paper-with-me

Papers

Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval

2019-06-11 · CVPR 2019 6 · Yale Song, Mohammad Soleymani

Visual-semantic embedding aims to find a shared latent space where related visual and textual instances are close to each other. Most current methods learn injective embedding functions that map an instance to a single point in the shared space. Unfortunately, injective embedding cannot effectively handle polysemous instances with multiple possible meanings; at best, it would find an average representation of different meanings. This hinders its use in real-world scenarios where individual instances and their cross-modal associations are often ambiguous. In this work, we introduce Polysemous Instance Embedding Networks (PIE-Nets) that compute multiple and diverse representations of an instance by combining global context with locally-guided features via multi-head self-attention and residual learning. To learn visual-semantic embedding, we tie-up two PIE-Nets and optimize them jointly in the multiple instance learning framework. Most existing work on cross-modal retrieval focuses on image-text data. Here, we also tackle a more challenging case of video-text retrieval. To facilitate further research in video-text retrieval, we release a new dataset of 50K video-sentence pairs collected from social media, dubbed MRW (my reaction when). We demonstrate our approach on both image-text and video-text retrieval scenarios using MS-COCO, TGIF, and our new MRW dataset.

📄 PDF Abstract BibTeX arXiv:1906.04402

Code (1)

yalesong/pvse pytorch

Tasks

Cross-Modal RetrievalMultiple Instance LearningRetrievalSentenceText RetrievalVideo-Text Retrieval

Similar Papers 제목 키워드 기반

How does BERT capture semantics? A closer look at polysemous words

2020-11-01 · EMNLP (BlackboxNLP) 2020 11 · David Yenicelik, Florian Schmidt, Yannic Kilcher

The recent paradigm shift to contextual word embeddings has seen tremendous success across a wide range of down-stream tasks. However, little is known on how the emergent relation of context and semantics manifests geome…

Semanticity predictionSemantic SimilarityWord EmbeddingsWord Sense Disambiguation+2

Multi Sense Embeddings from Topic Models

2019-09-17 · WS 2019 9 · Shobhit Jain, Sravan Babu Bodapati, Ramesh Nallapati, Anima Anandkumar

Distributed word embeddings have yielded state-of-the-art performance in many NLP tasks, mainly due to their success in capturing useful semantic information. These representations assign only a single vector to each wor…

Topic ModelsWord EmbeddingsWord Similarity

Uncertainty-based Cross-Modal Retrieval with Probabilistic Representations

2022-04-20 · Leila Pishdad, Ran Zhang, Konstantinos G. Derpanis, Allan Jepson 외

Probabilistic embeddings have proven useful for capturing polysemous word meanings, as well as ambiguity in image matching. In this paper, we study the advantages of probabilistic embeddings in a cross-modal setting (i.e…

Cross-Modal RetrievalImage RetrievalImage-text matchingImage to text+2

Chinese Word Sense Embedding with SememeWSD and Synonym Set

2022-06-29 · Yangxi Zhou, Junping Du, Zhe Xue, Ang Li 외

Word embedding is a fundamental natural language processing task which can learn feature of words. However, most word embedding methods assign only one vector to a word, even if polysemous words have multi-senses. To add…

Semantic SimilaritySemantic Textual SimilarityWord Sense Disambiguation

Towards Robust Visual Continual Learning with Multi-Prototype Supervision

2025-09-19 · Xiwei Liu, Yulong Li, Yichen Li, Xinlin Zhuang 외 arxiv

Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL). However, relying on a single target int…

Continual Learning