Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning

2021-04-06 · Pramod Chunduri, Jaeho Bang, Yao Lu, Joy Arulraj

Detection and localization of actions in videos is an important problem in practice. State-of-the-art video analytics systems are unable to efficiently and effectively answer such action queries because actions often involve a complex interaction between objects and are spread across a sequence of frames; detecting and localizing them requires computationally expensive deep neural networks. It is also important to consider the entire sequence of frames to answer the query effectively. In this paper, we present ZEUS, a video analytics system tailored for answering action queries. We present a novel technique for efficiently answering these queries using deep reinforcement learning. ZEUS trains a reinforcement learning agent that learns to adaptively modify the input video segments that are subsequently sent to an action classification network. The agent alters the input segments along three dimensions - sampling rate, segment length, and resolution. To meet the user-specified accuracy target, ZEUS's query optimizer trains the agent based on an accuracy-aware, aggregate reward function. Evaluation on three diverse video datasets shows that ZEUS outperforms state-of-the-art frame- and window-based filtering techniques by up to 22.1x and 4.7x, respectively. It also consistently meets the user-specified accuracy target across all queries.

📄 PDF Abstract BibTeX arXiv:2104.06142

Code (0)

등록된 구현이 없습니다.

Tasks

Action Classification Action DetectionAction LocalizationDeep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos

2020-04-15 · Guillaume Vaudaux-Ruth, Adrien Chan-Hon-Tong, Catherine Achard

Summarizing video content is an important task in many applications. This task can be defined as the computation of the ordered list of actions present in a video. Such a list could be extracted using action detection al…

Action Detection Action Spotting Deep Reinforcement Learning reinforcement-learning+2

Learning to Play 7 Wonders Duel Without Human Supervision

2024-06-02 · Giovanni Paolini, Lorenzo Moreschini, Francesco Veneziano, Alessandro Iraci

This paper introduces ZeusAI, an artificial intelligence system developed to play the board game 7 Wonders Duel. Inspired by the AlphaZero reinforcement learning algorithm, ZeusAI relies on a combination of Monte Carlo T…

Board Games reinforcement-learning

One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video

2018-06-29 · Wonjoon Goo, Scott Niekum

Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making cor…

One-Shot Learning Reinforcement Learning Task 2

Actor-centered Representations for Action Localization in Streaming Videos

2021-04-29 · Sathyanarayanan N. Aakur, Sudeep Sarkar

Event perception tasks such as recognizing and localizing actions in streaming videos are essential for scaling to real-world application contexts. We tackle the problem of learning actor-centered representations through…

Action Localization

Zeus: Towards Tuning-Free Foundation Model for Time Series Analysis

2026-07-02 · Yisong Fu, Zezhi Shao, Chengqing Yu, Yujie Li 외 arxiv

We present Zeus, a unified tuning-free Time Series Foundation Model (TSFM) that delivers superior performance across diverse analysis tasks without any task-specific fine-tuning. Unlike prior studies that primarily focus…

Computational Efficiency Time Series Analysis