paper-with-me

Papers

What value do explicit high level concepts have in vision to language problems?

2015-06-03 · CVPR 2016 6 · Qi Wu, Chunhua Shen, Lingqiao Liu, Anthony Dick, Anton Van Den Hengel

Much of the recent progress in Vision-to-Language (V2L) problems has been achieved through a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). This approach does not explicitly represent high-level semantic concepts, but rather seeks to progress directly from image features to text. We propose here a method of incorporating high-level concepts into the very successful CNN-RNN approach, and show that it achieves a significant improvement on the state-of-the-art performance in both image captioning and visual question answering. We also show that the same mechanism can be used to introduce external semantic information and that doing so further improves performance. In doing so we provide an analysis of the value of high level semantic information in V2L problems.

📄 PDF Abstract BibTeX arXiv:1506.01144

Code (1)

liuqihan/Image-Caption tf

Tasks

Image CaptioningQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)

Similar Papers 제목 키워드 기반

Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts

2022-06-20 · Alex Bäuerle, Daniel Jönsson, Timo Ropinski

A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing activation values, whereby current technique…

Can AI decrypt fashion jargon for you?

2020-03-18 · Yuan Shen, Shanduojiao Jiang, Muhammad Rizky Wellyanto, Ranjitha Kumar

When people talk about fashion, they care about the underlying meaning of fashion concepts,e.g., style.For example, people ask questions like what features make this dress smart.However, the product descriptions in today…

Concept Alignment as a Prerequisite for Value Alignment

2023-10-30 · Sunayana Rane, Mark Ho, Ilia Sucholutsky, Thomas L. Griffiths

Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently u…

Concept Alignment

Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text Generation

2021-04-18 · EMNLP 2021 11 · Yuning Mao, Wenchang Ma, Deren Lei, Jiawei Han 외

Prior studies on text-to-text generation typically assume that the model could figure out what to attend to in the input and what to include in the output via seq2seq learning, with only the parallel training data and no…

Conditional Text GenerationDenoisingText Generation

The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning

2023-01-30 · Justin Kang, Ramtin Pedarsani, Kannan Ramchandran

Modern data aggregation often involves a platform collecting data from a network of users with various privacy options. Platforms must solve the problem of how to allocate incentives to users to convince them to share th…

FairnessFederated LearningSensitivity