|
成本敏感的自上而下的/底部的多尺度行为识别推理
Cost-Sensitive Top-Down/Bottom-Up Inference for Multiscale Activity Recognition |
|
| |
| 课程网址: |
http://videolectures.net/eccv2012_amer_recognition/
|
| 主讲教师: |
Ivan Laptev, Michael J. Black, Mohamed Amer
|
| 开课单位: |
俄勒冈州立大学
|
| 开课时间: |
2012-11-12
|
| 课程语种: |
英语
|
| 中文简介: |
本文讨论了一个新的问题, 即多尺度活动识别。我们的目标是检测和本地化广泛的活动, 包括单独的行动和小组活动, 这些活动可能同时出现在高分辨率视频中。视频分辨率允许进行数字放大 (或缩小), 以检查识别所需的精细细节 (或粗刻度)。关键的挑战是如何避免在所有时空尺度上运行大量探测器, 同时获得整体一致的视频判读。为此, 我们使用三层 and-or 图共同建模组活动、单个操作和参与对象。and-or 图允许通过探索利用策略, 有原则地制定高效、成本敏感的推断。我们的推理以最佳方式安排了以下计算过程: 1) 直接应用活动检测器, 称为 α 过程;2) 基于检测活动部分的自下而上的推理, 称为 β 过程;3) 基于检测活动上下文称为 γ 过程的自上而下的推理。调度迭代地最大化了生成的解析图的对数后验。为了进行评估, 我们编制了一个新的高分辨率视频数据集, 这些视频是在加州大学洛杉矶分校校园的一个庭院中同时发生的。
|
| 课程简介: |
This paper addresses a new problem, that of multiscale activity recognition. Our goal is to detect and localize a wide range of activities, including individual actions and group activities, which may simultaneously co-occur in high-resolution video. The video resolution allows for digital zoom-in (or zoom-out) for examining fine details (or coarser scales), as needed for recognition. The key challenge is how to avoid running a multitude of detectors at all spatiotemporal scales, and yet arrive at a holistically consistent video interpretation. To this end, we use a three-layered AND-OR graph to jointly model group activities, individual actions, and participating objects. The AND-OR graph allows a principled formulation of efficient, cost-sensitive inference via an explore-exploit strategy. Our inference optimally schedules the following computational processes: 1) direct application of activity detectors-called α process; 2) bottom-up inference based on detecting activity parts-called β process; and 3) top-down inference based on detecting activity context-called γ process. The scheduling iteratively maximizes the log-posteriors of the resulting parse graphs. For evaluation, we have compiled and benchmarked a new dataset of high-resolution videos of group and individual activities co-occurring in a courtyard of the UCLA campus.
|
| 关 键 词: |
多尺度问题; 行为识别; 探测器; 视频解释; 图联合模型组
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2020-06-29：yumf
|
| 阅读次数: |
95
|
|
图 书 馆