Multimodal

By Amtrak Joe Barr, Kristin Elechko, Mbta Chris Hart. 2018

310 citations recorded by the source corpus.

Subfields: Language and Linguistics, Multimodal Learning

Citations in the corpus

• VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding (2025, unknown): “Table 4: Data mixture in video-centric fine-tuning stage.”
• Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives (2023, unknown): “…(to be performed before s t ); infer if s t is 2) optional or 3) a procedural mistake ; 4) predict missing keysteps (should have been performed before s t but were not); and ground truth or uses a task graph for representation learning [9, 107, 202] and short-term step understanding [9, 36, 202].”