paper-with-me

Papers

Learning to Learn from Web Data through Deep Semantic Embeddings

2018-08-20 · Raul Gomez, Lluis Gomez, Jaume Gibert, Dimosthenis Karatzas

In this paper we propose to learn a multimodal image and text embedding from Web and Social Media data, aiming to leverage the semantic knowledge learnt in the text domain and transfer it to a visual model for semantic image retrieval. We demonstrate that the pipeline can learn from images with associated text without supervision and perform a thourough analysis of five different text embeddings in three different benchmarks. We show that the embeddings learnt with Web and Social Media data have competitive performances over supervised methods in the text based image retrieval task, and we clearly outperform state of the art in the MIRFlickr dataset when training in the target data. Further we demonstrate how semantic multimodal image retrieval can be performed using the learnt embeddings, going beyond classical instance-level retrieval problems. Finally, we present a new dataset, InstaCities1M, composed by Instagram images and their associated texts that can be used for fair comparison of image-text embeddings.

📄 PDF Abstract BibTeX arXiv:1808.06368

Code (1)

gombru/LearnFromWebData 공식 구현

Tasks

Image RetrievalRetrieval

Similar Papers 제목 키워드 기반

Improving Entity Linking through Semantic Reinforced Entity Embeddings

2021-06-16 · ACL 2020 6 · Feng Hou, Ruili Wang, Jun He, Yi Zhou

Entity embeddings, which represent different aspects of each entity with a single vector like word embeddings, are a key component of neural entity linking models. Existing entity embeddings are learned from canonical Wi…

ArticlesEntity EmbeddingsEntity LinkingWord Embeddings

Lexical semantics enhanced neural word embeddings

2022-10-03 · Dongqiang Yang, Ning li, Li Zou, Hongwei Ma

Current breakthroughs in natural language processing have benefited dramatically from neural language models, through which distributional semantics can leverage neural data representations to facilitate downstream appli…

Metric LearningSemantic SimilaritySemantic Textual SimilarityWord Embeddings

VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning

2022-03-20 · CVPR 2022 1 · Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele 외

Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., w…

Transfer LearningWord EmbeddingsZero-Shot Learning

Probing Multimodal Embeddings for Linguistic Properties: the Visual-Semantic Case

2021-02-22 · COLING 2020 8 · Adam Dahlgren Lindström, Suna Bensch, Johanna Björklund, Frank Drewes

Semantic embeddings have advanced the state of the art for countless natural language processing tasks, and various extensions to multimodal domains, such as visual-semantic embeddings, have been proposed. While the powe…

Semantic Leakage from Image Embeddings

2026-01-30 · Yiyi Chen, Qiongkai Xu, Desmond Elliott, Qiongxiu Li 외 arxiv

Image embeddings are generally assumed to pose limited privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image embeddings. Surprising…