paper-with-me

홈 › Papers

GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation

2018-05-28 · Taehyeong Kim, Min-Oh Heo, Seonil Son, Kyoung-Wha Park, Byoung-Tak Zhang

The task of multi-image cued story generation, such as visual storytelling dataset (VIST) challenge, is to compose multiple coherent sentences from a given sequence of images. The main difficulty is how to generate image-specific sentences within the context of overall images. Here we propose a deep learning network model, GLAC Net, that generates visual stories by combining global-local (glocal) attention and context cascading mechanisms. The model incorporates two levels of attention, i.e., overall encoding level and image feature level, to construct image-dependent sentences. While standard attention configuration needs a large number of parameters, the GLAC Net implements them in a very simple way via hard connections from the outputs of encoders or image features onto the sentence generators. The coherency of the generated story is further improved by conveying (cascading) the information of the previous sentence to the next sentence serially. We evaluate the performance of the GLAC Net on the visual storytelling dataset (VIST) and achieve very competitive results compared to the state-of-the-art techniques. Our code and pre-trained models are available here.

📄 PDF Abstract BibTeX arXiv:1805.10973

Code (1)

tkim-snu/GLACNet 공식 구현 pytorch

Tasks

SentenceStory GenerationVisual Storytelling

Similar Papers 제목 키워드 기반

3DGTN: 3D Dual-Attention GLocal Transformer Network for Point Cloud Classification and Segmentation

2022-09-21 · Dening Lu, Kyle Gao, Qian Xie, Linlin Xu 외

Although the application of Transformers in 3D point cloud processing has achieved significant progress and success, it is still challenging for existing 3D Transformer methods to efficiently and accurately learn both va…

ClassificationDecoderPoint Cloud ClassificationSegmentation

AMD-HookNet for Glacier Front Segmentation

2023-02-06 · Fei Wu, Nora Gourmelon, Thorsten Seehaus, Jianlin Zhang 외

Knowledge on changes in glacier calving front positions is important for assessing the status of glaciers. Remote sensing imagery provides the ideal database for monitoring calving front positions, however, it is not fea…

Calving Front Delineation In Synthetic Aperture Radar ImageryCalving Front Delineation In Synthetic Aperture Radar Imagery With Fixed Training AmountSegmentation

GlocalFuse-Depth: Fusing Transformers and CNNs for All-day Self-supervised Monocular Depth Estimation

2023-02-20 · Zezheng Zhang, Ryan K. Y. Chan, Kenneth K. Y. Wong

In recent years, self-supervised monocular depth estimation has drawn much attention since it frees of depth annotations and achieved remarkable results on standard benchmarks. However, most of existing methods only focu…

AllDepth EstimationMonocular Depth Estimation

GlocalCLIP: Object-agnostic Global-Local Prompt Learning for Zero-shot Anomaly Detection

2024-11-09 · Jiyul Ham, Yonggon Jung, Jun-Geol Baek

Zero-shot anomaly detection (ZSAD) is crucial for detecting anomalous patterns in target datasets without using training samples, specifically in scenarios where there are distributional differences between the target do…

Anomaly DetectionContrastive LearningPrompt Learningzero-shot anomaly detection

Glacier Calving Front Segmentation Using Attention U-Net

2021-01-08 · Michael Holzmann, Amirabbas Davari, Thorsten Seehaus, Matthias Braun 외

An essential climate variable to determine the tidewater glacier status is the location of the calving front position and the separation of seasonal variability from long-term trends. Previous studies have proposed deep …