When Was That Made?

@article{Vittayakorn2017WhenWT,
  title={When Was That Made?},
  author={Sirion Vittayakorn and Alexander C. Berg and Tamara L. Berg},
  journal={2017 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2017},
  pages={715-724}
}
In this paper, we explore deep learning methods for estimating when the objects were made. Temporal estimation of objects is a challenging task which requires expertise in the object domain. With temporal information of objects, historian, genealogists, sociologist, archaeologist or conservationists can study the past through the objects. Toward this goal, we utilize features from existing deep networks and fine-tune new networks for temporal estimation task. The results demonstrate that the… Expand
Improving the Chronological Sorting of Images through Occlusion: A Study on the Notre-Dame Cathedral Fire
TLDR
This work trains a data-driven method to chronologically sort images originated from a real event, the Notre-Dame Cathedral fire, which broke out on April 15th, 2019, and investigates several occlusion strategies to improve classification accuracy, generalization and explainability of the method. Expand
Fashion Forward: Forecasting Visual Style in Fashion
TLDR
This work introduces the first approach to predict the future popularity of styles discovered from fashion images in an unsupervised manner, and trains a forecasting model to represent their trends over time. Expand
Fashion Meets Computer Vision
TLDR
A comprehensive survey of more than 200 major fashion-related works covering four main aspects for enabling intelligent fashion and highlighting promising directions for future research. Expand
Bilinear Image Translation for Temporal Analysis of Photo Collections
TLDR
By analyzing the generated history-lapse videos, a new trainable bilinear factor separation module is introduced that can identify object deformations across time, extracting interesting changes in visual style over decades. Expand
Fashion analysis and understanding with artificial intelligence
TLDR
The progress in fashion research is introduced and a taxonomy of these fashion studies that include low-level fashion recognition, middle- level fashion understanding and high-levelfashion applications is provided. Expand
A Novel Approach to Analyze Fashion Digital Archive from Humanities
TLDR
A new fashion image archive called Chronicle Archive of Tokyo Street Fashion (CAT STREET), which includes images showing the clothing people wore in their daily lives during the period 1970–2017, is created based on a review of the limitations in the existing digital fashion archives. Expand
Content-Based Detection of Temporal Metadata Manipulation
TLDR
This work proposes an end-to-end approach to verify whether the purported time of capture of an image is consistent with its content and geographic location, and improves upon previous work on a large benchmark dataset. Expand
CAT STREET: Chronicle Archive of Tokyo Street-fashion
TLDR
A new fashion image archive, Chronicle Archive of Tokyo Street-fashion (CAT STREET), is proposed, to shed light on daily life fashion trends and corroborated the rules-of-thumb for two fashion trend phenomena, namely how economic conditions affect fashion style share in the long term and how fashion styles emerge in the street and diffuse from street to street. Expand
Fashion Meets Computer Vision: A Survey
TLDR
A comprehensive survey of more than 200 major fashion-related works covering four main aspects for enabling intelligent fashion and highlighting promising directions for future research. Expand
...
1
2
...

References

SHOWING 1-10 OF 52 REFERENCES
Style-Aware Mid-level Representation for Discovering Visual Connections in Space and Time
We present a weakly-supervised visual data mining approach that discovers connections between recurring mid-level visual elements in historic (temporal) and geographic (spatial) image collections,Expand
Discovering objects and their location in images
TLDR
This work treats object categories as topics, so that an image containing instances of several categories is modeled as a mixture of topics, and develops a model developed in the statistical text literature: probabilistic latent semantic analysis (pLSA). Expand
Object Detectors Emerge in Deep Scene CNNs
TLDR
This work demonstrates that the same network can perform both scene recognition and object localization in a single forward-pass, without ever having been explicitly taught the notion of objects. Expand
Visualizing and Understanding Convolutional Networks
TLDR
A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark. Expand
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
TLDR
DeCAF, an open-source implementation of deep convolutional activation features, along with all associated network parameters, are released to enable vision researchers to be able to conduct experimentation with deep representations across a range of visual concept learning paradigms. Expand
Deep Residual Learning for Image Recognition
TLDR
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
Learning Deep Features for Scene Recognition using Places Database
TLDR
A new scene-centric database called Places with over 7 million labeled pictures of scenes is introduced with new methods to compare the density and diversity of image datasets and it is shown that Places is as dense as other scene datasets and has more diversity. Expand
Discovering localized attributes for fine-grained recognition
TLDR
This approach uses a latent conditional random field model to discover candidate attributes that are detectable and discriminative, and then employs a recommender system that selects attributes likely to be semantically meaningful from image datasets annotated only with fine-grained category labels and object bounding boxes. Expand
What makes Paris look like Paris?
TLDR
It is shown that geographically representative image elements can be discovered automatically from Google Street View imagery in a discriminative manner and it is demonstrated that these elements are visually interpretable and perceptually geo-informative. Expand
...
1
2
3
4
5
...