Sanjay Haresh

I am an AI Researcher at Qualcomm AI Research working in Roland Memisevic's team on Large Language Models. Before that, I completed my MSc. (Thesis) at Simon Fraser University (SFU), where I was advised by Prof. Manolis Savva .

Prior to SFU, I worked at Retrocausal for 2 years as a Research Engineer (Computer Vision) under the supervision of Dr. Quoc Huy Tran and Dr. Zeeshan Zia.

In 2019, I completed my undergrad Computer Science from FAST-NUCES Karachi, Pakistan, where I worked on Class Imbalance under the guidance of Prof. Tahir Syed.

Email  /  CV  /  Google Scholar  /  Twitter

profile photo
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.

Website layout is from Jon Barron