Oswald Lanz

Oswald Lanz is a Research Scientist at Fondazione Bruno Kessler (FBK) and former head of the computer vision research unit of FBK. His research interests are mainly in the area of Computer Vision and Machine Learning, more recently with focus on video representation learning (see below). Earlier research included people tracking, audio-visual tracking, pose estimation and group detection for behavior analysis. Oswald holds a number of international patents on video tracking.

NEWS

2019.12: GSM is state of the art in action recognition.

2019.12: Journal Paper accepted at IEEE Transactions on Image Processing.

2019.11: I gave an invited talk at ICCV'19 Egocentric Perception, Interaction and Computing workshop in Seoul, Korea.

2019.11: Let's welcome Alex, new PhD student on the topic of video question answering.

2019.07: Paper accepted at ICCV'19 main program. 

2019.07: I gave a seminar Learning to Recognize Actions in Video at Siena Artificial Intelligence Lab.

2019.06: Swathikiran defended his PhD thesis and graduated with cum laude mark. Congrats to my first PhD graduate!

2019.06: We ranked 3rd in the CVPR'19 EPIC Kitchens Action Recognition challenge, behind teams from Baidu and Facebook AI. Tech Report available here.

2019.06: I gave a seminar on our work on action recognition at FBK Spring of AI seminar series.

2019.04: Paper accepted at ICIP'19 main program.

2019.02: Paper accepted at CVPR'19 main program.

2019.02: Paper accepted at ICASSP'19 main program.

2019.01: Journal Paper accepted at ACM MultiMedia.

2019.01: Journal Paper accepted at Intelligenza Artificiale special issue on selected papers of AI*IA 2018 conference.

1. Xompero, Alessio; Lanz, Oswald; Cavallaro, Andrea,
   A spatio-temporal multi-scale binary descriptor,
   in «IEEE TRANSACTIONS ON IMAGE PROCESSING»,
   2020
   , pp. 1 -
   14
2. Qian, Xinyuan; Brutti, Alessio; Lanz, Oswald; Omologo, Maurizio; Cavallaro, Andrea,
   Multi-speaker tracking from an audio-visual sensing device,
   in «IEEE TRANSACTIONS ON MULTIMEDIA»,
   vol. 21,
   n. 10,
   2019
   , pp. 2576 -
   2588
3. Sudhakaran, Swathikiran; Lanz, Oswald,
   Top-down attention recurrent VLAD encoding for action recognition in videos,
   in «INTELLIGENZA ARTIFICIALE»,
   vol. 13,
   n. 1,
   2019
   , pp. 107 -
   118
4. Lanz, Oswald; Brutti, Alessio; Xompero, Alessio; Qian, Xinyuan; Omologo, Maurizio; Cavallaro, Andrea,
   Accurate Target Annotation in 3D from Multimodal Streams,
   Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP),
   2019
   , (IEEE International Conference on Acoustics, Speech, and Signal Processing,
   Brighton, UK,
   12 - 17 May, 2019)
5. Sudhakaran, Swathikiran; Escalera, Sergio; Lanz, Oswald,
   LSTA: Long Short-Term Attention for Egocentric Action Recognition,
   Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR),
   2019
   , pp. 9954-
   9963
   , (IEEE Computer Society Conference on Computer Vision and Pattern Recognition,
   Long Beach, CA,
   16 - 20 June, 2019)
6. Ilyes Lakhal, Mohamed; Lanz, Oswald; Cavallaro, Andrea,
   Learnable masks for pose-guided view synthesis,
   Proceedings of the IEEE International Conference on Image Processing (ICIP),
   2019
   , (IEEE International Conference on Image Processing,
   Taipei, Taiwan,
   22-25 September)
7. Ilyes Lakhal, Mohamed; Lanz, Oswald; Cavallaro, Andrea,
   View-LSTM: Novel-View Video Synthesis Through View Decomposition,
   IEEE International Conference on Computer Vision,
   2019
   , pp. 7577-
   7587
   , (ICCV,
   Seoul,
8. Sudhakaran, Swathikiran; Lanz, Oswald,
   An Analysis of Deep Neural Networks with Attention for Action Recognition from a Neurophysiological Perspective,
   CVPR19 Workshop - Mutual benefits of cognitive and computer vision,
   2019
   , (CVPR19 Workshop - Mutual benefits of cognitive and computer vision,
   Long Beach, CA,
   16 June, 2019)
9. Sudhakaran, Swathikiran; Escalera, Sergio; Lanz, Oswald,
   FBK-HUPBA Submission to the EPIC-Kitchens 2019 Action Recognition Challenge,
   In this report we describe the technical details of our submission to the EPIC-Kitchens 2019 action recognition challenge. To participate in the challenge we have developed a number of CNN-LSTA [3] and HF-TSN [2] variants, and submitted predictions from an ensemble compiled out of these two model families. Our submission, visible on the public leaderboard with team name FBK-HUPBA, achieved a top-1 action recognition accuracy of 35.54% on S1 setting, and 20.25% on S2 setting.,
   2019
10. Sudhakaran, Swathikiran; Escalera, Sergio; Lanz, Oswald,
    Gate-Shift Networks for Video Action Recognition,
    2019

Pages