Multiple Trajectory Prediction of Moving Agents With Memory Augmented Networks

Marchetti, Francesco; Becattini, Federico; Seidenari, Lorenzo; Bimbo, Alberto Del

doi:10.1109/tpami.2020.3008558

Cited by 39 publications

(19 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiments we use the KITTI dataset [9], which comprehends several data modalities such as calibrated RGB streams, LiDAR 3D point clouds, annotated objects, semantic segmentations and IMU. Here we refer to the tracking dataset, which has often been used for trajectory prediction [1], [2], [4], [29]. Despite this, several splits of the dataset have been used across prior work.…”

Section: A Datasets and Metricsmentioning

confidence: 99%

Multiple Future Prediction Leveraging Synthetic Trajectories

Berlincioni

Becattini

Seidenari

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

Self Cite

View full text Add to dashboard Cite

Trajectory prediction is an important task, especially in autonomous driving. The ability to forecast the position of other moving agents can yield to an effective planning, ensuring safety for the autonomous vehicle as well for the observed entities. In this work we propose a data driven approach based on Markov Chains to generate synthetic trajectories, which are useful for training a multiple future trajectory predictor. The advantages are twofold: on the one hand synthetic samples can be used to augment existing datasets and train more effective predictors; on the other hand, it allows to generate samples with multiple ground truths, corresponding to diverse equally likely outcomes of the observed trajectory. We define a trajectory prediction model and a loss that explicitly address the multimodality of the problem and we show that combining synthetic and real data leads to prediction improvements, obtaining state of the art results.

show abstract

Section: A Datasets and Metricsmentioning

confidence: 99%

Multiple Future Prediction Leveraging Synthetic Trajectories

Berlincioni

Becattini

Seidenari

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Indeed, videos collected form a self-driving car are based on an egocentric view of the scene, similarly to first person videos collected by humans. The main tasks useful in this area include either pedestrian intents prediction [30,31,32], future vehicle localization [33], or both [34]. Another important task in this setting, is predicting the time to the occurence of an event, such as a stopping or a collision [35].…”

Section: Application Areasmentioning

confidence: 99%

Predicting the Future from First Person (Egocentric) Vision: A Survey

Rodin¹,

Furnari²,

Mavroedis³

et al. 2021

Preprint

View full text Add to dashboard Cite

Egocentric videos can bring a lot of information about how humans perceive the world and interact with the environment, which can be beneficial for the analysis of human behaviour. The research in egocentric video analysis is developing rapidly thanks to the increasing availability of wearable devices and the opportunities offered by new large-scale egocentric datasets. As computer vision techniques continue to develop at an increasing pace, the tasks related to the prediction of future are starting to evolve from the need of understanding the present. Predicting future human activities, trajectories and interactions with objects is crucial in applications such as human-robot interaction, assistive wearable technologies for both industrial and daily living scenarios, entertainment and virtual or augmented reality. This survey summarises the evolution of studies in the context of future prediction from egocentric vision making an overview of applications, devices, existing problems, commonly used datasets, models and input modalities. Our analysis highlights that methods for future prediction from egocentric vision can have a significant impact in a range of applications and that further research efforts should be devoted to the standardisation of tasks and the proposal of datasets considering real-world scenarios such as the ones with an industrial vocation.

show abstract

“…Memory Augmented Neural Networks (MANN) are a particular declination of Neural Networks that exploit a controller network with an external memory, in which samples can be explicitly stored. These models have been originally introduced to solve algorithmic tasks [4,23,27,29], however several applications of MANNs have been proposed in literature [16,[18][19][20]31]. The first work to propose a model equipped with an external memory has been Neural Turing Machines (NTM) [4].…”

Section: Memory Augmented Networkmentioning

confidence: 99%

“…In particular, we focus on generating different modalities to compose an outfit, rather than suggesting redundant and similar items. To achieve this, we exploit a persistent Memory Augmented Neural Network (MANN), which has proven effective to model diversity [17,18]. This kind of models finds its strength in the usage of an external memory, where samples can be explicitly stored at training time and then be read at inference time.…”

Section: Introductionmentioning

confidence: 99%

Garment Recommendation with Memory Augmented Neural Networks

Divitiis¹,

Becattini²,

Baecchi³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Fashion plays a pivotal role in society. Combining garments appropriately is essential for people to communicate their personality and style. Also different events require outfits to be thoroughly chosen to comply with underlying social clothing rules. Therefore, combining garments appropriately might not be trivial. The fashion industry has turned this into a massive source of income, relying on complex recommendation systems to retrieve and suggest appropriate clothing items for customers. To perform better recommendations, personalized suggestions can be performed, taking into account user preferences or purchase histories. In this paper, we propose a garment recommendation system to pair different clothing items, namely tops and bottoms, exploiting a Memory Augmented Neural Network (MANN). By training a memory writing controller, we are able to store a non-redundant subset of samples, which is then used to retrieve a ranked list of suitable bottoms to complement a given top. In particular, we aim at retrieving a variety of modalities in which a certain garment can be combined. To refine our recommendations, we then include user preferences via Matrix Factorization. We experiment on IQON3000, a dataset collected from an online fashion community, reporting state of the art results.

show abstract

Multiple Trajectory Prediction of Moving Agents With Memory Augmented Networks

Cited by 39 publications

References 63 publications

Multiple Future Prediction Leveraging Synthetic Trajectories

Multiple Future Prediction Leveraging Synthetic Trajectories

Predicting the Future from First Person (Egocentric) Vision: A Survey

Garment Recommendation with Memory Augmented Neural Networks

Contact Info

Product

Resources

About