We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlappin
g positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming supervised approaches. Code is made available at https://github.com/pytorch/fairseq/examples/MMPT.
Recent question answering and machine reading benchmarks frequently reduce the task to one of pinpointing spans within a certain text passage that answers the given question. Typically, these systems are not required to actually understand the text o
n a deeper level that allows for more complex reasoning on the information contained. We introduce a new dataset called BiQuAD that requires deeper comprehension in order to answer questions in both extractive and deductive fashion. The dataset consist of 4,190 closed-domain texts and a total of 99,149 question-answer pairs. The texts are synthetically generated soccer match reports that verbalize the main events of each match. All texts are accompanied by a structured Datalog program that represents a (logical) model of its information. We show that state-of-the-art QA models do not perform well on the challenging long form contexts and reasoning requirements posed by the dataset. In particular, transformer based state-of-the-art models achieve F1-scores of only 39.0. We demonstrate how these synthetic datasets align structured knowledge with natural text and aid model introspection when approaching complex text understanding.
