• Publications
  • Influence
Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding
TLDR
We propose a novel Hollywood in Homes approach to collect a large-scale dataset of boring videos of daily activities. Expand
  • 432
  • 108
  • PDF
Learning from Synthetic Humans
TLDR
We present SURREAL: a large-scale dataset with synthetically-generated but realistic images of people rendered from 3D sequences of human motion capture data. Expand
  • 408
  • 59
  • PDF
Long-Term Temporal Convolutions for Action Recognition
TLDR
In this work we learn video representations using neural networks with long-term temporal convolutions with increased temporal extents improve the accuracy of action recognition. Expand
  • 564
  • 53
  • PDF
BodyNet: Volumetric Inference of 3D Human Body Shapes
TLDR
BodyNet is an end-to-end trainable network that benefits from (i) a volumetric 3D loss, (ii) a multi-view re-projection loss, and (iii) intermediate supervision. Expand
  • 164
  • 26
  • PDF
Learning Joint Reconstruction of Hands and Manipulated Objects
TLDR
We present an end-to-end learnable model that exploits a novel contact loss that favors phys- ically plausible hand-object constellations. Expand
  • 72
  • 13
  • PDF
Toward retail product recognition on grocery shelves
This paper addresses the problem of retail product recognition on grocery shelf images. We present a technique for accomplishing this task with a low time complexity. We decompose the problem intoExpand
  • 26
  • 2
  • PDF
Efficient large-scale action recognition in videos using extreme learning machines
TLDR
We describe a novel approach for large-scale action recognition from videos in a realistic setting. Expand
  • 29
  • 1
Product placement detection based on image processing
TLDR
We propose a novel technique for inventory management with the assumption that we can extract meaningful information from images using planogram context. Expand
  • 5
  • 1
Tutoring Robots - Multiparty Multimodal Social Dialogue with an Embodied Tutor
TLDR
This project explores a novel experimental setup towards building spoken, multi-modally rich, and human-like multiparty tutoring agent. Expand
  • 7
  • PDF
Extreme Learning Machine for Large-Scale Action Recognition
In this paper, we describe the method we applied for the action recognition task on the THUMOS 2014 challenge dataset. We study human action recognition in RGB videos through low-level features byExpand
  • 9
  • PDF