Participants are not allowed to modify the training procedure.

We decreased the confidence threshold to 0.1 to increase article and headline The following specifications were used: { resolution: 256, learning rate: 2e-3 }. This limit is binding for common words, e.g., "the". The recognizer is trained using the Supervised Contrastive ("SupCon") loss function [7], a gener-45 In particular, we work with the "outside" SupCon loss formulation We use a MobileNetV3 (Small) encoder pre-trained on ImageNet1k sourced from the timm [19] We use 0.1 as the temperature for Center Cropping, to avoid destroying too much information. C (Small) model that is developed in [2] for character recognition. If multiple article bounding boxes satisfy these rules for a given headline, then we take the highest.

Q6 How many instances are there in total (of each type, if appropriate)?

Generating video stories from text prompts is a complex task. In addition to having high visual quality, videos need to realistically adhere to a sequence of text prompts whilst being consistent throughout the frames.

Although freely accessible, it is provided in individual files for each year, and is difficult to combine in order to analyze spatial or temporal trends.

These target videos may vary widely in complexity of scenes, activities, camera trajectory, etc.