• Publications
  • Influence
TALL: Temporal Activity Localization via Language Query
TLDR
A novel Cross-modal Temporal Regression Localizer (CTRL) is proposed to jointly model text query and video clips, output alignment scores and action boundary regression results for candidate clips, and Experimental results show that CTRL outperforms previous methods significantly on both datasets. Expand
Global data association for multi-object tracking using network flows
TLDR
A network flow based optimization method for data association needed for multiple object tracking that is efficient and does not require hypotheses pruning, and compared with previous results on two public pedestrian datasets to show its improvement. Expand
Robust Object Tracking by Hierarchical Association of Detection Responses
TLDR
This work presents a detection-based three-level hierarchical association approach to robustly track multiple objects in crowded environments from a single camera and shows a great improvement in performance compared to previous methods. Expand
Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors
  • Bo Wu, R. Nevatia
  • Computer Science
  • Tenth IEEE International Conference on Computer…
  • 17 October 2005
TLDR
The human detection problem is formulated as maximum a posteriori (MAP) estimation, and edgelet features are introduced, which are a new type of silhouette oriented features that are learned by a boosting method. Expand
An online learned CRF model for multi-target tracking
  • Bo Yang, R. Nevatia
  • Mathematics, Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 16 June 2012
TLDR
The online CRF approach is more powerful at distinguishing spatially close targets with similar appearances, as well as in dealing with camera motions, and an efficient algorithm is introduced for finding an association with low energy cost. Expand
Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors
  • Bo Wu, R. Nevatia
  • Computer Science
  • International Journal of Computer Vision
  • 1 November 2007
TLDR
This work presents an approach to automatically detect and track multiple, possibly partially occluded humans in a walking or standing pose from a single camera, which may be stationary or moving. Expand
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
TLDR
A novel Temporal Unit Regression Network (TURN) model, which jointly predicts action proposals and refines the temporal boundaries by temporal coordinate regression, and outperforms state-of-the-art performance on THUMOS-14 and ActivityNet datasets. Expand
Recognition and Segmentation of 3-D Human Action Using HMM and Multi-class AdaBoost
TLDR
This work decomposes the high dimensional 3-D joint space into a set of feature spaces where each feature corresponds to the motion of a single joint or combination of related multiple joints. Expand
Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching
  • Fengjun Lv, R. Nevatia
  • Mathematics, Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 17 June 2007
TLDR
Each action is modeled as a series of synthetic 2D human poses rendered from a wide range of viewpoints and the constraints on transition of the synthetic poses is represented by a graph model called Action Net. Expand
Tracking multiple humans in complex situations
  • Tao Zhao, R. Nevatia
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 September 2004
TLDR
This work shows how multiple human objects are segmented and their global motions are tracked in 3D using ellipsoid human shape models and estimates the modes (e.g., walking, running, standing) of the locomotion and 3D body postures by making inference in a prior locomotion model. Expand
...
1
2
3
4
5
...