Skip to search formSkip to main contentSkip to account menu
Activity Forecasting
TLDR
The unified model uses state-of-the-art semantic scene understanding combined with ideas from optimal control theory to achieve accurate activity forecasting and shows how the same techniques can improve the results of tracking algorithms by leveraging information about likely goals and trajectories.
View via Publisher
Deep Supervised Hashing with Triplet Labels
TLDR
A triplet label based deep hashing method which aims to maximize the likelihood of the given triplet labels, which outperforms all the baselines on CIFAR-10 and NUS-WIDE datasets, including the state-of-the-art method DPSH.
View PDF on arXiv
Pixel-Level Hand Detection in Ego-centric Videos
TLDR
This work presents a fully labeled indoor/outdoor ego-centric hand detection benchmark dataset containing over 200 million labeled pixels, which contains hand images taken under various illumination conditions and highlights the effectiveness of sparse features and the importance of modeling global illumination.
View on IEEE
Going Deeper into First-Person Activity Recognition
TLDR
By learning to recognize objects, actions and activities jointly, the performance of individual recognition tasks also increase by 30% (actions) and 14% ( objects) and the results of extensive ablative analysis are included to highlight the importance of network design decisions.
View on IEEE
DLow: Diversifying Latent Flows for Diverse Human Motion Prediction
TLDR
A novel sampling method, Diversifying Latent Flows (DLow), to produce a diverse set of samples from a pretrained deep generative model that outperforms state-of-the-art baseline methods in terms of sample diversity and accuracy.
View PDF on arXiv
r2p2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting
TLDR
A method to forecast a vehicle’s ego-motion as a distribution over spatiotemporal paths, conditioned on features embedded in an overhead map, and obtains expressions for the cross-entropy metrics that can be efficiently evaluated and differentiated, enabling stochastic-gradient optimization.
View via Publisher
3D Human Motion Estimation via Motion Compression and Refinement
TLDR
A technique for generating smooth and accurate 3D human pose and motion estimates from RGB video sequences using auto-encoder-based motion compression and a residual representation learned through motion refinement.
View PDF on arXiv
NavCog: a navigational cognitive assistant for the blind
TLDR
This work proposes a smartphone-based system that provides turn-by-turn navigation assistance based on accurate real-time localization over large spaces and shows that the system is capable of guiding visually impaired users in complex and unfamiliar environments.
View on ACM
Human motion trajectory prediction: a survey
TLDR
A survey of human motion trajectory prediction and proposes a taxonomy that categorizes existing methods based on the motion modeling approach and level of contextual information used.
View on SAGE
First-Person Activity Forecasting with Online Inverse Reinforcement Learning
TLDR
DARKO learns and forecasts from first-person visual observations of the user’s daily behaviors via an Online Inverse Reinforcement Learning (IRL) approach, and shows DARKO forecasts goals better than competing methods in both noisy and ideal settings.
View on IEEE
...
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy, Terms of Service, and Dataset License