What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Algorithm
Liangliang Cao mainly focuses on Artificial intelligence, Pattern recognition, Machine learning, World Wide Web and Information retrieval. His Artificial intelligence study frequently draws connections between related disciplines such as Computer vision. His work on Feature extraction, Dimensionality reduction and k-nearest neighbors algorithm is typically connected to Generative model as part of general Pattern recognition study, connecting several disciplines of science.
His Machine learning research is multidisciplinary, incorporating elements of Similarity and Inference. His World Wide Web study combines topics from a wide range of disciplines, such as Topic model and Data science. The various areas that he examines in his Information retrieval study include Annotation, Semantic gap and Scale-invariant feature transform.
His most cited work include:
- Learning Locally-Adaptive Decision Functions for Person Verification (387 citations)
- Spatially Coherent Latent Topic Model for Concurrent Segmentation and Classification of Objects and Scenes (328 citations)
- Large-scale image classification: Fast feature extraction and SVM training (293 citations)
What are the main themes of his work throughout his whole career to date?
Liangliang Cao mostly deals with Artificial intelligence, Pattern recognition, Computer vision, Information retrieval and Machine learning. His Natural language processing research extends to the thematically linked field of Artificial intelligence. His Natural language processing research includes elements of Crowdsourcing and Semantics.
His work on Image texture as part of general Pattern recognition study is frequently connected to TRECVID, therefore bridging the gap between diverse disciplines of science and establishing a new relationship between them. Liangliang Cao has researched Information retrieval in several fields, including Visualization, Data mining, Annotation, Cluster analysis and Social media. His research on Machine learning often connects related topics like Classifier.
He most often published in these fields:
- Artificial intelligence (54.35%)
- Pattern recognition (24.64%)
- Computer vision (16.67%)
What were the highlights of his more recent work (between 2015-2021)?
- Artificial intelligence (54.35%)
- Speech recognition (10.14%)
- Natural language processing (7.97%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Artificial intelligence, Speech recognition, Natural language processing, End-to-end principle and Benchmark. His Artificial intelligence research includes themes of Machine learning, Information retrieval and Pattern recognition. He combines subjects such as Object detection, Pascal and Outlier with his study of Pattern recognition.
Semantics is closely connected to Social media in his research, which is encompassed under the umbrella topic of Natural language processing. The various areas that Liangliang Cao examines in his End-to-end principle study include Sentiment analysis and Classifier. His Benchmark study combines topics in areas such as Ranking and Image.
Between 2015 and 2021, his most popular works were:
- Learning from Noisy Labels with Distillation (234 citations)
- Mining Fashion Outfit Composition Using an End-to-End Deep Learning Approach on Set Data (109 citations)
- Focal Visual-Text Attention for Visual Question Answering (70 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Algorithm
Liangliang Cao mainly investigates Artificial intelligence, Benchmark, Natural language processing, Information retrieval and Pattern recognition. His work deals with themes such as Machine learning and Metadata, which intersect with Artificial intelligence. Liangliang Cao combines subjects such as Ranking and Image with his study of Benchmark.
His studies in Natural language processing integrate themes in fields like Crowdsourcing and Social media. His Social media research is multidisciplinary, incorporating elements of Sentiment analysis, Parsing, Classifier, Semantic learning and Sentence. His Pattern recognition research integrates issues from Object detector, Pascal and Outlier.
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.
