CVJul 31, 2019

Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition

arXiv:1907.13369v2135 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of efficient and accurate video classification for computer vision applications, though it is an incremental improvement over existing learning-based approaches.

The paper tackles the problem of frame sampling for untrimmed video recognition by developing a multi-agent reinforcement learning (MARL) strategy, which outperforms hand-crafted methods and achieves state-of-the-art results on datasets like YouTube Birds and YouTube Cars.

Video Recognition has drawn great research interest and great progress has been made. A suitable frame sampling strategy can improve the accuracy and efficiency of recognition. However, mainstream solutions generally adopt hand-crafted frame sampling strategies for recognition. It could degrade the performance, especially in untrimmed videos, due to the variation of frame-level saliency. To this end, we concentrate on improving untrimmed video classification via developing a learning-based frame sampling strategy. We intuitively formulate the frame sampling procedure as multiple parallel Markov decision processes, each of which aims at picking out a frame/clip by gradually adjusting an initial sampling. Then we propose to solve the problems with multi-agent reinforcement learning (MARL). Our MARL framework is composed of a novel RNN-based context-aware observation network which jointly models context information among nearby agents and historical states of a specific agent, a policy network which generates the probability distribution over a predefined action space at each step and a classification network for reward calculation as well as final recognition. Extensive experimental results show that our MARL-based scheme remarkably outperforms hand-crafted strategies with various 2D and 3D baseline methods. Our single RGB model achieves a comparable performance of ActivityNet v1.3 champion submission with multi-modal multi-model fusion and new state-of-the-art results on YouTube Birds and YouTube Cars.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes