paper-with-me

홈 › Papers

Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions

2018-11-26 · CVPR 2019 6 · Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the corresponding caption through a recurrent architecture which predicts textual chunks explicitly grounded on regions, following the constraints of the given control. Experiments are conducted on Flickr30k Entities and on COCO Entities, an extended version of COCO in which we add grounding annotations collected in a semi-automatic manner. Results demonstrate that our method achieves state of the art performances on controllable image captioning, in terms of caption quality and diversity. Code and annotations are publicly available at: https://github.com/aimagelab/show-control-and-tell.

📄 PDF Abstract BibTeX arXiv:1811.10652

Code (1)

aimagelab/show-control-and-tell 공식 구현 pytorch

Tasks

controllable image captioningDiversityImage Captioning

Similar Papers 제목 키워드 기반

Controllable Video Generation by Learning the Underlying Dynamical System with Neural ODE

2023-03-09 · Yucheng Xu, Li Nanbo, Arushi Goel, Zijian Guo 외

Videos depict the change of complex dynamical systems over time in the form of discrete image sequences. Generating controllable videos by learning the dynamical system is an important yet underexplored topic in the comp…

Video Generation

BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs

2025-09-30 · Yue Wang, Ruotian Ma, Xingyu Chen, Zhengliang Shi 외 arxiv

The rise of Large Language Models (LLMs) is reshaping multimodel models, with speech synthesis being a prominent application. However, existing approaches often underutilize the linguistic intelligence of these models, t…

Speech Synthesis

Generating Diverse Story Continuations with Controllable Semantics

2019-09-30 · WS 2019 11 · Lifu Tu, Xiaoan Ding, Dong Yu, Kevin Gimpel

We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story given its context. As controllable dimension…

DiversitySentence

Unified Generative Adversarial Networks for Controllable Image-to-Image Translation

2019-12-12 · Hao Tang, Hong Liu, Nicu Sebe

We propose a unified Generative Adversarial Network (GAN) for controllable image-to-image translation, i.e., transferring an image from a source to a target domain guided by controllable structures. In addition to condit…

Facial Expression TranslationGenerative Adversarial NetworkGesture-to-Gesture TranslationImage Generation+2

Emergence of Physical Intelligence via Controllable Information Production

2026-01-30 · Tristan Shah, Stas Tiomkin arxiv

Intrinsic Motivation (IM) aims to train agents without external rewards, enabling useful behavior to emerge from the agent's interaction with its environment alone. However, the dominant IM approaches rely on information…