequence users struggle in finding relevant pictures in the ever growing photo collections. Content-based image retrieval (CBIR) solves this and takes away burdens like manual tagging. CBIR methods are often inspired by text mining techniques and concepts. In this pro...

Motivated by computer privacy issues, we present the novel problem of document recovery from an index: given only a document’s bag-of-words (BOW) vector or other type of index, reconstruct the original ordered document. We investigate a variety of index types, including count-based BOW vectors, stopwords-removed count BOW vectors, indicator BOW vectors, and bigram count vectors. We formulate th...