Text to Video Retrieval

AbstractLeveraging large-scale unlabeled web videos such as instructional videos for pre-training followed by task-specific finetuning has become the de facto approach for many video-and-language tasks. However, these instructional videos are …...

AbstractTraining an effective video-and-language model intuitively requires multiple frames as model inputs. However, it is unclear whether using multiple frames is beneficial to downstream tasks, and if yes, whether the …...