activity
20222026
most citedGraph2Vid: Flow graph to Video Grounding for Weakly-supervised Multi-Step Localization

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CV2026

No Hard Negatives Required: Concept Centric Learning Leads to Compositionality without Degrading Zero-shot Capabilities of Contrastive Models

Hai X. Pham, David T. Hoffmann, Ricardo Guerrero +1

Contrastive vision-language (V&L) models remain a popular choice for various applications. However, several limitations have emerged, most notably the limited ability of V&L models…