2 papers
cs.CV2026
TubeLite: Lightweight Multi-Actor Spatio-Temporal Action Detection
Ali Soltaninezhad, Melissa Cote, Alejandro Rico Espinosa +2
Spatio-temporal action detection in videos requires jointly localizing actors in space and identifying action boundaries over time. A common challenge is constructing temporally st…
cs.CV2025
Exploring text-to-image generation for historical document image retrieval
Melissa Cote, Alexandra Branzan Albu
Attribute-based document image retrieval (ABDIR) was recently proposed as an alternative to query-by-example (QBE) searches, the dominant document image retrieval (DIR) paradigm. O…