HEAT: Iterative relevance feedback with one million images

Suditu, Nicolae; Fleuret, François

doi:10.1109/iccv.2011.6126487

Cited by 8 publications

(7 citation statements)

References 19 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we focus on the target search problem with respect to mental images, for which the goal is to retrieve a specific target that resides only in the user's mind via implicit relevance feedback. In addition to the exact target retrieval problem, the feature re-weighting scheme adopted in our method can also be employed for the retrieval of similar images from a larger dataset using the methods described in [16], [47]; this task will be the focus of our future work. We conducted a user study to evaluate the effectiveness of the proposed re-weighting scheme; here, we present discussions of the experimental results.…”

Section: Methodsmentioning

confidence: 99%

“…Afterwards, Ferecatu [16] extended the framework to category search instead of target search. The application was scaled to large-scale datasets by Suditu and Fleuret [47], [48] who adopted a hierarchical and expandable adaptive trace algorithm benefited from adaptive exploration/exploitation tradeoff. Similar to the idea of mental image retrieval, Auer et al [3] maintained the weights of images by giving less relevant images a constant discount at each iteration.…”

Section: Related Workmentioning

confidence: 99%

“…the absence of an explicit query image, we propose to solve this problem via implicit relevance feedback [58]. Our method is inspired by the mental image retrieval algorithm [15], [16], [47], [48], which introduced an interactive search paradigm based on user feedback. In this method, the target image is modeled as a random variable, and a cumulative probability distribution of this variable is stored to track past interactions with the user.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Query-Free Clothing Retrieval via Implicit Relevance Feedback

Chen

Zhang

et al. 2018

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-Image-based clothing retrieval is receiving increasing interest with the growth of online shopping. In practice, users may often have a desired piece of clothing in mind (e.g., either having seen it before on the street or requiring certain specific clothing attributes) but may be unable to supply an image as a query. We model this problem as a new type of image retrieval task in which the target image resides only in the user's mind (called "mental image retrieval" hereafter). Because of the absence of an explicit query image, we propose to solve this problem through relevance feedback. Specifically, a new Bayesian formulation is proposed that simultaneously models the retrieval target and its high-level representation in the mind of the user (called the "user metric" hereafter) as posterior distributions of pre-fetched shop images and heterogeneous features extracted from multiple clothing attributes, respectively. Requiring only clicks as user feedback, the proposed algorithm is able to account for the variability in human decision-making.Experiments with real users demonstrate the effectiveness of the proposed algorithm.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Query-Free Clothing Retrieval via Implicit Relevance Feedback

Chen

Zhang

et al. 2018

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…Suditu and Fleuret [34] presented an image retrieval system that features iterative relevance feedback for a very large set of images. At each step, the user is presented with a set of images, and selects a single image that is the closest match to the desired query.…”

Section: Relevance Feedbackmentioning

confidence: 99%

DynamicMaps

Kleiman

Lanir

Danon

et al. 2015

Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

We present a novel system for browsing through a very large set of images according to similarity. The images are dynamically placed on a 2D canvas next to their nearest neighbors in a high-dimensional feature space. The layout and choice of images is generated on-the-fly during user interaction, reflecting the user's navigation tendencies and interests. This intuitive solution for image browsing provides a continuous experience of navigating through an infinite 2D grid arranged by similarity. In contrast to common multidimensional embedding methods, our solution does not entail an upfront creation of a full global map. Image map generation is dynamic, fast and scalable, independent of the number of images in the dataset, and seamlessly supports online updates to the dataset. Thus, the technique is a viable solution for massive and constantly varying datasets consisting of millions of images. Evaluation of our approach shows that when using DynamicMaps, users viewed many more images per minute compared to a standard relevance feedback interface, suggesting that it supports more fluid and natural interaction that enables easier and faster movement in the image space. Most users preferred DynamicMaps, indicating it is more exploratory, better supports serendipitous browsing and more fun to use.

show abstract

“…global descriptors of color, texture and shape). Recently, the framework was adopted and extended for large-scale image collections of millions of images in the HEAT retrieval system of Suditu and Fleuret [15]. Motivated by the potential of this queryfree retrieval approach, our research takes a complementary direction and improves on its searching capabilities.…”

Section: Related Workmentioning

confidence: 99%

Iterative relevance feedback with adaptive exploration/exploitation trade-off

Suditu

Fleuret

2012

Proceedings of the 21st ACM International Conference on Information and Knowledge Management

Self Cite

View full text Add to dashboard Cite

Content-based image retrieval systems have to cope with two different regimes: understanding broadly the categories of interest to the user, and refining the search in this or these categories to converge to specific images among them. Here, in contrast with other types of retrieval systems, these two regimes are of great importance since the search initialization is hardly optimal (i.e. the page-zero problem) and the relevance feedback must tolerate the semantic gap of the image's visual features.We present a new approach that encompasses these two regimes, and infers from the user actions a seamless transition between them. Starting from a query-free approach meant to solve the page-zero problem, we propose an adaptive exploration/exploitation trade-off that transforms the original framework into a versatile retrieval framework with full searching capabilities. Our approach is compared to the state-of-the-art it extends by conducting user evaluations on a collection of 60,000 images from the ImageNet database.

show abstract

HEAT: Iterative relevance feedback with one million images

Cited by 8 publications

References 19 publications

Query-Free Clothing Retrieval via Implicit Relevance Feedback

Query-Free Clothing Retrieval via Implicit Relevance Feedback

DynamicMaps

Iterative relevance feedback with adaptive exploration/exploitation trade-off

Contact Info

Product

Resources

About