Otniel-Bogdan Mercea

Machine Learning Researcher @Apple | PhD @MPI_IS,@uni_tue | MSc @EdinburghUni | Ex. @GoogleDeepMind,@GoogleAI,@TU_Muenchen | Multimodal and efficient learning

[Otniel-Bogdan Mercea @MerceaOtniel]

This was a joint work with David Kurzendörfer, @ASophiaKoepke and @zeynepakata. You can find the paper and the code at https://t.co/GKndtRmGbb. (4/4)

[Otniel-Bogdan Mercea @MerceaOtniel]

Excited to share that I’ll be presenting today our work on “Audio-Visual Generalized Zero-Shot Learning using Pre-Trained Large Multi-Modal Models” at the L3D-IVU workshop at @CVPR. Come to poster 125 to find more about our work. (1/4)

[Otniel-Bogdan Mercea @MerceaOtniel]

We propose a new set of features based on CLIP and CLAP embeddings. Additionally, we propose a simple yet effective model that fuses the information from both CLIP and CLAP text encoders for an enhanced text representation. (3/4)

[Thomas Hummel @hummelth_]

Excited to share that I'll be presenting our work on "Video-adverb retrieval with compositional adverb-action embeddings" as an Oral today in beautiful Aberdeen at #BMVC2023 @BMVCconf! 🎉(1/4)

[Intelligent Systems @MPI_IS]

Researching #AI #MachineLearning #Robotics or #HCI? Join our elite #PhD program - a partnership with @uni_stuttgart & @uni_tue! Applications accepted until Nov 15, 2023 at https://t.co/veVpmjl215 #Hiring #Job #KI #Tübingen #Stuttgart

[Explainable Machine Learning @ExplainableML]

At #GCPR23 today? Then come to our poster on "Text-to-feature diffusion for audio-visual few-shot learning" by @MerceaOtniel, @hummelth_, A. Sophia Koepke and @zeynepakata! Find out more about our work here: https://t.co/TRUL7tMGLG

[Explainable Machine Learning @ExplainableML]

Interested in XAI? Do not miss the Explainability in ML workshop!

It will take place March 28-29 in Tübingen (Germany) and will feature talks from prominent researchers in the field.

Check the program here https://t.co/yfjmJhaOE6, and register in advance: few spots remaining!

[Explainable Machine Learning @ExplainableML]

🗓️Sess 6 | 101, 25/10 | afternoon
“Temporal and cross-modal attention for audio-visual zero-shot learning”

@MerceaOtniel* @hummelth_*, A. S. Koepke, @zeynepakata

We leverage temporal context for better and improved audio-visual zero-shot learning!

Blog https://t.co/9ZcsS3SxJF

[Intelligent Systems @MPI_IS]

Want to join this amazing #IMPRSIS community of talented young researchers in the field of #AI #MachineLearning #Robotics & #ComputerVision? Join our #PhD program - a partnership with @uni_stuttgart & @uni_tue! New application round until Nov 1, 2022 https://t.co/veVpmjlzQD

[Explainable Machine Learning @ExplainableML]

If you are at #CVPR2022, come check out one of our six publications!

We have topics ranging from training on partially labelled dataset to (multi-modal) contrastive metric learning and all manners of zero-shot learning!

A quick 🧵 (sorted by date):