Where to Buy It: Matching Street Clothing Photos in Online Shops

By M. Kiapour, Xufeng Han, Svetlana Lazebnik, Alexander C. Berg, Tamara L. Berg. 2015

470 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

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, background): “are identical or similar to what you have seen in a movie [160] or in the street [161].”
Sampling Matters in Deep Embedding Learning (2017, background): “Models that transform images into rich, semantic representations lie at the heart of modern computer vision, with applications ranging from zero-shot learning [5, 41] and visual search [3, 10, 22, 29], to face recognition [6, 23, 25, 28] or fine-grained retrieval [22, 28, 29].”
DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images (2019, methodology): “Several clothes datasets have been proposed such as [20, 5, 7, 14, 21, 1] as summarized in Table 1.”
Part-Stacked CNN for Fine-Grained Visual Categorization (2015, background): “For instance, the performance of recommendation systems for online shopping [24] could definitely benefit from the analysis of clothing attributes from local parts.”
Automatic Spatially-Aware Fashion Concept Discovery (2017, background): “There have been several clothing datasets collected recently [16, 8, 21, 6, 7].”
Hard-Aware Deeply Cascaded Embedding (2016, methodology): “shion datasets. Our method outperforms state-of-the-art methods by a large margin. 1. Introduction Deep metric embedding has achieved promising results on various tasks, such as visual product search [6, 9, 19, 24, 27, 34], face recognition [4, 10, 22, 32, 40], local image descriptor learning [2, 13”
Fashion Landmark Detection in the Wild (2016, background): “To better capture discriminative information in fashion items, previous works have explored the usage of full image [2], general object proposals [2], bounding boxes [9,17] and even masks [22,18,23,24].”
Exact clothing retrieval approach based on deep neural network (2016, methodology): “[4] compute the CNN features on the detected clothing region and train a three-layer fullyconnected network to learn the similarity between a street feature and a shop feature.”
Fully Convolutional Attention Networks for Fine-Grained Recognition (2016, background): “s [2], car models [3], ﬂower categories [4, 5], food dishes [6, 7], etc. With the great potential in rivaling human experts, it has shown tremendous applications in real world ranging from e-commerce [8, 9] to education [10, 11]. Although great success has been achieved for basic-level recognition i”
DeepStore: In-Storage Acceleration for Intelligent Queries (2019, methodology): “Exact Street to Shop (ESTP) [48] Visual Online shopping of garment item using a real-world garment item 16 0 3 0 4.”
Instance-level Human Parsing via Part Grouping Network (2018, background): “, clothes recognition, retrieval [28,30] and fashion modeling [36], our CIHP that mainly focuses on instance-level human parsing is the largest one and provides more elaborate dense annotations for diverse images.”
Visual7W: Grounded Question Answering in Images (2015, background): “The 7W questions roughly correspond to an array of standard vision tasks: what [9, 15, 39], where [24, 50], when [30, 32], who [35, 42], why [33], how [23, 31] and which [16, 17].”
Memory-Based Neighbourhood Embedding for Visual Recognition (2019, background): “Images from the same or related classes are desired to be mapped to nearby points on a manifold, which is critical to many applications like few-shot learning [41, 31, 37], visual search [7, 13, 45], face/person recognition [20, 26, 43, 2] and fine-grained retrieval [19, 18].”
DeepFashion: Powering Robust Clothes Recognition and Retrieval with Rich Annotations (2016, background): “The previous datasets were labeled with limited number of attributes, bounding boxes [12], or consumer-to-shop pair correspondences [10].”
Learning Fashion Compatibility with Bidirectional LSTMs (2017, methodology): “further utilized deep learning techniques to learn the similarity between street and shop images [5].”
Deep Metric Learning with Angular Loss (2017, background): “…non-linear feature representation, deep metric learning has achieved promising results on various tasks, such as visual product search [1, 20, 17], face recognition [6, 30, 24], feature matching [7], ﬁne-grained image classiﬁcation [33, 38], zero-shot learning [11, 35] and collaborative…”