What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Computer vision
His primary scientific interests are in Artificial intelligence, Collaborative filtering, Machine learning, Feature extraction and Recommender system.
The various areas that Alan Hanjalic examines in his Artificial intelligence study include Metric, Computer vision and Pattern recognition.
His Collaborative filtering study integrates concerns from other disciplines, such as Data mining and Feature vector.
His work deals with themes such as Adversarial system and Text retrieval, which intersect with Machine learning.
In his research on the topic of Feature extraction, Search engine indexing, Human–computer interaction and Event is strongly related with Multimedia.
Alan Hanjalic combines subjects such as Unary operation and Leverage with his study of Recommender system.
His most cited work include:
- Affective video content representation and modeling (545 citations)
- Collaborative Filtering beyond the User-Item Matrix: A Survey of the State of the Art and Future Challenges (520 citations)
- Shot-boundary detection: unraveled and resolved? (446 citations)
What are the main themes of his work throughout his whole career to date?
Alan Hanjalic focuses on Artificial intelligence, Multimedia, Information retrieval, Machine learning and Computer vision.
Alan Hanjalic focuses mostly in the field of Artificial intelligence, narrowing it down to topics relating to Pattern recognition and, in certain cases, Image retrieval.
His work focuses on many connections between Multimedia and other disciplines, such as World Wide Web, that overlap with his field of interest in Multimedia information retrieval.
In general Information retrieval, his work in Query expansion, Search engine indexing and Search engine is often linked to Set linking many areas of study.
His Collaborative filtering, Recommender system and Relevance study are his primary interests in Machine learning.
His Collaborative filtering research is multidisciplinary, incorporating elements of Ranking and Data mining.
He most often published in these fields:
- Artificial intelligence (36.40%)
- Multimedia (24.40%)
- Information retrieval (23.60%)
What were the highlights of his more recent work (between 2016-2021)?
- Artificial intelligence (36.40%)
- Machine learning (14.40%)
- Recommender system (11.60%)
In recent papers he was focusing on the following fields of study:
His scientific interests lie mostly in Artificial intelligence, Machine learning, Recommender system, Representation and Speech recognition.
Many of his studies involve connections with topics such as Natural language processing and Artificial intelligence.
The concepts of his Machine learning study are interwoven with issues in Standardization and SIMPLE.
Alan Hanjalic studies Recommender system, namely Collaborative filtering.
His studies examine the connections between Speech recognition and genetics, as well as such issues in Closed captioning, with regards to Realization, Generator, Convolution and Feature extraction.
He interconnects Social media, Multimedia and Metric in the investigation of issues within Information retrieval.
Between 2016 and 2021, his most popular works were:
- Adversarial Cross-Modal Retrieval (286 citations)
- From Deterministic to Generative: Multimodal Stochastic RNNs for Video Captioning (125 citations)
- Video Captioning by Adversarial LSTM (85 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Operating system
Artificial intelligence, Machine learning, Stochastic process, Closed captioning and Human–computer interaction are his primary areas of study.
Alan Hanjalic combines Artificial intelligence and Binary code in his studies.
His Machine learning research incorporates elements of Adversarial system, Subspace topology, Classifier and Representation.
His Representation study incorporates themes from Transfer of learning, Visualization, Recurrent neural network and Latent variable.
His Closed captioning research is multidisciplinary, relying on both Speech recognition, Convolution, Realization and Feature extraction.
His research in Human–computer interaction intersects with topics in Annotation and Valence.
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.
