chl260

chain-of-table

Code for paper Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

composed_image_retrieval

missing_aware_prompts

Multimodal Prompting with Missing Modalities for Visual Recognition, CVPR'23

vrdu

We identify the desiderata for a comprehensive benchmark and propose Visually Rich Document Understanding (VRDU). VRDU contains two datasets that represent several challenges: rich schema including diverse data types, complex templates, and diversity of layouts within a single document type.

TA3N

[ICCV 2019 (Oral)] Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (PyTorch)