English
Related papers

Related papers: Phrase Grounding by Soft-Label Chain Conditional R…

200 papers

Dense captioning aims at simultaneously localizing semantic regions and describing these regions-of-interest (ROIs) with short phrases or sentences in natural language. Previous studies have shown remarkable progresses, but they are often…

Computer Vision and Pattern Recognition · Computer Science 2019-04-03 Guojun Yin , Lu Sheng , Bin Liu , Nenghai Yu , Xiaogang Wang , Jing Shao

Weakly supervised phrase grounding aims at learning region-phrase correspondences using only image-sentence pairs. A major challenge thus lies in the missing links between image regions and sentence phrases during training. To address this…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Liwei Wang , Jing Huang , Yin Li , Kun Xu , Zhengyuan Yang , Dong Yu

We introduce a unified framework to jointly model images, text, and human attention traces. Our work is built on top of the recent Localized Narratives annotation framework [30], where each word of a given caption is paired with a mouse…

Computer Vision and Pattern Recognition · Computer Science 2021-05-14 Zihang Meng , Licheng Yu , Ning Zhang , Tamara Berg , Babak Damavandi , Vikas Singh , Amy Bearman

Existing models which generate textual explanations enforce task relevance through a discriminative term loss function, but such mechanisms only weakly constrain mentioned object parts to actually be present in the image. In this paper, a…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Lisa Anne Hendricks , Ronghang Hu , Trevor Darrell , Zeynep Akata

Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding. Recent approaches have attempted to harness the capabilities of deep learning techniques for image recognition to tackle pixel-level…

Computer Vision and Pattern Recognition · Computer Science 2016-04-15 Shuai Zheng , Sadeep Jayasumana , Bernardino Romera-Paredes , Vibhav Vineet , Zhizhong Su , Dalong Du , Chang Huang , Philip H. S. Torr

Localizing phrases in images is an important part of image understanding and can be useful in many applications that require mappings between textual and visual information. Existing work attempts to learn these mappings from examples of…

Computer Vision and Pattern Recognition · Computer Science 2019-08-22 Josiah Wang , Lucia Specia

Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic…

Computer Vision and Pattern Recognition · Computer Science 2019-11-26 Yongfei Liu , Bo Wan , Xiaodan Zhu , Xuming He

Semantic segmentation (i.e. image parsing) aims to annotate each image pixel with its corresponding semantic class label. Spatially consistent labeling of the image requires an accurate description and modeling of the local contextual…

Computer Vision and Pattern Recognition · Computer Science 2019-01-24 Hasan F. Ates , Sercan Sunetci

Often we wish to predict a large number of variables that depend on each other as well as on other observed variables. Structured prediction methods are essentially a combination of classification and graphical modeling, combining the…

Machine Learning · Statistics 2010-11-19 Charles Sutton , Andrew McCallum

We propose a novel discriminative model for sequence labeling called Bregman conditional random fields (BCRF). Contrary to standard linear-chain conditional random fields, BCRF allows fast parallelizable inference algorithms based on…

Machine Learning · Computer Science 2025-06-03 Caio Corro , Mathieu Lacroix , Joseph Le Roux

Textual grounding, i.e., linking words to objects in images, is a challenging but important task for robotics and human-computer interaction. Existing techniques benefit from recent progress in deep learning and generally formulate the task…

Computer Vision and Pattern Recognition · Computer Science 2018-03-30 Raymond A. Yeh , Minh N. Do , Alexander G. Schwing

We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with…

Computer Vision and Pattern Recognition · Computer Science 2017-05-04 Fanyi Xiao , Leonid Sigal , Yong Jae Lee

Sequence labeling is a widely used method for named entity recognition and information extraction from unstructured natural language data. In clinical domain one major application of sequence labeling involves extraction of medical entities…

Computation and Language · Computer Science 2016-08-03 Abhyuday Jagannatha , Hong Yu

We study the problem of weakly supervised grounded image captioning. That is, given an image, the goal is to automatically generate a sentence describing the context of the image with each noun word grounded to the corresponding region in…

Computer Vision and Pattern Recognition · Computer Science 2021-08-24 Nenglun Chen , Xingjia Pan , Runnan Chen , Lei Yang , Zhiwen Lin , Yuqiang Ren , Haolei Yuan , Xiaowei Guo , Feiyue Huang , Wenping Wang

Visually grounded speech models learn from images paired with spoken captions. By tagging images with soft text labels using a trained visual classifier with a fixed vocabulary, previous work has shown that it is possible to train a model…

Computation and Language · Computer Science 2021-06-24 Kayode Olaleye , Herman Kamper

Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection from a set of bounding box proposals obtained from deep net…

Computer Vision and Pattern Recognition · Computer Science 2018-04-02 Raymond A. Yeh , Jinjun Xiong , Wen-mei W. Hwu , Minh N. Do , Alexander G. Schwing

Despite the substantial progress in recent years, the image captioning techniques are still far from being perfect.Sentences produced by existing methods, e.g. those based on RNNs, are often overly rigid and lacking in variability. This…

Computer Vision and Pattern Recognition · Computer Science 2017-08-14 Bo Dai , Sanja Fidler , Raquel Urtasun , Dahua Lin

Sequence labeling is a fundamental problem in machine learning, natural language processing and many other fields. A classic approach to sequence labeling is linear chain conditional random fields (CRFs). When combined with neural network…

Machine Learning · Computer Science 2020-11-11 Yang Zhou , Yong Jiang , Zechuan Hu , Kewei Tu

Despite successful applications across a broad range of NLP tasks, conditional random fields ("CRFs"), in particular the linear-chain variant, are only able to model local features. While this has important benefits in terms of inference…

Computation and Language · Computer Science 2017-10-13 Fei Liu , Timothy Baldwin , Trevor Cohn

Conditional Random Fields (CRFs) constitute a popular and efficient approach for supervised sequence labelling. CRFs can cope with large description spaces and can integrate some form of structural dependency between labels. In this…

Machine Learning · Computer Science 2015-05-14 Nataliya Sokolovska , Thomas Lavergne , Olivier Cappé , François Yvon