📄️ [19.08] LXMERT
Pre-training Matters
📄️ [19.08] ViLBERT
Interwoven Layers in the Beginning
📄️ [19.08] VisualBERT
Gaze at the Prelude
📄️ [19.08] VL-BERT
Watching from the Sidelines
📄️ [19.09] UNITER
The Song of the Unifiers
📄️ [20.04] Oscar
The Anchors of Oscar
📄️ [20.04] Pixel-BERT
The Language of Pixels
📄️ [20.06] ERNIE-ViL
The Double-Edged Sword of Knowledge
📄️ [20.06] VILLA
The Phantom in the Villa
📄️ [20.12] UNIMO
Intertwined Clues
📄️ [21.01] VinVL
Revisiting Oscar
📄️ [21.02] ViLT
Enter the Scene
📄️ [21.02] VL-T5
Consistent Output
📄️ [21.03] CLIP
Breaking the Dimensional Barrier
📄️ [21.04] MDETR
The Art of Continuity
📄️ [21.07] ALBEF
Pursuing the Pure Path
📄️ [21.08] SimVLM
Simplifying Things
📄️ [21.11] Florence
Renaissance
📄️ [21.11] METER
Vibrant Dashboard
📄️ [22.01] BLIP
Synthetic Text Technology
📄️ [22.04] Flamingo
Richly Illustrated
📄️ [22.12] FLIP
Fast CLIP
📄️ [24.08] xGen-MM
Also Known As BLIP-3