Entity-aware Image Caption Generation (D18-1)

Copied to clipboard

Challenge: Existing image captioning approaches generate generic descriptions of visual content and ignore background information.
Approach: They propose a task which generates informative image captions using images and hashtags as input.
Outcome: The proposed model outperforms unimodal baselines significantly with evaluation metrics on a dataset from Flickr.

Similar Papers

Informative Image Captioning with External Sources of Information (P19-1)

Copied to clipboard

Challenge: Current captioning models are trained to generate captions that only contain common object names, thus falling short on an important “informativeness” dimension.
Approach: They propose a mechanism for integrating image information and fine-grained labels into a caption that describes the image in a fluent and informative manner.
Outcome: The proposed model integrates image information with fine-grained labels to produce fluent captions . it can control the appearance of these labels in the output, resulting in fluent and informative captions.
Neural Caption Generation for News Images (L18-1)

Copied to clipboard

Challenge: Existing methods for automatic caption generation of images are lacking in the field of image-related applications.
Approach: They propose a method for automatically generating captions for news images . they propose several deep neural network architectures built upon Recurrent Neural Networks .
Outcome: The proposed method outperforms a traditional method on a BBC News dataset using automatic evaluation and human evaluation.
Improving Image Captioning with Better Use of Caption (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to image captioning focus on visual attention, but many do not.
Approach: They propose a framework that explores semantics available in captions and leverages that to enhance both image representation and caption generation.
Outcome: The proposed framework outperforms baselines on the MSCOCO dataset and is state-of-the-art under a wide range of evaluation metrics.
Cross-modal Coherence Modeling for Caption Generation (2020.acl-main)

Copied to clipboard

Challenge: Existing methods for image captioning do not guarantee consistent image-text relations . current models do not provide enough data for training robust captioning models .
Approach: They use an annotation protocol specifically devised for capturing image–caption coherence relations to study image captioning.
Outcome: The proposed protocol improves image captioning models with coherence relations . the dataset is large enough to alleviate content hallucinations, the authors show .
Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning (P19-1)

Copied to clipboard

Challenge: Existing research on image captioning generates frequent n-grams with irrelevant words.
Approach: They propose to construct an image-grounded vocabulary incorporating visual information and relations among words into the decoding process directly.
Outcome: The proposed framework is compared with state-of-the-art models on MS COCO and Flickr30k and shows that it is more efficient than existing models.
Journalistic Guidelines Aware News Image Captioning (2021.emnlp-main)

Copied to clipboard

Challenge: Experimental results show that JoGANIC outperforms state-of-the-art methods for image caption generation.
Approach: They propose a method to generate descriptive and informative captions for news article images . they leverage the structure of captions to improve the generation quality and guide their representation .
Outcome: The proposed method outperforms state-of-the-art methods on two large-scale datasets.
Image Caption Generation for News Articles (2020.coling-main)

Copied to clipboard

Challenge: Existing work on news-image captioning requires a joint understanding of image and text.
Approach: They propose a Transformer model that integrates text and image modalities and attends to textual features from visual features in generating a caption.
Outcome: The proposed model outperforms the state-of-the-art model and improves the quality of news-image captions.
CapOnImage: Context-driven Dense-Captioning on Image (2022.emnlp-main)

Copied to clipboard

Challenge: Existing image captioning systems generate narrative captions for images, which are spatially detached from the image in presentation.
Approach: They propose a task called captioning on image which generatesense captions at different locations of the image based on contextual information.
Outcome: The proposed model achieves the best results in both captioning accuracy and diversity aspects.
Focus! Relevant and Sufficient Context Selection for News Image Captioning (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent work only coarsely leverages the article to extract the necessary context, which makes it difficult for models to identify relevant events and named entities.
Approach: They propose to use a vision and language retrieval model CLIP to localize the visually grounded entities in the news article and then capture the non-visual entities via an open relation extraction model.
Outcome: The proposed model significantly improves on existing models and achieves state-of-the-art on multiple benchmarks.
Exploring the Impact of Vision Features in News Image Captioning (2023.findings-acl)

Copied to clipboard

Challenge: Recent state-of-art models can achieve competitive performance even without vision features.
Approach: They conduct extensive experiments with mainstream news image captioning models to determine whether vision features contribute to the generation of captions.
Outcome: The proposed models can achieve competitive performance even without vision features.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations