Image ranking and retrieval based on multi-attribute queries

By Behjat Siddiquie, Rogério Schmidt Feris, Larry S. Davis. Computer Vision and Pattern Recognition, 2011

390 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/dd7a19664c7f698cbb5d6a48a43012103f73b71a

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Multi-Task CNN Model for Attribute Prediction (2015, neutral): “dation, multimedia search and retrieval [5], [13], [14], [20], [30], [35], [36], [38], [43], [49].”
Exploiting local features from deep networks for image retrieval (2015, background): “Some approaches rely on semantic concepts or attributes to capture mid-level image information [7, 28, 24], where attributes are binary values indicating the presence of semantic characteristics.”
Crowdsourcing in Computer Vision (2016, positive): “…attribute-based applications can be developed, e.g., for object recognition [Farhadi et al., 2009, Branson et al., 2010] or image retrieval [Kovashka et al., 2012, Siddiquie et al., 2011], an attribute vocabulary needs to be devised, i.e., a list of attribute terms for which models will be trained.”
Multi-attribute spaces: Calibration for attribute fusion and similarity search (2012, methodology): “Recently, more powerful approaches to the problem [10, 18] have shown excellent promise for general use.”
An Attribute-Assisted Reranking Model for Web Image Search (2015, background): “On the other hand, semantic attributes have received tremendous attention recently, where their effectiveness was demonstrated in broad applications, including face verification [6], object recognition [5]–[11], fine-grained visual categorization [16], classification with humans-in-the-loop [22] and”
A Deep Sum-Product Architecture for Robust Facial Attributes Analysis (2013, background): “[19] exploited the cooccurrences of attributes to improve image search performance.”
Recognizing Complex Events Using Large Margin Joint Low-Level Event Model (2012, background): “On the other hand, the use of different attributes for the recognition task has recently been explored in different computer vision applications such as object classification [10–13], image ranking and retrieval [14] and human action recognition [15].”
Cross-Domain Image Retrieval with a Dual Attribute-Aware Ranking Network (2015, background): “Among other applications, attributes have been used for zero-shot learning [27], image ranking and retrieval [38, 22, 17], fine-grained categorization [3], scene understanding [35], and sentence generation from images [25].”
WhittleSearch: Image search with relative attribute feedback (2012, background): “The same attributes can also be used to pose queries in semantic terms [12, 23].”
Hi, magic closet, tell me what to wear! (2012, methodology): “We evaluate their performance via Normalized Discounted Cumulative Gain (NDCG) [12] which is commonly used to evaluate ranking systems.”
Label-Embedding for Image Classification (2015, neutral): “Attributes have been used for image description [19], [18], [9], caption generation [27], [41], face recognition [29], [51], [10], image retrieval [28], [56], [15], action recognition [32], [69], novelty detection [62] and object classiﬁcation [30], [18], [64], [65], [34], [54], [38].”
A Pooling Approach to Modelling Spatial Relations for Image Retrieval and Annotation (2014, methodology): “esponse scores from each object detector is used as a score and the MARR model [17]. The latter uses object detections as the features Structured queries Method mAP Part based detector [5] 7:76% MARR [28] 10:01% Structure model [17] 11:16% Our model 11:12% Extended dataset of human queries Our model”
Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set (2012, background): “The precision calculation is extended to multiple attributes according to [10].”
Learning Decision Trees Recurrently Through Communication (2021, methodology): “Attributes have been used for image description [14, 6], caption generation [47], face recognition [7], image retrieval [33, 54], action recognition [67, 63], novelty detection [57] and object classification [35, 53, 42, 52, 8].”
Discovering Attribute Shades of Meaning with the Crowd (2015, methodology): “For example, an image search system that allows attribute-based queries (Kumar et al, 2011; Siddiquie et al, 2011; Scheirer et al, 2012; Rastegari et al, 2013; Vaquero et al, 2009; Kovashka et al, 2012) will frustrate a user if the system’s notion of “formal” does not match the user’s notion.”
Attribute feedback (2012, background): “[18] proposed a structural SVM based approach for image search using multi-attribute text-based queries specified by users.”
Latent Embeddings for Zero-Shot Classification (2016, background): “They are typically collected through costly human annotation [7, 17, 28] and have shown promising results [1, 3, 6, 20, 22, 33, 34, 40] in various computer vision problems.”