Rehg, James M.

Associated Organization(s)
Organizational Unit
ArchiveSpace Name Record

Publication Search Results

Now showing 1 - 4 of 4
  • Item
    Joint Semantic Segmentation and 3D Reconstruction from Monocular Video
    (Georgia Institute of Technology, 2014-09) Kundu, Abhijit ; Li, Yin ; Dellaert, Frank ; Li, Fuxin ; Rehg, James M.
    We present an approach for joint inference of 3D scene structure and semantic labeling for monocular video. Starting with monocular image stream, our framework produces a 3D volumetric semantic + occupancy map, which is much more useful than a series of 2D semantic label images or a sparse point cloud produced by traditional semantic segmentation and Structure from Motion(SfM) pipelines respectively. We derive a Conditional Random Field (CRF) model defined in the 3D space, that jointly infers the semantic category and occupancy for each voxel. Such a joint inference in the 3D CRF paves the way for more informed priors and constraints, which is otherwise not possible if solved separately in their traditional frameworks. We make use of class specific semantic cues that constrain the 3D structure in areas, where multiview constraints are weak. Our model comprises of higher order factors, which helps when the depth is unobservable. We also make use of class specific semantic cues to reduce either the degree of such higher order factors, or to approximately model them with unaries if possible. We demonstrate improved 3D structure and temporally consistent semantic segmentation for diffcult, large scale, forward moving monocular image sequence.
  • Item
    Movement Pattern Histogram for Action Recognition and Retrieval
    (Georgia Institute of Technology, 2014) Ciptadi, Arridhana ; Goodwin, Matthew S. ; Rehg, James M.
    We present a novel action representation based on encoding the global temporal movement of an action. We represent an action as a set of movement pattern histograms that encode the global temporal dynamics of an action. Our key observation is that temporal dynamics of an action are robust to variations in appearance and viewpoint changes, making it useful for action recognition and retrieval. We pose the problem of computing similarity between action representations as a maximum matching problem in a bipartite graph. We demonstrate the effectiveness of our method for cross-view action recognition on the IXMAS dataset. We also show how our representation complements existing bag- of-features representations on the UCF50 dataset. Finally we show the power of our representation for action retrieval on a new real-world dataset containing repetitive motor movements emitted by children with autism in an unconstrained classroom setting.
  • Item
    Weakly Supervised Learning of Object Segmentations from Web-Scale Video
    (Georgia Institute of Technology, 2012-10) Hartmann, Glenn ; Grundmann, Matthias ; Hoffman, Judy ; Tsai, David ; Kwatra, Vivek ; Madani, Omid ; Vijayanarasimhan, Sudheendra ; Essa, Irfan ; Rehg, James M. ; Sukthankar, Rahul
    We propose to learn pixel-level segmentations of objects from weakly labeled (tagged) internet videos. Specifically, given a large collection of raw YouTube content, along with potentially noisy tags, our goal is to automatically generate spatiotemporal masks for each object, such as "dog", without employing any pre-trained object detectors. We formulate this problem as learning weakly supervised classifiers for a set of independent spatio-temporal segments. The object seeds obtained using segment-level classifiers are further refined using graphcuts to generate high-precision object masks. Our results, obtained by training on a dataset of 20,000 YouTube videos weakly tagged into 15 classes, demonstrate automatic extraction of pixel-level object masks. Evaluated against a ground-truthed subset of 50,000 frames with pixel-level annotations, we confirm that our proposed methods can learn good object masks just by watching YouTube.
  • Item
    Categorizing Turn-Taking Interactions
    (Georgia Institute of Technology, 2012-10) Prabhakar, Karthir ; Rehg, James M.
    We address the problem of categorizing turn-taking interactions between individuals. Social interactions are characterized by turn-taking and arise frequently in real-world videos. Our approach is based on the use of temporal causal analysis to decompose a space-time visual word representation of video into co-occuring independent segments, called causal sets [1]. These causal sets then serves the input to a multiple instance learning framework to categorize turn- taking interactions. We introduce a new turn-taking interactions dataset consisting of social games and sports rallies. We demonstrate that our formulation of multiple instance learning (QP-MISVM) is better able to leverage the repetitive structure in turn-taking interactions and demonstrates superior performance relative to a conventional bag of words model.