paper-with-me

Papers

Cross-Modal Discrete Representation Learning

2021-06-10 · ACL 2022 5 · Alexander H. Liu, SouYoung Jin, Cheng-I Jeff Lai, Andrew Rouditchenko, Aude Oliva, James Glass

Recent advances in representation learning have demonstrated an ability to represent information from different modalities such as video, text, and audio in a single high-level embedding vector. In this work we present a self-supervised learning framework that is able to learn a representation that captures finer levels of granularity across different modalities such as concepts or events represented by visual objects or spoken words. Our framework relies on a discretized embedding space created via vector quantization that is shared across different modalities. Beyond the shared embedding space, we propose a Cross-Modal Code Matching objective that forces the representations from different views (modalities) to have a similar distribution over the discrete embedding space such that cross-modal objects/actions localization can be performed without direct supervision. In our experiments we show that the proposed discretized multi-modal fine-grained representation (e.g., pixel/word/frame) can complement high-level summary representations (e.g., video/sentence/waveform) for improved performance on cross-modal retrieval tasks. We also observe that the discretized representation uses individual clusters to represent the same semantic concept across modalities.

📄 PDF Abstract BibTeX arXiv:2106.05438

Code (0)

등록된 구현이 없습니다.

Tasks

Cross-Modal RetrievalQuantizationRepresentation LearningRetrievalSelf-Supervised LearningSentence

Similar Papers 제목 키워드 기반

Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations

2026-05-12 · Souptik Sen, Raneen Younis, Zahra Ahmadi arxiv

Multimodal learning seeks to integrate information across diverse sensory sources, yet current approaches struggle to balance cross-modal generalizability with modality-specific structure. Continuous (implicit) methods p…

Representation LearningDomain GeneralizationVideo Segmentation

Enhancing Multimodal Unified Representations for Cross Modal Generalization

2024-03-08 · Hai Huang, Yan Xia, Shengpeng Ji, Shulei Wang 외

To enhance the interpretability of multimodal unified representations, many studies have focused on discrete unified representations. These efforts typically start with contrastive learning and gradually extend to the di…

Contrastive LearningDisentanglementQuantizationRepresentation Learning

Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens

2023-03-27 · CVPR 2023 1 · Yuxiao Chen, Jianbo Yuan, Yu Tian, Shijie Geng 외

Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-tex…

Contrastive Learningcross-modal alignment

Achieving Cross Modal Generalization with Multimodal Unified Representation

2023-09-21 · NeurIPS 2023 11

This paper introduces a novel task called Cross Modal Generalization (CMG), which addresses the challenge of learning a unified discrete representation from paired multimodal data during pre-training. Then in downstream …

Kelix Technical Report

2026-02-10 · Boyang Ding, Chenglong Chu, Dunju Zang, Han Li 외 arxiv

Autoregressive large language models (LLMs) scale well by expressing diverse tasks as sequences of discrete natural-language tokens and training with next-token prediction, which unifies comprehension and generation unde…

Self-Supervised Learning