Publications and Preprints
Papers are in reverse chronological order. '*' denotes equal contribution.
|
|
Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of
Approaches and Challenges
Sanjay Haresh,
Xiaohao Sun,
Hanxiao Jiang,
Angel Chang,
Manolis Savva
3DV, 2022
project page
/
arXiv
We canonicalize the task of reconstruction 3D human object from videos and benchmark 5 families of methods on the task.
|
|
Timestamp-Supervised Action Segmentation with Graph Convolutional Networks
Hamza Khan
Sanjay Haresh,
Awais Ahmed,
Shakeeb Siddiqui,
Andrey Konin ,
M. Zeeshan Zia,
Quoc-Huy Tran
IROS, 2022
project page
/
arXiv
We leverage graph convolutional networks to propagate timestamp labels to the whole video resulting in a 97% reduction of required labels.
|
|
Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering
Sanjay Haresh*,
Sateesh Kumar*,
Awais Ahmed,
Andrey Konin ,
M. Zeeshan Zia,
Quoc-Huy Tran
CVPR, 2022
project page
/
arXiv
We proposed temporal optimal transport for jointly learning representations and performing online clustering in an unsupervised manner.
|
|
Learning by Aligning Video in Time
Sanjay Haresh*,
Sateesh Kumar*,
Huseyin Coskun,
Shahram N. Syed,
Andrey Konin ,
M. Zeeshan Zia,
Quoc-Huy Tran
CVPR, 2021
project page
/
arXiv
Good frame representations can be learned by learning global alignment across pairs of videos via differentiable dynamic time warping.
|
|
Towards Anomaly Detection in Dashcam Videos
Sanjay Haresh*,
Sateesh Kumar*,
M. Zeeshan Zia
Quoc-Huy Tran
IV, 2020
talk
/
arXiv
We curated a large dataset of dashcam videos for road anomalies understanding. We proposed an object-object interaction
reasoning approach for detecting anomalies without additional supervision.
|
|