A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks
원문 초록
Many high-level procedural tasks can be decomposed into sequences of instructions that vary in their order and choice of tools. In the cooking domain, the web offers many partially-overlapping text and video recipes (i.e. procedures) that describe how to make the same dish (i.e. high-level task). Aligning instructions for the same dish across different sources can yield descriptive visual explanations that are far richer semantically than conventional textual instructions, providing commonsense insight into how real-world procedures are structured. Learning to align these different instruction sets is challenging because: a) different recipes vary in their order of instructions and use of ingredients; and b) video instructions can be noisy and tend to contain far more information than text instructions. To address these challenges, we first use an unsupervised alignment algorithm that learns pairwise alignments between instructions of different recipes for the same dish. We then use a graph algorithm to derive a joint alignment between multiple text and multiple video recipes for the same dish. We release the Microsoft Research Multimodal Aligned Recipe Corpus containing 150K pairwise alignments between recipes across 4,262 dishes with rich commonsense information.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Describe Anything Model for Visual Question Answering on Text-rich Images
Assay2Mol: large language model-based drug design using BioAssay context
Beyond Accuracy: Metrics that Uncover What Makes a 'Good' Visual Descriptor
Dataset Distillation via Vision-Language Category Prototype
DRAMA-X: A Fine-grained Intent Prediction and Risk Reasoning Benchmark For Driving
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
토론
이 논문과 연결된 포럼 글이 아직 없습니다.