Topic Models for Image Annotation and Text Illustration

By Yansong Feng, Mirella Lapata. 2010

123 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Experience Grounds Language (2020, background): “This idea is not new (Chen and Mooney, 2008; Feng and Lapata, 2010; Bruni et al., 2014; Lazaridou et al., 2016) and has accelerated in the last few years.”
Self-Supervised Learning of Visual Features through Embedding Images into Text Topic Spaces (2017, neutral): “[11] uses the joint BoW representation of text and image for learning LDA.”
Visual Madlibs: Fill in the blank Image Generation and Question Answering (2015, methodology): “The second type of approach explored methods to make use of existing text either directly associated with an image [11, 1] or retrieved from visually similar images [27, 19, 24].”
A Shared Task on Multimodal Machine Translation and Crosslingual Image Description (2016, background): “, 2016), image retrieval based on textual and visual cues (Feng and Lapata, 2010), visual question answering (Yang et al.”
Domain-Specific Image Captioning (2014, background): “The MixLDA model (Feng and Lapata, 2010b; Feng and Lapata, 2010a) learns from news images and natural language descriptions, but to generate words for a new image it requires both a query image and query text in the form of a news article.”
Composing Simple Image Descriptions using Web-scale N-grams (2011, methodology): “Our work contrasts to most previous approaches in four key aspects: ﬁrst, we compose fresh sentences from scratch, instead of retrieving (Farhadi et al. (2010)), or summarizing existing text fragments associated with an image (e.g., Aker and Gaizauskas (2010), Feng and Lapata (2010a)).”
Multimodal News Article Analysis (2017, background): “Many works have addressed this task, some in the news article domain [Feng and Lapata, 2010; 2013], but more commonly in datasets of images with short and accurate descriptions [Barnard et al., 2003; Kovashka et al., 2015; Rasiwasia et al., 2007; Douze et al., 2011].”
Generalizing Image Captions for Image-Text Parallel Corpus (2013, background): “Other work (e.g. Feng and Lapata (2010a), Feng and Lapata (2010b)) uses computer vision to bias summarization of text associated with images to produce descriptions.”
How Many Words Is a Picture Worth? Automatic Caption Generation for News Images (2010, methodology): “Our experiments made use of the probabilistic model presented in Feng and Lapata (2010).”
A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching (2013, unknown): “[4] and subsequent extensions [6, 7, 11, 22, 32] jointly model image features (predominantly SIFT and HOG derivatives) and language words as mixed memberships over latent topics with considerable success.”
Visual Madlibs: Fill in the Blank Description Generation and Question Answering (2015, background): “Early work in this area focused on detecting content elements and then composing captions [20, 36, 28, 11, 18] or made use of existing text either directly associated with an image [12, 1] or retrieved from visually similar images [29, 21, 26].”
Automatic Caption Generation for News Images (2013, background): “• Chapter 5 elaborates on the paper “Topic Models for Image Annotation and Text Illustration” (Feng and Lapata, 2010b), where we demonstrate how a classic topic model can be extended to perform the automatic image annotation task in our news dataset.”
Title Generation with Quasi-Synchronous Grammar (2010, background): “Secondly, the model often generates an appropriate title that is lexically distinct from the reference even though it expresses similar meaning.”