NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning
This work addresses the challenge of video learning without frame-level annotations, which is crucial for handling large-scale video data, though it appears incremental in its approach.
The authors tackled the problem of weakly supervised video learning by proposing a novel learning algorithm with a Viterbi-based loss, which improved action segmentation by up to 10% compared to state-of-the-art methods.
Video learning is an important task in computer vision and has experienced increasing interest over the recent years. Since even a small amount of videos easily comprises several million frames, methods that do not rely on a frame-level annotation are of special importance. In this work, we propose a novel learning algorithm with a Viterbi-based loss that allows for online and incremental learning of weakly annotated video data. We moreover show that explicit context and length modeling leads to huge improvements in video segmentation and labeling tasks andinclude these models into our framework. On several action segmentation benchmarks, we obtain an improvement of up to 10% compared to current state-of-the-art methods.