
Video Action Recognition Methodology and Proposed Model
0 likes · 10 views · Mar 8, 2025
The app takes a video as input and generates a caption by training a model with spatial, temporal (Optical Flow) features, and text labels from the dataset.

0 likes · 10 views · Mar 8, 2025
The app takes a video as input and generates a caption by training a model with spatial, temporal (Optical Flow) features, and text labels from the dataset.