Garment Recommendation with Memory Augmented Neural Networks

Divitiis, Lavinia De; Becattini, Federico; Baecchi, Claudio; Bimbo, Alberto Del

doi:10.1007/978-3-030-68790-8_23

Cited by 19 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Follow-up works have extended and refined the formulation of the NTM [11], [12], [13], [39]. Recently, several declinations of MANNs have been proposed to tackle more complex problems such as online learning [40], object tracking [41], [42], visual question answering [43], [44], person re-identification [45], action recognition [46] and garment recommendation [47].…”

Section: Memory Augmented Neural Networkmentioning

confidence: 99%

SMEMO: Social Memory for Trajectory Forecasting

Marchetti¹,

Becattini²,

Seidenari³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Effective modeling of human interactions is of utmost importance when forecasting behaviors such as future trajectories. Each individual, with its motion, influences surrounding agents since everyone obeys to social non-written rules such as collision avoidance or group following. In this paper we model such interactions, which constantly evolve through time, by looking at the problem from an algorithmic point of view, i.e. as a data manipulation task. We present a neural network based on an end-to-end trainable working memory, which acts as an external storage where information about each agent can be continuously written, updated and recalled. We show that our method is capable of learning explainable cause-effect relationships between motions of different agents, obtaining state-of-the-art results on multiple trajectory forecasting datasets.

show abstract

Section: Memory Augmented Neural Networkmentioning

confidence: 99%

SMEMO: Social Memory for Trajectory Forecasting

Marchetti¹,

Becattini²,

Seidenari³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another fundamental topic is clothing retrieval [2,[39][40][41], which can be used to find a specific clothes in an online shop using a picture taken in the wild. In addition to that, recommendation systems are also of great interest in order to suggest particular clothes based on the user's preferences [3,[42][43][44][45][46][47]. The task that is most relevant to this paper is that of synthesizing clothes images.…”

Section: Related Workmentioning

confidence: 99%

Would Your Clothes Look Good on Me? Towards Transferring Clothing Styles with Adaptive Instance Normalization

Fontanini¹,

Ferrari²

2022

Sensors

View full text Add to dashboard Cite

Several applications of deep learning, such as image classification and retrieval, recommendation systems, and especially image synthesis, are of great interest to the fashion industry. Recently, image generation of clothes gained lot of popularity as it is a very challenging task that is far from being solved. Additionally, it would open lots of possibilities for designers and stylists enhancing their creativity. For this reason, in this paper we propose to tackle the problem of style transfer between two different people wearing different clothes. We draw inspiration from the recent StarGANv2 architecture that reached impressive results in transferring a target domain to a source image and we adapted it to work with fashion images and to transfer clothes styles. In more detail, we modified the architecture to work without the need of a clear separation between multiple domains, added a perceptual loss between the target and the source clothes, and edited the style encoder to better represent the style information of target clothes. We performed both qualitative and quantitative experiments with the recent DeepFashion2 dataset and proved the efficacy and novelty of our method.

show abstract

“…Diversity is enforced with the introduction of a variety loss, which optimizes only the best prediction thus leaving the model free to explore the output space with multiple outcomes. The usage of a variety loss is now a common approach for generating multimodal predictions, not only for trajectory forecasting [5,15,24,30,35,42,64]. In the present article, we leverage this domain knowledge by considering the variety loss to enable the training of our DVMS model aiming to produce diverse plausible trajectories.…”

Section: Multiple Trajectory Prediction In Roboticsmentioning

confidence: 99%

Deep variational learning for multiple trajectory prediction of 360° head movements

Guimard

Sassatelli

Marchetti

et al. 2022

Proceedings of the 13th ACM Multimedia Systems Conference

Self Cite

View full text Add to dashboard Cite

Prediction of head movements in immersive media is key to design efficient streaming systems able to focus the bandwidth budget on visible areas of the content. Numerous proposals have therefore been made in the recent years to predict 360°images and videos. However, the performance of these models is limited by a main characteristic of the head motion data: its intrinsic uncertainty. In this article, we present an approach to generate multiple plausible futures of head motion in 360°videos, given a common past trajectory. Our method provides likelihood estimates of every predicted trajectory, enabling direct integration in streaming optimization. To the best of our knowledge, this is the first work that considers the problem of multiple head motion prediction for 360°video streaming. We first quantify this uncertainty from the data. We then introduce our discrete variational multiple sequence (DVMS) learning framework, which builds on deep latent variable models. We design a training procedure to obtain a flexible and lightweight stochastic prediction model compatible with sequence-to-sequence recurrent neural architectures. Experimental results on 3 different datasets show that our method DVMS outperforms competitors adapted from the selfdriving domain by up to 37% on prediction horizons up to 5 sec., at lower computational and memory costs. Finally, we design a method to estimate the respective likelihoods of the multiple predicted trajectories, by exploiting the stationarity of the distribution of the prediction error over the latent space. Experimental results on 3 datasets show the quality of these estimates, and how they depend on the video category. CCS CONCEPTS• Human-centered computing → Virtual reality; • Information systems → Multimedia streaming; • Computing methodologies → Neural networks.

show abstract

Garment Recommendation with Memory Augmented Neural Networks

Cited by 19 publications

References 25 publications

SMEMO: Social Memory for Trajectory Forecasting

SMEMO: Social Memory for Trajectory Forecasting

Would Your Clothes Look Good on Me? Towards Transferring Clothing Styles with Adaptive Instance Normalization

Deep variational learning for multiple trajectory prediction of 360° head movements

Contact Info

Product

Resources

About