Nakul Agarwal

I am a Machine Learning Research Engineer at Honda Research Institute, USA working on challening problems related to computer vision and machine learning with application to Advanced Driver Assistance Systems (ADAS), autonomous navigation and robotics.

I graduated with a M.S. degree in EECS from UC Merced where I was working in the Vision and Learning Lab under the supervision of Prof. Ming-Hsuan Yang. Prior to joining UC Merced as a graduate student, I worked with Prof. C. V. Jawahar and Prof. Vineeth N. Balasubramaniam at Centre for Visual Information Technology in IIIT Hyderabad, India. I received my B.E. (Bachelor of Engineering) degree from Netaji Subhas Institute of Technology, University of Delhi in 2016.

Email / CV / Google Scholar

News

10 / 2022: Our paper on "Risk Perception in Driving Scenes" has been accepted at NeurIPS 2022 Workshop on Machine Learning for Autonomous Driving!.
03 / 2022: Our paper on "Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos" has been accepted at CVPR 2022!.
12 / 2021: I will be serving as a reviewer for CVPR 2022.
07 / 2020: One paper on Unsupervised Domain Adaptation accepted in BMVC'20!
03 / 2020: One paper accepted in CVPR'20 workshop!
08 / 2018: Our paper on "Connecting Visual Experiences using Max-flow Network with Application to Visual Localization" is out on arXiv!
06 / 2018: Our paper on "Improving Multiclass Classification by Deep Networks using DAGSVM and Triplet Loss" has been accepted at Pattern Recognition Letters 2018!
05 / 2018: Started my internship at Honda Research Institute, Mountain View
08 / 2017: Started my M.S. at UC Merced

Research

	Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner Chunhui Zhang, Sean Dae Houlihan, Kwonjoon Lee, Nakul Agarwal, Zhongyu Ouyang, Soroush Vosoughi, Shao-Yuan Lo ICML, 2025 (Spotlight - Selection rate 2.6%) project paper
	Pose-Aware Weakly-Supervised Action Segmentation Zhihao Zhao, Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Behzad Dariush Multimodal Learning and Applications CVPR, 2025 project paper
	ACE: Action Concept Enhancement of Video-Language Models in Procedural Videos Reza Ghoddoosian, Nakul Agarwal, Isht Dwivedi, Behzad Dariush WACV, 2025 project paper
	Vamos: Versatile Action Models for Video Understanding Shijie Wang, Qi Zhao, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, Chen Sun ECCV, 2024 project paper code
	M2D2M: Multi-Motion Generation from Text with Discrete Diffusion Models Seunggeun Chi, Hyung-gun Chi, Hengbo Ma, Nakul Agarwal, Faizan Siddiqui, Karthik Ramani, Kwonjoon Lee ECCV, 2024 project paper
	Uncertainty-aware Action Decoupling Transformer for Action Anticipation Hongji Guo, Nakul Agarwal, Shao-Yuan Lo, Kwonjoon Lee, Qiang Ji CVPR, 2024 (Highlight - Selection rate 2.8%) project paper
	Can’t make an Omelette without Breaking some Eggs: Plausible Action Anticipation using Large Video-Language Models Himangi Mittal, Nakul Agarwal, Shao-Yuan Lo, Kwonjoon Lee CVPR, 2024 project paper
	AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos? Qi Zhao, Ce Zhang, Shijie Wang, Changcheng Fu, Minh Quan Do, Nakul Agarwal, Kwonjoon Lee, Chen Sun (* equal contribution) ICLR, 2024 project paper code
	Disentangled Neural Relational Inference for Interpretable Motion Prediction Victoria Magdalena Dax, Jiachen Li, Enna Sachdeva, Nakul Agarwal, Mykel Kochenderfer RA-L and ICRA, 2024 project paper
	Rank2Tell: A Multimodal Driving Dataset for Joint Importance Ranking and Reasoning Enna Sachdeva, Nakul Agarwal, Suhas Chundi, Jiachen Li, Mykel Kochenderfer, Chiho Choi, Behzad Dariush, (* equal contribution) WACV, 2024 project paper
	Object-centric Video Representation for Long-term Action Anticipation Ce Zhang, Changcheng Fu, Shijie Wang, Nakul Agarwal, Kwonjoon Lee, Chiho Choi, Chen Sun (* equal contribution) WACV, 2024 project paper
	Ordered Atomic Activity for Fine-Grained Interactive Traffic Scenario Understanding Nakul Agarwal, Yi-Ting Chen ICCV, 2023 project paper
	Weakly-Supervised Action Segmentation and Unseen Error Detection in Anomalous Instructional Videos Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Behzad Dariush ICCV, 2023 project paper
	Latency Matters: Real-Time Action Forecasting Transformer Harshayu Girase, Nakul Agarwal, Chiho Choi, Karttikeya Mangalam CVPR, 2023 (Highlight - Selection rate 2.6%) project paper
	AdamsFormer for Spatial Action Localization in the Future Hyung-gun Chi, Kwonjoon Lee, Nakul Agarwal, Yi Xu, Karthik Ramani, Chiho Choi CVPR, 2023 project paper
	Risk Perception in Driving Scenes Nakul Agarwal, Yi-Ting Chen Machine Learning for Autonomous Driving NeurIPS, 2022 project paper
	Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos Reza Ghoddoosian, Isht Dwivedi, Nakul Agarwal, Chiho Choi, Behzad Dariush CVPR, 2022 project paper code
	Unsupervised Domain Adaptation for Spatio-Temporal Action Localization Nakul Agarwal, Yi-Ting Chen, Behzad Dariush, Ming-Hsuan Yang BMVC, 2020 project paper Short Version: VL3 Workshop, CVPR, 2020
	SegRPN: Scale Aware Joint Object Detection and Semantic Segmentation Nakul Agarwal, Wei-Chih Hung, Yi-Hsuan Tsai, Ming-Hsuan Yang Manuscript, 2019 paper
	Improving Multiclass Classification by Deep Networks using DAGSVM and Triplet Loss Nakul Agarwal, Vineeth N. Balasubramaniam, C. V. Jawahar Pattern Recognition Letters, 2018 paper bibtex
	Connecting Visual Experiences using Max-flow Network with Application to Visual Localization Nakul Agarwal, A.H. Abdul Hafez, C. V. Jawahar (* equal contribution) arXiv, 2018 paper bibtex