paper-with-me

홈 › Papers

Semi Supervised Phrase Localization in a Bidirectional Caption-Image Retrieval Framework

2019-08-08 · Deepan Das, Noor Mohammed Ghouse, Shashank Verma, Yin Li

We introduce a novel deep neural network architecture that links visual regions to corresponding textual segments including phrases and words. To accomplish this task, our architecture makes use of the rich semantic information available in a joint embedding space of multi-modal data. From this joint embedding space, we extract the associative localization maps that develop naturally, without explicitly providing supervision during training for the localization task. The joint space is learned using a bidirectional ranking objective that is optimized using a $N$-Pair loss formulation. This training mechanism demonstrates the idea that localization information is learned inherently while optimizing a Bidirectional Retrieval objective. The model's retrieval and localization performance is evaluated on MSCOCO and Flickr30K Entities datasets. This architecture outperforms the state of the art results in the semi-supervised phrase localization setting.

📄 PDF Abstract BibTeX arXiv:1908.02950

Code (0)

등록된 구현이 없습니다.

Tasks

Image RetrievalRetrieval

Similar Papers 제목 키워드 기반

Align2Ground: Weakly Supervised Phrase Grounding Guided by Image-Caption Alignment

2019-03-27 · ICCV 2019 10 · Samyak Datta, Karan Sikka, Anirban Roy, Karuna Ahuja 외

We address the problem of grounding free-form textual phrases by using weak supervision from image-caption pairs. We propose a novel end-to-end model that uses caption-to-image retrieval as a `downstream' task to guide t…

Image RetrievalPhrase GroundingRetrievalVisual Grounding

Adapting CLIP For Phrase Localization Without Further Training

2022-04-07 · Jiahao Li, Greg Shakhnarovich, Raymond A. Yeh

Supervised or weakly supervised methods for phrase localization (textual grounding) either rely on human annotations or some other supervised models, e.g., object detectors. Obtaining these annotations is labor-intensive…

Describe Anything: Detailed Localized Image and Video Captioning

2025-04-22 · Long Lian, Yifan Ding, Yunhao Ge, Sifei Liu 외

Generating detailed and accurate descriptions for specific regions in images and videos remains a fundamental challenge for vision-language models. We introduce the Describe Anything Model (DAM), a model designed for det…

SentenceVideo Captioning

MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding

2020-10-12 · EMNLP 2020 11 · Qinxin Wang, Hao Tan, Sheng Shen, Michael W. Mahoney 외

Phrase localization is a task that studies the mapping from textual phrases to regions of an image. Given difficulties in annotating phrase-to-object datasets at scale, we develop a Multimodal Alignment Framework (MAF) t…

Phrase Grounding

What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs

2022-06-19 · Tal Shaharabany, Yoad Tewel, Lior Wolf

Given an input image, and nothing else, our method returns the bounding boxes of objects in the image and phrases that describe the objects. This is achieved within an open world paradigm, in which the objects in the inp…

BenchmarkingImage CaptioningImage to textPhrase Grounding+2