Amitabha Mukerjee

Learn More
Most geometric models are quantitative, making it diffiiult to abstract the underlying spatial information needed for tasks such as planning, learning or vision. Furthermore, the precision used in a typical quantitative system often exceeds the actual accuracy of the data. In this work we describe a systematic representation that builds spatial maps based(More)
Complex Predicates or CPs are multiword complexes functioning as single verbal units. CPs are particularly pervasive in Hindi and other IndoAryan languages, but an usage account driven by corpus-based identification of these constructs has not been possible since single-language systems based on rules and statistical approaches require reliable tools (POS(More)
Occlusions are a central phenomenon in multiobject computer vision. However, formal analyses (LOS14, ROC20) proposed in the spatial reasoning literature ignore many distinctions crucial to computer vision, as a result of which these algebras have been largely ignored in vision applications. Two distinctions of relevance to visual computation are (a) whether(More)
Algorithms for nonlinear dimensionality reduction (NLDR) find meaningful hidden low-dimensional structures in a high-dimensional space. Current algorithms for NLDR are Isomaps, Local Linear Embedding and Laplacian Eigenmaps. Isomaps are able to reliably recover lowdimensional nonlinear structures in high-dimensional data sets, but suffer from the problem of(More)
Tracking multiple agents in a monocular visual surveillance system is often challenged by the phenomenon of occlusions. Agents entering the field of view can undergo two different forms of occlusions, either caused by crowding or due to obstructions by background objects at finite distances from the camera. The agents are primarily detected as foreground(More)
Given source text in several languages, can one answer queries in some other language, without translating any of the sources into the language of the questioner? While this task seems extremely difficult at first sight, it is possible that the ongoing UN sponsored Universal Networking Language (UNL) proposal may hold some clues towards achieving this(More)
We present a bilingual syntactic parser that operates on input strings from Hindi and English, as well as code-switching strings drawing upon the two languages. Using the HPSG formalism, we develop grammars for Hindi and English, as well as for the Hindi-English CodeSwitching variety (HECS), resulting from contact between these languages in the Indian(More)