paper-with-me

홈 › Papers

Self-Guiding Multimodal LSTM - when we do not have a perfect training dataset for image captioning

2017-09-15 · Yang Xian, YingLi Tian

In this paper, a self-guiding multimodal LSTM (sg-LSTM) image captioning model is proposed to handle uncontrolled imbalanced real-world image-sentence dataset. We collect FlickrNYC dataset from Flickr as our testbed with 306,165 images and the original text descriptions uploaded by the users are utilized as the ground truth for training. Descriptions in FlickrNYC dataset vary dramatically ranging from short term-descriptions to long paragraph-descriptions and can describe any visual aspects, or even refer to objects that are not depicted. To deal with the imbalanced and noisy situation and to fully explore the dataset itself, we propose a novel guiding textual feature extracted utilizing a multimodal LSTM (m-LSTM) model. Training of m-LSTM is based on the portion of data in which the image content and the corresponding descriptions are strongly bonded. Afterwards, during the training of sg-LSTM on the rest training data, this guiding information serves as additional input to the network along with the image representations and the ground-truth descriptions. By integrating these input components into a multimodal block, we aim to form a training scheme with the textual information tightly coupled with the image content. The experimental results demonstrate that the proposed sg-LSTM model outperforms the traditional state-of-the-art multimodal RNN captioning framework in successfully describing the key components of the input images.

📄 PDF Abstract BibTeX arXiv:1709.05038

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningSentence

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Unsupervised Natural Language Inference via Decoupled Multimodal Contrastive Learning

2020-10-16 · EMNLP 2020 11 · Wanyun Cui, Guangyu Zheng, Wei Wang

We propose to solve the natural language inference problem without any supervision from the inference labels via task-agnostic multimodal pretraining. Although recent studies of multimodal self-supervised learning also r…

Contrastive LearningNatural Language InferenceSelf-Supervised LearningSTS+1

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization

2025-11-17 · Xuankun Rong, Wenke Huang, Tingfeng Wang, Daiguo Zhou 외 arxiv

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex…

Incomplete Multimodal Learning for Remote Sensing Data Fusion

2023-04-22 · Yuxing Chen, Maofan Zhao, Lorenzo Bruzzone

The mechanism of connecting multimodal signals through self-attention operation is a key factor in the success of multimodal Transformer networks in remote sensing data fusion tasks. However, traditional approaches assum…

Semantic Segmentation

ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better

2025-11-21 · Yuan Zhang, Ming Lu, Junwen Pan, Tao Huang 외 arxiv

Recent advances in multimodal reasoning models have demonstrated impressive capabilities across text and vision. However, even leading models exhibit redundant self-reflection when generating lengthy reasoning chains. Wh…

Multimodal Reasoning

Guiding the Long-Short Term Memory Model for Image Caption Generation

2015-12-01 · ICCV 2015 12 · Xu Jia, Efstratios Gavves, Basura Fernando, Tinne Tuytelaars

In this work we focus on the problem of image caption generation. We propose an extension of the long short term memory (LSTM) model, which we coin gLSTM for short. In particular, we add semantic information extracted f…

Caption Generation