HMM-guided frame querying for bandwidth-constrained video search

TL;DR

This paper presents a method combining CNNs and HMMs to efficiently identify key video frames under bandwidth constraints, enabling high accuracy with minimal data transfer.

Contribution

It introduces a novel approach that uses HMM-guided frame querying with CNN scores to reduce bandwidth in remote video search tasks.

Findings

Achieves 98% frame omission without losing classification accuracy.

Effective in identifying temporal regions of interest with sparse sampling.

Demonstrates scalability on ImageNet-VID dataset.

Abstract

We design an agent to search for frames of interest in video stored on a remote server, under bandwidth constraints. Using a convolutional neural network to score individual frames and a hidden Markov model to propagate predictions across frames, our agent accurately identifies temporal regions of interest based on sparse, strategically sampled frames. On a subset of the ImageNet-VID dataset, we demonstrate that using a hidden Markov model to interpolate between frame scores allows requests of 98% of frames to be omitted, without compromising frame-of-interest classification accuracy.