Video understanding basics in Prompt Engineering / GenAI - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main purpose of video understanding in AI?

Imagine you have a video of a soccer game. What does video understanding help AI do with this video?

A Recognize actions, objects, and events happening in the video

B Only extract the audio from the video

C Convert the video into a text document without any analysis

D Change the video colors to black and white

💡 Hint

Think about what you want a smart system to learn from watching a video.

Video understanding means the AI can identify what is happening, like recognizing players, the ball, and actions such as kicking or scoring.

❓ Predict Output

intermediate

Output of frame extraction code snippet

What will be the output of this Python code that extracts frames from a video?

Prompt Engineering / GenAI

import cv2
cap = cv2.VideoCapture('video.mp4')
count = 0
while True:
    ret, frame = cap.read()
    if not ret or count == 3:
        break
    print(f'Frame {count} shape:', frame.shape)
    count += 1
cap.release()

A

Frame 0 shape: (480, 640, 3)
Frame 1 shape: (480, 640, 3)
Frame 2 shape: (480, 640, 3)

B

Frame 0 shape: (640, 480, 3)
Frame 1 shape: (640, 480, 3)
Frame 2 shape: (640, 480, 3)

C

Frame 0 shape: (480, 640)
Frame 1 shape: (480, 640)
Frame 2 shape: (480, 640)

D No output because of error reading video

💡 Hint

Remember that OpenCV reads frames as height x width x channels.

OpenCV frames have shape (height, width, channels). Typical video size is 640x480 pixels with 3 color channels.

❓ Model Choice

advanced

Best model type for action recognition in videos

You want to build an AI that recognizes actions like running or jumping in videos. Which model type is best suited?

A Convolutional Neural Network (CNN) applied only on single images

B Recurrent Neural Network (RNN) processing video frame sequences

C Simple linear regression model

D 3D Convolutional Neural Network (3D CNN) that analyzes spatial and temporal data

💡 Hint

Think about a model that can understand both space (image) and time (video).

3D CNNs process both spatial and temporal information, making them ideal for action recognition in videos.

❓ Metrics

advanced

Choosing the right metric for video classification

You trained a video classification model to label videos into categories. Which metric best shows how well your model predicts the correct category?

A Mean Squared Error (MSE)

B Accuracy

C BLEU score

D Perplexity

💡 Hint

Think about a metric that counts correct predictions out of total predictions.

Accuracy measures the percentage of correct predictions, suitable for classification tasks like video labeling.

🔧 Debug

expert

Debugging a video captioning model output error

You have a video captioning model that generates text descriptions. The output is always empty strings. What is the most likely cause?

A The video frames are too large in resolution

B The optimizer learning rate is too high

C The model's vocabulary is empty or not loaded properly

D The video file format is unsupported

💡 Hint

Think about what the model needs to produce words in captions.

If the vocabulary is missing or empty, the model cannot map outputs to words, resulting in empty captions.