Arun Balajee Vasudevan

Research Scientist, Amazon

Contact: arunbalajeev[at]zohomail.com


I was a postdoctoral fellow in Prof. Deva Ramanan's lab at Robotics Institute, CMU. Before that, I completed my PhD in the Computer Vision Lab, ETH Zurich, working under Prof. Luc Van Gool and Dr. Dengxin Dai.
I obtained my Bachelor's in Electrical Engineering from IIT Jodhpur, India in May 2014 and Master's in Computer Science from EPFL, Switzerland in Sept 2016.
[CV][Scholar]

Publications

Clink! Chop! Thud! - Learning Object Sounds from Real-World Interactions
Mengyu Yang, Yiming Chen, Haozheng Pei, Siddhant Agarwal, Arun Balajee Vasudevan, James Hays
ICCV 2025.


Planning with Adaptive World Models for Autonomous Driving
Arun Balajee Vasudevan, Neehar Peri, Jeff Schneidar, Deva Ramanan
ICRA 2025.
[pdf][Project]


LCA-on-the-Line: Benchmarking Out-of-Distribution Generalization with Class Taxonomies
Jia Shi, Gautam Gare, Jinjin Tian, Siqi Chai, Zhiqiu Lin, Arun Balajee Vasudevan, Di Feng, Francesco Ferroni, Shu Kong
ICML 2024 [ORAL].
[pdf][Project][Code]


The Un-Kidnappable Robot: Acoustic Localization of Sneaking People
Mengyu Yang, Patrick Grady, Samarth Brahmbhatt, Arun Balajee Vasudevan, Charles C Kemp, James Hays
ICRA 2024.
[pdf][Project]


Sound and Visual Representation Learning with Multiple Pretraining Tasks
Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
CVPR 2022.
[pdf]


Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds
Dengxin Dai, Arun Balajee Vasudevan, Jiri Matas, Luc Van Gool
TPAMI 2021.
[pdf][Project][Code]][Data]


Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds
Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
ECCV 2020 [SPOTLIGHT].
[pdf][Website][Code]][Data]


Talk2Nav: Vision-and-Language Navigation in Cities
Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
IJCV 2020.
[pdf][arxiv][Website] [Video][Data]


Object Referring in Videos with Language and Human Gaze
Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
CVPR 2018.
[pdf][data][code][Website] [Video][Supplementary]


Object Referring in Visual Scene with Spoken Language
Arun Balajee Vasudevan, Dengxin Dai, Luc Van Gool
WACV 2018.
[pdf]


Query-adaptive Video Summarization via Quality-aware Relevance Estimation
Arun Balajee Vasudevan, Michael Gygli, Anna Volokitin, Luc Van Gool
ACM Multimedia 2017.
[pdf][code]


Search-free Approach to the Extraction of Multiple Salient objects from an Image
Srikanth Muralidharan, Arun Balajee Vasudevan, Shiva Pratheek Chintapalli, Shanmuganathan Raman
IEEE SPICES 2015.
[pdf]


Motion Categorization of a Dynamic Scene
Arun Balajee Vasudevan, Srikanth Muralidharan, Shiva Pratheek Chintapalli, Shanmuganathan Raman
VISAPP 2014.
[pdf]


Dynamic Scene Classification using Spatial and Temporal Cues
Arun Balajee Vasudevan, Srikanth Muralidharan, Shiva Pratheek Chintapalli, Shanmuganathan Raman
ICCV workshops 2013.
[pdf]



Master Thesis

Deep Visual Semantic Embedding for Video Thumbnail Selection . [pdf][slides]
Arun Balajee Vasudevan, Michael Gygli, Anna Volokitin, Luc Van Gool, Achanta Radhakrishna, Sabine Susstrunk

Bachelor Thesis

Design and Implementation of Global Navigation Satellite System(GNSS) receiver . [pdf][slides]
Aswin Suresh, Mahesh Chand Gurjar, Arun Balajee Vasudevan, Arun Kumar Singh