Verifying broadcast video footage means ensuring that contracted network transitions, sponsor logos, and graphics air correctly. However, manually checking through hours of footage to log the exact timestamps of these split-second transitions is inefficient and prone to error. Being able to automatically track when these contracted logos appear is vital for compliance and ad-revenue reporting. The Find Events task on the Abilities tab can act as a compliance tool to determine if a video contains a specific network or sponsor logo and locating those occurrences throughout the timeline. 

For example, when a broadcast switches from the live game to the studio panel, it often plays a brief, prominent graphic featuring the network's logo. A specific segment of footage should be flagged with the label logo if it shows this dedicated, full-screen or highly prominent branding graphic.

We will need to separate normal live gameplay or standard studio camera feeds from the exact moments these specific transition graphics command the screen.

Our expected inputs are videos, and the expected output will be the timestamps identifying exactly when the logo appears throughout the footage.

‍

UI Tutorial

Step 1: Create an Ability

Go to the Abilities tab and select the button Create Ability. Get early access to Abilities here >

Fill out basic information about the ability such as its name and the description of the task itself. Since we are classifying events in a video, select the Task Type as Find Events.

‍

Step 2: Task Configuration

To configure the task, we need to select a dataset for the specific task. If you have already uploaded your videos in a dataset simply select the name of your dataset. However, if you haven’t already done so then select <New Dataset> and upload your videos, label them by identifying when the brand logo appears in the broadcast, and create a label logo in Event Names. 

‍

Step 3: Configuration

Our next step is to configure the prompt, select the model, and image size. For this use case, we recommend using the below prompt and settings for highest accuracy and best results.

‍

Prompt: 

You are an expert broadcast auditor reviewing television and video footage. Your task is to identify moments when a prominent network, sponsor, or production company logo takes over the screen, such as during a transition bumper, sponsor slide, or end-credit title card.

Because the specific brand will change between videos, you must... Get early access to Abilities here >

‍

Step 4: Run Evaluation

To check how well the prompt does against the dataset, our next step is to run the evaluation. If needed, review the examples in your dataset to ensure all necessary images can be used in the evaluation. 

‍

Step 5: Check Evaluation

All evaluations can be reviewed in the Abilities tab by clicking the dropdown arrow next to the associated ability-alias. Evaluations can take around 15-20 minutes to complete based on the size of the dataset.

In addition to the performance, recall, and precision percentages on the abilities tab, you can see a visualization of what the model predicted by revisiting the dataset. Click on the three dots and select “Go to reference dataset”. 

Select one of the videos in the dataset and click on the review button. 

After running the evaluation you can see what the model labelled as logo and compare it to what you labelled. With this, you can improve your prompts and thus improve your accuracy. 

‍

Tips for Accuracy

1. Define "Edge Cases"  The key to high accuracy is a deep understanding of your specific acceptance criteria. In a marketplace context, the line between "acceptable" and "rejected" can be thin. You must be explicitly clear about where that line is drawn.

2. Updating FPS Depending on the size and location of the logo you are trying to find, update the FPS accordingly. For smaller logos use a smaller FPS (3-5) and for larger logos that appear for longer use 6-10.