First-Person Activity Forecasting with Online Inverse Reinforcement Learning

Rhinehart, Nicholas; Kitani, Kris M.

doi:10.1109/iccv.2017.399

Cited by 121 publications

(77 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Past works on anticipation from egocentric visual data have investigated different problems and considered different evaluation frameworks [5,10,17,42,45,47,50,53,65,68]. Instead, we tackle the egocentric action anticipation challenge recently proposed in [8], which has been little investigated so far [16].…”

Section: Anticipation In First Person Visionmentioning

confidence: 99%

What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention

Furnari

Farinella

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

168

218

View full text Add to dashboard Cite

Egocentric action anticipation consists in understanding which objects the camera wearer will interact with in the near future and which actions they will perform. We tackle the problem proposing an architecture able to anticipate actions at multiple temporal scales using two LSTMs to 1) summarize the past, and 2) formulate predictions about the future. The input video is processed considering three complimentary modalities: appearance (RGB), motion (optical flow) and objects (object-based features). Modalityspecific predictions are fused using a novel Modality AT-Tention (MATT) mechanism which learns to weigh modalities in an adaptive fashion. Extensive evaluations on two large-scale benchmark datasets show that our method outperforms prior art by up to +7% on the challenging EPIC-Kitchens dataset including more than 2500 actions, and generalizes to EGTEA Gaze+. Our approach is also shown to generalize to the tasks of early action recognition and action recognition. Our method is ranked first in the public leaderboard of the EPIC-Kitchens egocentric action anticipation challenge 2019. Please see the project web page for code and additional details: http://iplab.dmi.unict.it/rulstm.

show abstract

Section: Anticipation In First Person Visionmentioning

confidence: 99%

What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention

Furnari

Farinella

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

168

218

View full text Add to dashboard Cite

show abstract

“…Such models aim to anticipate future trajectories of a ball and individual players. IRL has also been recently applied to activity forecasting from firstperson egocentric daily activity videos [33]. On the other hand, Wu et al [49] combine on-wrist motion accelerometer and camera to perform daily intention anticipation.…”

Section: Related Workmentioning

confidence: 99%

Leveraging the Present to Anticipate the Future in Videos

Miech

Laptev

Šivic

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

Anticipating actions before they are executed is crucial for a wide range of practical applications including autonomous driving and robotics. While most prior work in this area requires partial observation of executed actions, in the paper we focus on anticipating actions seconds before they start. Our proposed approach is the fusion of a purely anticipatory model with a complementary model constrained to reason about the present. In particular, the latter predicts present action and scene attributes, and reasons about how they evolve over time. By doing so, we aim at modeling action anticipation at a more conceptual level than directly predicting future actions. Our model outperforms previously reported methods on the EPIC-KITCHENS and Breakfast datasets.

show abstract

“…Online Inverse Reinforcement Learning (Rhinehart and Kitani, 2017) is a novel method for predicting future behaviors by modeling the interactions between the subject, objects, and their environment, through a first-person mounted camera. The system makes use of online inverse reinforcementlearning.Thus,makingitpossibletocontinuallydiscovernewlong-termgoalsand relationships.…”

Section: Approachmentioning

confidence: 99%

Accelerating Deep Action Recognition Networks for Real-Time Applications

Ivorra-Piqueres

Vargas

Martinez-Gonzalez

2019

International Journal of Computer Vision and Image Processing

View full text Add to dashboard Cite

In this work, the authors propose several techniques for accelerating a modern action recognition pipeline. This article reviewed several recent and popular action recognition works and selected two of them as part of the tools used for improving the aforementioned acceleration. Specifically, temporal segment networks (TSN), a convolutional neural network (CNN) framework that makes use of a small number of video frames for obtaining robust predictions which have allowed to win the first place in the 2016 ActivityNet challenge, and MotionNet, a convolutional-transposed CNN that is capable of inferring optical flow RGB frames. Together with the last proposal, this article integrated a new software for decoding videos that takes advantage of NVIDIA GPUs. This article shows a proof of concept for this approach by training the RGB stream of the TSN network in videos loaded with NVIDIA Video Loader (NVVL) of a subset of daily actions from the University of Central Florida 101 dataset.

show abstract

First-Person Activity Forecasting with Online Inverse Reinforcement Learning

Cited by 121 publications

References 30 publications

What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention

What Would You Expect? Anticipating Egocentric Actions With Rolling-Unrolling LSTMs and Modality Attention

Leveraging the Present to Anticipate the Future in Videos

Accelerating Deep Action Recognition Networks for Real-Time Applications

Contact Info

Product

Resources

About