What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
His scientific interests lie mostly in Artificial intelligence, Computer vision, Pattern recognition, Feature extraction and Speech recognition.
His Artificial intelligence research includes elements of Audio signal processing and Machine learning.
His Computer vision research is multidisciplinary, relying on both Mode and Decoding methods.
His Pattern recognition research incorporates elements of Object detection, Algorithm design and Search engine indexing.
His Feature extraction study incorporates themes from Motion, Cognitive neuroscience of visual object recognition and Visual appearance.
His Speech recognition research integrates issues from Wiener filter and Food recognition.
His most cited work include:
- Algorithms and system for segmentation and structure analysis in soccer video (234 citations)
- Structure analysis of soccer video with hidden Markov models (228 citations)
- Speech denoising using nonnegative matrix factorization with priors (224 citations)
What are the main themes of his work throughout his whole career to date?
Ajay Divakaran focuses on Artificial intelligence, Computer vision, Pattern recognition, Multimedia and Feature extraction.
In most of his Artificial intelligence studies, his work intersects topics such as Machine learning.
His research in Computer vision tackles topics such as Search engine indexing which are related to areas like Video sequence.
Ajay Divakaran interconnects Speech recognition, Feature and Feature in the investigation of issues within Pattern recognition.
His Multimedia study combines topics in areas such as Metadata, Index, Video browsing, Video processing and Information retrieval.
His Feature extraction research is multidisciplinary, incorporating perspectives in Audio signal processing, Data compression, Image segmentation and Histogram.
He most often published in these fields:
- Artificial intelligence (61.85%)
- Computer vision (32.13%)
- Pattern recognition (21.69%)
What were the highlights of his more recent work (between 2013-2021)?
- Artificial intelligence (61.85%)
- Machine learning (11.65%)
- Pattern recognition (21.69%)
In recent papers he was focusing on the following fields of study:
Ajay Divakaran mostly deals with Artificial intelligence, Machine learning, Pattern recognition, Information retrieval and Human–computer interaction.
The study incorporates disciplines such as Key and Natural language processing in addition to Artificial intelligence.
He usually deals with Machine learning and limits it to topics linked to Training set and Similarity and Categorization.
His research in the fields of Segmentation overlaps with other disciplines such as Estimation.
The various areas that he examines in his Information retrieval study include Image and Location.
The study incorporates disciplines such as Facial expression recognition and Session in addition to Human–computer interaction.
Between 2013 and 2021, his most popular works were:
- ZERO-SHOT OBJECT DETECTION (93 citations)
- Vpa with integrated object recognition and facial expression recognition (74 citations)
- “Snap-n-Eat” Food Recognition and Nutrition Estimation on a Smartphone (56 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
His main research concerns Artificial intelligence, Machine learning, Discriminative model, Pattern recognition and Information retrieval.
His study connects Natural language processing and Artificial intelligence.
His Machine learning study incorporates themes from Object detection and Shot.
In his study, which falls under the umbrella issue of Discriminative model, Test data generation, Missing data, Speech recognition and Feature learning is strongly linked to Generative model.
The Segmentation and Support vector machine research Ajay Divakaran does as part of his general Pattern recognition study is frequently linked to other disciplines of science, such as Photography and Android, therefore creating a link between diverse domains of science.
His Information retrieval research is multidisciplinary, incorporating elements of Matching, Location and Data mining.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
