Guiding creative design in online advertising

Mishra, Shaunak; Verma, Manisha; Gligorijević, Jelena

doi:10.1145/3298689.3347022

Cited by 11 publications

(18 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a followup work [30], the focus was on understanding symbolism in ads (via object recognition and image captioning) to match human-generated statements describing actions suggested in the ad. Understanding ad creatives from a brand's perspective was missing in both [15,30], and [22] was the first to study the problem of recommending keywords for guiding a brand's creative design. However, [22] was limited to only text inputs for a brand (e.g., the brand's Wikipedia page), and the recommendation was limited to single words (keywords).…”

Section: Automatic Understanding Of Ad Creativesmentioning

confidence: 99%

“…Understanding ad creatives from a brand's perspective was missing in both [15,30], and [22] was the first to study the problem of recommending keywords for guiding a brand's creative design. However, [22] was limited to only text inputs for a brand (e.g., the brand's Wikipedia page), and the recommendation was limited to single words (keywords). In this paper, we extend the setup in [22] in a non-trivial manner by including multimodal information from past ad campaigns, e.g., images, text in the image (OCR), and Wikipedia pages of associated brands.…”

Section: Automatic Understanding Of Ad Creativesmentioning

confidence: 99%

“…However, [22] was limited to only text inputs for a brand (e.g., the brand's Wikipedia page), and the recommendation was limited to single words (keywords). In this paper, we extend the setup in [22] in a non-trivial manner by including multimodal information from past ad campaigns, e.g., images, text in the image (OCR), and Wikipedia pages of associated brands. We also extend the recommendations from single words to longer keyphrases.…”

Section: Automatic Understanding Of Ad Creativesmentioning

confidence: 99%

“…4.2.2 Ranking metrics. We use the same evaluation metrics from prior work [22], mainly precision (P@K), recall (R@K), and NDCG@K [16] to evaluate the proposed ranking model. It is worth noting that recall is computed differently for evaluating ranking and classification models proposed in this work.…”

Section: Classification Metricsmentioning

confidence: 99%

“…In particular, no connection was made with the brands inferred in creatives, and the associated world knowledge on the inferred brands. As the first work in connecting the above dataset [1] with brands, [22] formulated a keyword ranking problem for a brand (represented via its Wikipedia page), and such keywords could be subsequently used as themes for ad creative design. However, the ad images were not used in [22], and recommended themes were restricted to single words (keywords) as opposed to longer keyphrases which could be more relevant.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Recommending Themes for Ad Creative Design via Visual-Linguistic Representations

Zhou

Mishra

Verma

et al. 2020

Proceedings of the Web Conference 2020

Self Cite

View full text Add to dashboard Cite

There is a perennial need in the online advertising industry to refresh ad creatives, i.e., images and text used for enticing online users towards a brand. Such refreshes are required to reduce the likelihood of ad fatigue among online users, and to incorporate insights from other successful campaigns in related product categories. Given a brand, to come up with themes for a new ad is a painstaking and time consuming process for creative strategists. Strategists typically draw inspiration from the images and text used for past ad campaigns, as well as world knowledge on the brands. To automatically infer ad themes via such multimodal sources of information in past ad campaigns, we propose a theme (keyphrase) recommender system for ad creative strategists. The theme recommender is based on aggregating results from a visual question answering (VQA) task, which ingests the following: (i) ad images, (ii) text associated with the ads as well as Wikipedia pages on the brands in the ads, and (iii) questions around the ad. We leverage transformer based cross-modality encoders to train visual-linguistic representations for our VQA task. We study two formulations for the VQA task along the lines of classification and ranking; via experiments on a public dataset, we show that cross-modal representations lead to significantly better classification accuracy and ranking precision-recall metrics. Cross-modal representations show better performance compared to separate image and text representations. In addition, the use of multimodal information shows a significant lift over using only textual or visual information.

show abstract