What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Computer vision
- Machine learning
The scientist’s investigation covers issues in Artificial intelligence, Computer vision, Machine learning, Pattern recognition and Feature extraction.
His work often combines Artificial intelligence and Action recognition studies.
In Computer vision, Ivan Laptev works on issues like Pattern recognition, which are connected to Aerial imagery and Edge extraction.
His study on Discriminative model is often connected to Scripting language as part of broader study in Machine learning.
The Pattern recognition study combines topics in areas such as Video tracking, Motion compensation and 3D single-object recognition.
His biological study spans a wide range of topics, including Motion and Gesture recognition.
His most cited work include:
- Learning realistic human actions from movies (3082 citations)
- Recognizing human actions: a local SVM approach (2910 citations)
- On Space-Time Interest Points (2261 citations)
What are the main themes of his work throughout his whole career to date?
Ivan Laptev mainly investigates Artificial intelligence, Computer vision, Machine learning, Pattern recognition and Object.
Ivan Laptev integrates many fields in his works, including Artificial intelligence and Action recognition.
His studies deal with areas such as Annotation and Classifier as well as Machine learning.
His Pattern recognition study incorporates themes from Cognitive neuroscience of visual object recognition, Viola–Jones object detection framework and Leverage.
His Object research is multidisciplinary, incorporating perspectives in Pairwise comparison, State, Heuristic and Flow network.
His Support vector machine research is multidisciplinary, relying on both Contextual image classification and Histogram.
He most often published in these fields:
- Artificial intelligence (83.72%)
- Computer vision (38.37%)
- Machine learning (22.67%)
What were the highlights of his more recent work (between 2018-2021)?
- Artificial intelligence (83.72%)
- Object (18.02%)
- Machine learning (22.67%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Object, Machine learning, Natural language processing and Human–computer interaction.
His study in Artificial intelligence is interdisciplinary in nature, drawing from both Task analysis and Computer vision.
His Object research includes elements of Probabilistic logic, Image retrieval and Metric.
His Image retrieval research is multidisciplinary, incorporating elements of Natural language understanding and Pattern recognition.
His work investigates the relationship between Machine learning and topics such as Robot that intersect with problems in Real image.
The Natural language processing study combines topics in areas such as End-to-end principle and Supervised learning.
Between 2018 and 2021, his most popular works were:
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips (117 citations)
- Learning Joint Reconstruction of Hands and Manipulated Objects (101 citations)
- End-to-End Learning of Visual Representations From Uncurated Instructional Videos (98 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Computer vision
- Machine learning
His primary areas of study are Artificial intelligence, Computer vision, Object, Natural language processing and Embedding.
His research investigates the link between Artificial intelligence and topics such as Task analysis that cross with problems in Human–computer interaction.
His research integrates issues of Tree and Monte Carlo tree search in his study of Computer vision.
His studies deal with areas such as Robot, Robotics, Machine learning and Task as well as Object.
His Natural language processing study combines topics in areas such as Supervised learning, Segmentation and Training set.
His studies in Embedding integrate themes in fields like Information retrieval, Natural language, Predicate and CLIPS.
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.
