Loukas Bampis
Papers
21
Total Citations
663
H-Index
13
About
Loukas Bampis is a researcher whose work sits at the intersection of robotics, computer vision, and human-robot interaction, with a particular focus on simultaneous localization and mapping (SLAM) and visual place recognition. His most significant contributions center on the loop closure detection problem — the challenge of enabling autonomous robots to recognize previously visited locations — a capability fundamental to reliable navigation in complex environments. Bampis has approached this problem through multiple innovative lenses, developing probabilistic appearance-based methods, sequence-based algorithms, and vocabulary-driven frameworks, including his influential "Bag of Tracked Words" paradigm, which offers low-complexity yet effective place recognition. His 2022 survey on visual loop closure detection has already accumulated 154 citations, establishing it as an authoritative reference in the field. Beyond robotics, his research extends into multimodal emotion recognition for human-robot interaction, with an active learning framework for audio-visual emotion recognition earning over 114 citations. Collectively, his ten most-cited papers have garnered over 570 citations, reflecting the breadth and sustained relevance of his contributions. His work on unsupervised semantic clustering and dynamic sequence-based SLAM further demonstrates a commitment to advancing autonomous systems capable of intelligent, adaptive perception in real-world settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2An Active Learning Paradigm for Online Audio-Visual Emotion Recognition114 citations · 2019
- 3Assigning Visual Words to Places for Loop Closure Detection76 citations · 2018
- 4
- 5
- 6Unsupervised semantic clustering and localization for mobile robotics tasks33 citations · 2020
- 7
- 8
- 9SeqSLAM with Bag of Visual Words for Appearance Based Loop Closure Detection21 citations · 2018
- 10