MERLOT: Multimodal Neural Script Knowledge Models
arXiv:2106.02636
Abstract
As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech -- in an entirely label-free, self-supervised manner. By pretraining with a mix of both frame-level (spatial) and video-level (temporal) objectives, our model not only learns to match images to temporally corresponding words, but also to contextualize what is happening globally over time. As a result, MERLOT exhibits strong out-of-the-box representations of temporal commonsense, and achieves state-of-the-art performance on 12 different video QA datasets when finetuned. It also transfers well to the world of static images, allowing models to reason about the dynamic context behind visual scenes. On Visual Commonsense Reasoning, MERLOT answers questions correctly with 80.6% accuracy, outperforming state-of-the-art models of similar size by over 3%, even those that make heavy use of auxiliary supervised data (like object bounding boxes). Ablation analyses demonstrate the complementary importance of: 1) training on videos versus static images; 2) scaling the magnitude and diversity of the pretraining video corpus; and 3) using diverse objectives that encourage full-stack multimodal reasoning, from the recognition to cognition level.
project page at https://rowanzellers.com/merlot; NeurIPS 2021 camera ready
References in corpus (10)
- Learning Transferable Visual Models From Natural Language Supervision
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- YouTube-8M: A Large-Scale Video Classification Benchmark
- Interaction Networks for Learning about Objects, Relations and Physics
- How Much Can CLIP Benefit Vision-and-Language Tasks?
- Learning Language-Visual Embedding for Movie Understanding with Natural-Language
- Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling
- RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning
- Mining YouTube - A dataset for learning fine-grained action concepts from webly supervised video data
- Disembodied Machine Learning: On the Illusion of Objectivity in NLP