paper-with-me

홈 › Papers

Context-aware Captions from Context-agnostic Supervision

2017-01-11 · CVPR 2017 7 · Ramakrishna Vedantam, Samy Bengio, Kevin Murphy, Devi Parikh, Gal Chechik

We introduce an inference technique to produce discriminative context-aware image captions (captions that describe differences between images or visual concepts) using only generic context-agnostic training data (captions that describe a concept or an image in isolation). For example, given images and captions of "siamese cat" and "tiger cat", we generate language that describes the "siamese cat" in a way that distinguishes it from "tiger cat". Our key novelty is that we show how to do joint inference over a language model that is context-agnostic and a listener which distinguishes closely-related concepts. We first apply our technique to a justification task, namely to describe why an image contains a particular fine-grained category as opposed to another closely-related category of the CUB-200-2011 dataset. We then study discriminative image captioning to generate language that uniquely refers to one of two semantically-similar images in the COCO dataset. Evaluations with discriminative ground truth for justification and human studies for discriminative image captioning reveal that our approach outperforms baseline generative and speaker-listener approaches for discrimination.

📄 PDF Abstract BibTeX arXiv:1701.02870

Code (1)

ruotianluo/DiscCaptioning pytorch

Tasks

Image CaptioningLanguage ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models

2025-10-04 · Min Woo Sun, Alejandro Lozano, Javier Gamazo Tejero, Vishwesh Nath 외 arxiv

Embedding vision-language models (VLMs) are typically pretrained with short text windows (<77 tokens), which forces the truncation of long-format captions. Yet, the distribution of biomedical captions from large-scale op…

Hierarchical Context-aware Network for Dense Video Event Captioning

2021-08-01 · ACL 2021 5 · Lei Ji, Xianglin Guo, Haoyang Huang, Xilin Chen

Dense video event captioning aims to generate a sequence of descriptive captions for each event in a long untrimmed video. Video-level context provides important information and facilities the model to generate consisten…

Descriptive

Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts

2026-04-20 · Run Xu, Lu Li, Rongzhao Zhang, Jie Xu arxiv

Recent multimodal large language models have shown promising ability in generating humorous captions for images, yet they still lack stable control over explicit cultural context, making it difficult to jointly maintain …

multimodal generation

Linguistic Structures as Weak Supervision for Visual Scene Graph Generation

2021-05-28 · CVPR 2021 1 · Keren Ye, Adriana Kovashka

Prior work in scene graph generation requires categorical supervision at the level of triplets - subjects and objects, and predicates that relate them, either with or without bounding box information. However, scene grap…

Graph GenerationScene Graph Generation

BioCAP: Exploiting Synthetic Captions Beyond Labels in Biological Foundation Models

2025-10-23 · Ziheng Zhang, Xinyue Ma, Arpita Chowdhury, Elizabeth G. Campolongo 외 arxiv

This work investigates descriptive captions as an additional source of supervision for biological multimodal foundation models. Images and captions can be viewed as complementary samples from the latent morphospace of a …

Image Retrieval