What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Information retrieval, Artificial intelligence, TRECVID, Search engine indexing and Image retrieval are his primary areas of study.
His study in the field of Ontology is also linked to topics like Social image.
His studies deal with areas such as Machine learning, Computer vision and Pattern recognition as well as Artificial intelligence.
His Search engine indexing research is multidisciplinary, incorporating elements of Image processing, Ranking, Multimedia and Modality.
His Content-based image retrieval and Visual Word study, which is part of a larger body of work in Image retrieval, is frequently linked to Set, bridging the gap between disciplines.
His research investigates the link between Content-based image retrieval and topics such as Automatic image annotation that cross with problems in Multimedia information retrieval, Semantic interpretation, Semantic gap and Relevance feedback.
His most cited work include:
- Content-based image retrieval at the end of the early years (5505 citations)
- Early versus late fusion in semantic video analysis (649 citations)
- The challenge problem for automated detection of 101 semantic concepts in multimedia (555 citations)
What are the main themes of his work throughout his whole career to date?
His scientific interests lie mostly in Artificial intelligence, Information retrieval, Multimedia, Search engine indexing and Computer vision.
His research in Artificial intelligence focuses on subjects like Machine learning, which are connected to Representation, Relevance feedback and Classifier.
His Information retrieval research is multidisciplinary, incorporating perspectives in Image, Image retrieval, Information visualization and TRECVID.
Image retrieval connects with themes related to Image processing in his study.
His work focuses on many connections between Multimedia and other disciplines, such as Analytics, that overlap with his field of interest in Cultural analytics.
Search engine indexing is closely attributed to Feature extraction in his research.
He most often published in these fields:
- Artificial intelligence (35.85%)
- Information retrieval (35.01%)
- Multimedia (22.97%)
What were the highlights of his more recent work (between 2017-2021)?
- Artificial intelligence (35.85%)
- Machine learning (10.64%)
- Interactive Learning (3.64%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Artificial intelligence, Machine learning, Interactive Learning, Relevance feedback and Information retrieval.
His research in Artificial intelligence tackles topics such as Natural language processing which are related to areas like Pipeline, Feature and Closed captioning.
His work deals with themes such as Classifier, Scalability and Search engine indexing, which intersect with Interactive Learning.
Marcel Worring has included themes like External Data Representation, Mobile device and Key in his Search engine indexing study.
His Relevance feedback research integrates issues from Multimodal learning, Multimedia, State and Human–computer interaction.
His biological study spans a wide range of topics, including Generator and Benchmark.
Between 2017 and 2021, his most popular works were:
- OmniArt: A Large-scale Artistic Benchmark (30 citations)
- BERT for Evidence Retrieval and Claim Verification (23 citations)
- Many Task Learning With Task Routing (23 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
Marcel Worring spends much of his time researching Artificial intelligence, Interactive Learning, Relevance feedback, State and Machine learning.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Hypergraph, Information retrieval and Pattern recognition.
His Information retrieval research incorporates themes from Cognitive neuroscience of visual object recognition, Metadata, Color space, Point and Benchmark.
The concepts of his Interactive Learning study are interwoven with issues in Scalability and Search engine indexing.
The Search engine indexing study combines topics in areas such as Multimedia and Mobile device.
Marcel Worring interconnects Multimodal learning and Relevance in the investigation of issues within Relevance feedback.
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.
