@inproceedings{hinami-satoh-2018-discriminative,
title = "Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation",
author = "Hinami, Ryota and
Satoh, Shin{'}ichi",
editor = "Riloff, Ellen and
Chiang, David and
Hockenmaier, Julia and
Tsujii, Jun{'}ichi",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
month = oct # "-" # nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-1281",
doi = "10.18653/v1/D18-1281",
pages = "2605--2615",
abstract = "Thanks to the success of object detection technology, we can retrieve objects of the specified classes even from huge image collections. However, the current state-of-the-art object detectors (such as Faster R-CNN) can only handle pre-specified classes. In addition, large amounts of positive and negative visual samples are required for training. In this paper, we address the problem of open-vocabulary object retrieval and localization, where the target object is specified by a textual query (e.g., a word or phrase). We first propose Query-Adaptive R-CNN, a simple extension of Faster R-CNN adapted to open-vocabulary queries, by transforming the text embedding vector into an object classifier and localization regressor. Then, for discriminative training, we then propose negative phrase augmentation (NPA) to mine hard negative samples which are visually similar to the query and at the same time semantically mutually exclusive of the query. The proposed method can retrieve and localize objects specified by a textual query from one million images in only 0.5 seconds with high precision.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hinami-satoh-2018-discriminative">
<titleInfo>
<title>Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryota</namePart>
<namePart type="family">Hinami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shin’ichi</namePart>
<namePart type="family">Satoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Riloff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hockenmaier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun’ichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Thanks to the success of object detection technology, we can retrieve objects of the specified classes even from huge image collections. However, the current state-of-the-art object detectors (such as Faster R-CNN) can only handle pre-specified classes. In addition, large amounts of positive and negative visual samples are required for training. In this paper, we address the problem of open-vocabulary object retrieval and localization, where the target object is specified by a textual query (e.g., a word or phrase). We first propose Query-Adaptive R-CNN, a simple extension of Faster R-CNN adapted to open-vocabulary queries, by transforming the text embedding vector into an object classifier and localization regressor. Then, for discriminative training, we then propose negative phrase augmentation (NPA) to mine hard negative samples which are visually similar to the query and at the same time semantically mutually exclusive of the query. The proposed method can retrieve and localize objects specified by a textual query from one million images in only 0.5 seconds with high precision.</abstract>
<identifier type="citekey">hinami-satoh-2018-discriminative</identifier>
<identifier type="doi">10.18653/v1/D18-1281</identifier>
<location>
<url>https://aclanthology.org/D18-1281</url>
</location>
<part>
<date>2018-oct-nov</date>
<extent unit="page">
<start>2605</start>
<end>2615</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation
%A Hinami, Ryota
%A Satoh, Shin’ichi
%Y Riloff, Ellen
%Y Chiang, David
%Y Hockenmaier, Julia
%Y Tsujii, Jun’ichi
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
%D 2018
%8 oct nov
%I Association for Computational Linguistics
%C Brussels, Belgium
%F hinami-satoh-2018-discriminative
%X Thanks to the success of object detection technology, we can retrieve objects of the specified classes even from huge image collections. However, the current state-of-the-art object detectors (such as Faster R-CNN) can only handle pre-specified classes. In addition, large amounts of positive and negative visual samples are required for training. In this paper, we address the problem of open-vocabulary object retrieval and localization, where the target object is specified by a textual query (e.g., a word or phrase). We first propose Query-Adaptive R-CNN, a simple extension of Faster R-CNN adapted to open-vocabulary queries, by transforming the text embedding vector into an object classifier and localization regressor. Then, for discriminative training, we then propose negative phrase augmentation (NPA) to mine hard negative samples which are visually similar to the query and at the same time semantically mutually exclusive of the query. The proposed method can retrieve and localize objects specified by a textual query from one million images in only 0.5 seconds with high precision.
%R 10.18653/v1/D18-1281
%U https://aclanthology.org/D18-1281
%U https://doi.org/10.18653/v1/D18-1281
%P 2605-2615
Markdown (Informal)
[Discriminative Learning of Open-Vocabulary Object Retrieval and Localization by Negative Phrase Augmentation](https://aclanthology.org/D18-1281) (Hinami & Satoh, EMNLP 2018)
ACL