Efficient Activity Detection in Untrimmed Video with Max-Subgraph Search

07/11/2016
by   Chao-Yeh Chen, et al.
0

We propose an efficient approach for activity detection in video that unifies activity categorization with space-time localization. The main idea is to pose activity detection as a maximum-weight connected subgraph problem. Offline, we learn a binary classifier for an activity category using positive video exemplars that are "trimmed" in time to the activity of interest. Then, given a novel untrimmed video sequence, we decompose it into a 3D array of space-time nodes, which are weighted based on the extent to which their component features support the learned activity model. To perform detection, we then directly localize instances of the activity by solving for the maximum-weight connected subgraph in the test video's space-time graph. We show that this detection strategy permits an efficient branch-and-cut solution for the best-scoring---and possibly non-cubically shaped---portion of the video for a given activity classifier. The upshot is a fast method that can search a broader space of space-time region candidates than was previously practical, which we find often leads to more accurate detection. We demonstrate the proposed algorithm on four datasets, and we show its speed and accuracy advantages over multiple existing search strategies.

READ FULL TEXT

page 1

page 3

page 5

page 7

page 8

page 11

page 13

research
06/16/2023

Learning Space-Time Semantic Correspondences

We propose a new task of space-time semantic correspondence prediction i...
research
12/15/2022

Learning a Fast 3D Spectral Approach to Object Segmentation and Tracking over Space and Time

We pose video object segmentation as spectral graph clustering in space ...
research
07/13/2020

Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization

Temporally localizing activities within untrimmed videos has been extens...
research
10/23/2014

Density-Based Region Search with Arbitrary Shape for Object Localization

Region search is widely used for object localization. Typically, the reg...
research
04/18/2019

New Subgraph Isomorphism Algorithms: Vertex versus Path-at-a-time Matching

Graphs are widely used to model complicated data semantics in many appli...
research
04/11/2019

Recurrent Space-time Graphs for Video Understanding

Visual learning in the space-time domain remains a very challenging prob...

Please sign up or login with your details

Forgot password? Click here to reset