Ishan Rajendrakumar Dave* — accepted AI-conference papers

2024

FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition

Ishan Rajendrakumar Dave*, Mamshad Nayeem Rizve*, Mubarak Shah

ECCV 2024poster

"Real-life applications of action recognition often require a fine-grained understanding of subtle movements, e.g., in sports analytics, user interactions in AR/VR, and surgical videos. Although fine-grained actions are more costly to annotate, existing semi-supervised action recognition has mainly…

Cited by 5 Source ↗PDF ↗Scholar ↗

2024

Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets

Ishan Rajendrakumar Dave*, Fabian Caba, Mubarak Shah, Simon Jenni*

ECCV 2024oral

"Temporal video alignment aims to synchronize the key events like object interactions or action phase transitions in two videos. Such methods could benefit various video editing, processing, and understanding tasks. However, existing approaches operate under the restrictive assumption that a suitabl…

Cited by 1 Source ↗PDF ↗Scholar ↗