Field dossier · from the corpus
Modal
0predicted collisions
Where this field is predicted to collide
No open collisions on this field in the current run.
Most cited work
ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
TALL: Temporal Activity Localization via Language Query
MaPLe: Multi-modal Prompt Learning
Adversarial Cross-Modal Retrieval
Unicoder-VL: A Universal Encoder for Vision and Language by Cross-Modal Pre-Training
MDETR - Modulated Detection for End-to-End Multi-Modal Understanding