Srihari, R. K. 1995 Computational Models for Integrating Linguistic and Visual Information: A Survey. Artificial Intelligence Review 8(5-6):349-369.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....scheme. Finally, we will give some experimental results of the implemented system (section 6) showing the robustness of our approach and a short conclusion (section 7) 2 Related Work In literature the topic of integrating vision and speech understanding is referenced from different viewpoints [21]. The construction of mental pictures [7] can be induced by verbal descriptions or previously seen objects. They are used to reason about scenes which are currently not visible. This is an important aspect in language understanding when spatial knowledge is involved [29, 1, 16] Other systems [13, ....

R. K. Srihari. Computational models for integrating linguistic and visual information: A survey. In Artificial Intelligence Review, 8, pages 349--369, Netherlands, 1994. Kluwer Academic Publishers.

....mental abilities for human communication. Therefore, intuitive human computer interfaces especially have to support these two input modalities. In artificial intelligence, there has been a long tradition to realize these capabilities as separate tasks. But as mentioned by many researchers (e.g. [14]) integrating language and vision has implications on both processing tasks. In particular, a separated approach is inherently error prone because all decisions are exclusively based on one part of the whole input. One possibility to overcome these drawbacks but still using a separated approach is ....

R. K. Srihari. Computational models for integrating linguistic and visual information: A survey. In Artificial Intelligence Review, 8, pages 349--369, Netherlands, 1994. Kluwer Academic Publishers.

....are subjective. The content based image retrieval paradigm was conceived in order to address these limitations. Here retrieval is based on the visual properties of an image such as colour and texture. Though successful to a certain extent this method has its own limitations. Srihari [13] is one of the first researchers to contemplate the notion of a more effective understanding and retrieval of pictures if the two modalities of vision and language are combined. For humans, the correlation of visual information with speech text is a given in that such a correspondence expedites ....

Srihari R.K., "Computational Models for Integrating Linguistic and Visual Information: A Survey, Artificial Intelligence Review, special issue on Integrating Language and Vision", Volume 8, pp. 349--369, 1995.

.... multimodal input systems requires, on the one hand, the processing of single modalities and, on the other hand, the integration of multiple modalities [5] To enable a technical system to coordinate and integrate perceived speech and gestures in their natural flow, two problems have to be solved [23]: The segmentation problem: Given that the system is to process open input, how is the right chunk of information determined that the system takes in for processing at a time How are consecutive chunks linked together The correspondence problem: Given that the system is to integrate ....

. R.K. Srihari. Computational models for integrating linguistic and visual information: a survey. Artificial Intelligence Review 8: 349-369, 1995.

.... systems requires, on the one hand, the processing of single modalities and, on the other hand, the integration of multiple modalities (Coutaz et al. 1995) To enable a technical system to coordinate and integrate perceived speech and gestures in their natural flow, two problems have to be solved (Srihari, 1995): The segmentation problem: Given that the system is to process open input, how is the right chunk of information determined that the system takes in for processing at a time How are consecutive chunks linked together The correspondence problem: Given that the system is to integrate ....

Srihari, R.K. (1995). Computational models for integrating linguistic and visual information: a survey. Artificial Intelligence Review, 8, 349-369.

....the caption. As we shall see later, we extend the use of collateral information in this domain, as well as make the ideas developed in Srihari s thesis suitable for application in other domains. Recently, there has been a lot of academic interest in the Integration of Natural Language and Vision [Srihari, 1995b; McKevitt, 1994; Srihari, 1995a ] One of the objectives of that research effort is to use the interpretation of data in one modality to drive the interpretation of data in the other. We highlight the fact that collateral based vision exploits a reliable hypothesis of scene contents. We obtain ....

Rohini K. Srihari. Computational models for integrating linguistic and visual information: A survey. Artificial Intelligence Review (special issue on integration of NLP and Vision), 8(5):349--369, 1995.

....the caption. As we shall see later, we extend the use of collateral information in this domain, as well as make the ideas developed in Srihari s thesis suitable for application in other domains. Recently, there has been a lot of academic interest in the Integration of Natural Language and Vision [Srihari, 1995b; McKevitt, 1994; Srihari, 1995a ] One of the objectives of that research effort is to use the interpretation of data in one modality to drive the interpretation of data in the other. We highlight the fact that collateral based vision exploits a reliable hypothesis of scene contents. We obtain ....

Rohini K. Srihari. Computational models for integrating linguistic and visual information: A survey. Artificial Intelligence Review (special issue on integration of NLP and Vision), 8(5):349--369, 1995.

No context found.

Srihari, R. K. 1995 Computational Models for Integrating Linguistic and Visual Information: A Survey. Artificial Intelligence Review 8(5-6):349-369.

No context found.

R. Srihari, `Computational models for integrating linguistic and visual information: A survey', Artificial Intelligence Review, 8(5/6), 349--369, (1994).

No context found.

Srihari (1995a). Rohini K. Srihari, "Computational Models for Integrating Linguistic and Visual Information: A Survey," Artificial Intelligence Review, special issue on Integrating Language and Vision, Vol. 8 (5-6), pp.349-369.

No context found.

R. Srihari. Computational models for integrating linguistic and visual information: A survey. Artificial Intelligence Review, special issue on Integrating Language and Vision, 8:349--369, 1995.

No context found.

R. Srihari, `Computational models for integrating linguistic and visual information: A survey', Artificial Intelligence Review, 8(5/6), 349--369, (1994).

No context found.

R. K. Srihari. Computational models for integrating linguistic and visual information: A survey. Artificial Intelligence Review, special issue on Integrating Language and Vision, 8:349--369, 1995.

No context found.

Rohini K. Srihari. Computational Models for Integrating Linguistic and Visual Information: A Survey. Artificial Intelligence Review, 8:349--369, 1994.

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