In this paper, we address the challenging problem of efficient temporal activity detection in untrimmed long videos. While most recent work has focused and advanced the detection accuracy, the inference time can take seconds to minutes in processing each single video, which is too slow to be useful in real-world settings. This motivates the proposed budget-aware framework, which learns to perform activity detection by intelligently selecting a small subset of frames according to a specified time budget. We formulate this problem as a Markov decision process, and adopt a recurrent network to model the frame selection policy. We derive a recurrent policy gradient based approach to approximate the gradient of the non-decomposable and non-differentiable objective defined in our problem. In the extensive experiments, we achieve competitive detection accuracy, and more importantly, our approach is able to substantially reduce computation time and detect multiple activities with only 0.35s for each untrimmed long video.
This paper formulates and presents a solution to the new problem of budgeted semantic video segmentation. Given a video, the goal is to accurately assign a semantic class label to every pixel in the video within a specified time budget. Typical approaches to such labeling problems, such as Conditional Random Fields (CRFs), focus on maximizing accuracy but do not provide a principled method for satisfying a time budget. For video data, the time required by CRF and related methods is often dominated by the time to compute low-level descriptors of supervoxels across the video. Our key contribution is the new budgeted inference framework for CRF models that intelligently selects the most useful subsets of descriptors to run on subsets of supervoxels within the time budget. The objective is to maintain an accuracy as close as possible to the CRF model with no time bound, while remaining within the time budget. Our second contribution is the algorithm for learning a policy for the sparse selection of supervoxels and their descriptors for budgeted CRF inference. This learning algorithm is derived by casting our problem in the framework of Markov Decision Processes, and then instantiating a state-of-the-art policy learning algorithm known as Classification-Based Approximate Policy Iteration. Our experiments on multiple video datasets show that our learning approach and framework is able to significantly reduce computation time, and maintain competitive accuracy under varying budgets.