Action recognition basics in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main input type for action recognition models?

Action recognition models analyze data to identify what action is happening. What kind of input data do these models mainly use?

A Single images showing a moment in time

B Text descriptions of actions

C Audio recordings of sounds related to actions

D Sequences of images or video clips showing movement over time

💡 Hint

Think about how you recognize actions yourself. Do you need just one picture or a series of pictures?

Action recognition models need to see how things change over time, so they use sequences of images or video clips, not just single images.

❓ Model Choice

intermediate

Which model type is best suited for capturing temporal information in action recognition?

To understand actions, models must capture how things change over time. Which model type is designed to handle sequences and temporal data?

A Feedforward Neural Networks without loops

B Recurrent Neural Networks (RNNs) or Long Short-Term Memory (LSTM) networks

C Convolutional Neural Networks (CNNs) only

D Support Vector Machines (SVMs)

💡 Hint

Think about models that remember past information to understand sequences.

RNNs and LSTMs are designed to process sequences and keep track of past information, making them suitable for temporal data like videos.

❓ Predict Output

advanced

What is the output shape of a 3D CNN model for action recognition given input shape (batch_size=8, frames=16, height=64, width=64, channels=3) and 10 action classes?

Consider a 3D CNN model that takes video clips as input. The input shape is (8, 16, 64, 64, 3) representing batch size, frames, height, width, and color channels. The model outputs predictions for 10 action classes. What is the shape of the output tensor?

Computer Vision

input_shape = (8, 16, 64, 64, 3)
num_classes = 10
# Model outputs class probabilities for each video in the batch

A (8, 16, 10)

B (16, 10)

C (8, 10)

D (8, 64, 64, 10)

💡 Hint

The model predicts one action class per video clip in the batch.

The model outputs one prediction per video clip, so the output shape is (batch_size, num_classes) = (8, 10).

❓ Metrics

advanced

Which metric is most appropriate to evaluate an action recognition model on a balanced multi-class dataset?

You trained an action recognition model on a dataset with 10 balanced classes. Which metric best measures how well your model predicts the correct action?

A Accuracy

B Root Mean Squared Error (RMSE)

C Mean Squared Error (MSE)

D Precision for one class only

💡 Hint

Think about a metric that counts how many predictions are exactly right out of all predictions.

Accuracy measures the proportion of correct predictions over all predictions, which is suitable for balanced multi-class classification.

🔧 Debug

expert

Why does this action recognition training code raise a shape mismatch error?

Consider this PyTorch training snippet for an action recognition model:

outputs = model(inputs)  # outputs shape: (8, 10)
labels = labels.unsqueeze(1)  # labels shape: (8, 1)
loss = criterion(outputs, labels)

Why does this code raise a shape mismatch error during loss calculation?

A Because labels need to be a 1D tensor of shape (8,) for CrossEntropyLoss

B Because outputs should have shape (8, 1) to match labels

C Because inputs and labels have different batch sizes

D Because criterion expects labels to be one-hot encoded

💡 Hint

Check the expected label shape for PyTorch's CrossEntropyLoss.

PyTorch's CrossEntropyLoss expects labels as a 1D tensor with class indices, not as a 2D tensor. Unsqueezing labels adds an extra dimension causing mismatch.