paper-with-me

Papers

Image Captioning: Transforming Objects into Words

2019-06-14 · NeurIPS 2019 12 · Simao Herdade, Armin Kappeler, Kofi Boakye, Joao Soares

Image captioning models typically follow an encoder-decoder architecture which uses abstract image feature vectors as input to the encoder. One of the most successful algorithms uses feature vectors extracted from the region proposals obtained from an object detector. In this work we introduce the Object Relation Transformer, that builds upon this approach by explicitly incorporating information about the spatial relationship between input detected objects through geometric attention. Quantitative and qualitative results demonstrate the importance of such geometric attention for image captioning, leading to improvements on all common captioning metrics on the MS-COCO dataset.

📄 PDF Abstract BibTeX arXiv:1906.05963

Code (4)

yahoo/object_relation_transformer 공식 구현 pytorch
Japanese-Image-Captioning/ORT-for-Japanese pytorch
hieunghia-pat/ObjectRelationTransformerAoA
hieunghia-pat/uit-objectaoa

Tasks

DecoderImage CaptioningObject

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Adam 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning

2021-08-05 · Findings (ACL) 2021 8 · Fenglin Liu, Xuancheng Ren, Xian Wu, Bang Yang 외

Video captioning combines video understanding and language generation. Different from image captioning that describes a static image with details of almost every object, video captioning usually considers a sequence of f…

AttributeCaption GenerationImage CaptioningText Generation+2

Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects

2017-08-17 · CVPR 2017 7 · Ting Yao, Yingwei Pan, Yehao Li, Tao Mei

Image captioning often requires a large set of training image-sentence pairs. In practice, however, acquiring sufficient training pairs is always expensive, making the recent captioning models limited in their ability to…

DecoderImage CaptioningObject RecognitionSentence

RORPCap: Retrieval-based Objects and Relations Prompt for Image Captioning

2025-08-10 · Jinjing Gu, Tianbao Qin, Yuanyuan Pu, Zhengpeng Zhao arxiv

Image captioning aims to generate natural language descriptions for input images in an open-form manner. To accurately generate descriptions related to the image, a critical step in image captioning is to identify object…

Image CaptioningText Retrieval

Top-Down Framework for Weakly-supervised Grounded Image Captioning

2023-06-13 · Chen Cai, Suchen Wang, Kim-Hui Yap, Yi Wang

Weakly-supervised grounded image captioning (WSGIC) aims to generate the caption and ground (localize) predicted object words in the input image without using bounding box supervision. Recent two-stage solutions mostly a…

Image CaptioningMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONObject+1

Guided Open Vocabulary Image Captioning with Constrained Beam Search

2016-12-02 · EMNLP 2017 9 · Peter Anderson, Basura Fernando, Mark Johnson, Stephen Gould

Existing image captioning models do not generalize well to out-of-domain images containing novel scenes or objects. This limitation severely hinders the use of these models in real world applications dealing with images …

Image CaptioningTAGWord Embeddings