Selecting Relevant Web Trained Concepts for Automated Event Retrieval

09/25/2015
by   Bharat Singh, et al.
0

Complex event retrieval is a challenging research problem, especially when no training videos are available. An alternative to collecting training videos is to train a large semantic concept bank a priori. Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos. However, defining an exhaustive concept lexicon and pre-training it requires vast computational resources. Therefore, recent approaches automate concept discovery and training by leveraging large amounts of weakly annotated web data. Compact visually salient concepts are automatically obtained by the use of concept pairs or, more generally, n-grams. However, not all visually salient n-grams are necessarily useful for an event query--some combinations of concepts may be visually compact but irrelevant--and this drastically affects performance. We propose an event retrieval algorithm that constructs pairs of automatically discovered concepts and then prunes those concepts that are unlikely to be helpful for retrieval. Pruning depends both on the query and on the specific video instance being evaluated. Our approach also addresses calibration and domain adaptation issues that arise when applying concept detectors to unseen videos. We demonstrate large improvements over other vision based systems on the TRECVID MED 13 dataset.

READ FULL TEXT

page 2

page 4

page 5

research
06/08/2015

EventNet: A Large Scale Structured Concept Library for Complex Event Detection in Video

Event-specific concepts are the semantic concepts designed for the event...
research
01/17/2017

Complex Event Recognition from Images with Few Training Examples

We propose to leverage concept-level representations for complex event r...
research
01/14/2016

Dynamic Concept Composition for Zero-Example Event Detection

In this paper, we focus on automatically detecting events in unconstrain...
research
10/30/2017

Open Set Logo Detection and Retrieval

Current logo retrieval research focuses on closed set scenarios. We argu...
research
05/05/2017

Unified Embedding and Metric Learning for Zero-Exemplar Event Detection

Event detection in unconstrained videos is conceived as a content-based ...
research
10/10/2015

TagBook: A Semantic Video Representation without Supervision for Event Detection

We consider the problem of event detection in video for scenarios where ...
research
10/30/2020

Biomedical Concept Relatedness – A large EHR-based benchmark

A promising application of AI to healthcare is the retrieval of informat...

Please sign up or login with your details

Forgot password? Click here to reset