Learning Temporal Alignment Uncertainty for Efficient Event Detection

09/04/2015
by   Iman Abbasnejad, et al.
0

In this paper we tackle the problem of efficient video event detection. We argue that linear detection functions should be preferred in this regard due to their scalability and efficiency during estimation and evaluation. A popular approach in this regard is to represent a sequence using a bag of words (BOW) representation due to its: (i) fixed dimensionality irrespective of the sequence length, and (ii) its ability to compactly model the statistics in the sequence. A drawback to the BOW representation, however, is the intrinsic destruction of the temporal ordering information. In this paper we propose a new representation that leverages the uncertainty in relative temporal alignments between pairs of sequences while not destroying temporal ordering. Our representation, like BOW, is of a fixed dimensionality making it easily integrated with a linear detection function. Extensive experiments on CK+, 6DMG, and UvA-NEMO databases show significant performance improvements across both isolated and continuous event detection tasks.

READ FULL TEXT

page 4

page 5

page 6

research
01/14/2017

Marked Temporal Dynamics Modeling based on Recurrent Neural Network

We are now witnessing the increasing availability of event stream data, ...
research
12/31/2020

Conditional Generation of Temporally-ordered Event Sequences

Models encapsulating narrative schema knowledge have proven to be useful...
research
05/11/2021

Representation Learning via Global Temporal Alignment and Cycle-Consistency

We introduce a weakly supervised method for representation learning base...
research
06/27/2019

Few-Shot Video Classification via Temporal Alignment

There is a growing interest in learning a model which could recognize no...
research
02/17/2022

Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences

Recent developments in predictive modeling using marked temporal point p...
research
04/13/2020

Event detection in coarsely annotated sports videos via parallel multi receptive field 1D convolutions

In problems such as sports video analytics, it is difficult to obtain ac...
research
08/20/2019

Evaluating Alignment Approaches in Superimposed Time-Series and Temporal Event-Sequence Visualizations

Composite temporal event sequence visualizations have included sentinel ...

Please sign up or login with your details

Forgot password? Click here to reset