About

Dr. Aniket Bera is an Assistant Research Professor at the University of Maryland Institute for Advanced Computer Studies (UMIACS) with appointments/affiliations with the Department of Computer Science, Maryland Robotics Center (James Clark School of Engineering), Brain and Behavior Initiative (BBI), and Maryland Transportation Institute (MTI). Prior to this, he was a Research Assistant Professor at University of North Carolina at Chapel Hill. He received his Ph.D. in 2017 from the University of North Carolina at Chapel Hill.

His core research interests are in Social Robotics, Behavior AI, Multi-agent Modeling, Affective Computing, Computer Graphics (Physically-based Modelling and Simulation, AR/VR), Motion Planning, Autonomous Vehicles, Behavior-based AI, Social Robotics (HRI), Data-Driven Crowd Simulations, Cognitive modeling: Knowledge, reasoning, and planning for intelligent characters. He is a faculty with the GAMMA group.

His current research focuses on the social perception of intelligent agents and robotics. He also works with the University of Maryland at Baltimore Medical School to build algorithms and systems to help therapists and doctors detect mental health and social anxiety issues. His research involves novel combinations of methods and collaborations in machine learning, computational psychology, computer graphics, and physically-based simulation to develop real-time computational models to learn human behaviors. Dr. Bera has previously worked in many research labs, including Disney Research, Intel, and Centre for Development of Advanced Computing (Govt. of India).

Dr. Bera's research has been featured on CBS, WIRED, Forbes, FastCompany, Times of India etc.

Note: This WWW isn't updated regularly. For full list of publications, grants and workshops please refer to CV or Google Scholar

PROSPECTIVE STUDENTS:

  1. If you're looking for graduate admissions, please apply to UMD CS (https://www.cs.umd.edu/grad/catalog) and mention my name and research interests. Please note that all admission decisions are taken by the committee.
  2. If you're already a student at UMD, the best way to increase the chances of a response to an e-mail is to read one of my recent papers and include a concise paragraph with the benefits and drawbacks of the main idea as well as possible improvements you'd be interested to try and send me an email with your CV and background.

Updates/News

  • 10/13/2020
    IROS 2020: Associate Editor and Session Chair: Navigation and Collision Avoidance
  • 9/5/2020
    "Sci-Fi Social Distancing?" Maryland Today covers our on-going COVID-19 Robot research
  • 9/1/2020
    "UMIACS Faculty Receive MPower Funding to Improve Mental Telehealth Services Using AI" MPower Grant Coverage by UMD UMIACS
  • 6/6/2020
    Multiple papers accepted in ECCV 2020, ACM Multimedia 2020 and ISMAR 2020
  • 9/1/2020
    "Aniket Bera and Dinesh Manocha Receive the 2020 Brain and Behavior Initiative Seed Grant" BBI Grant Coverage by UMD CS
  • 8/4/2020
    Grant Awarded by "University of Maryland MPower Grant" COVID-19 Initiative (Principal Investigator)
  • 6/24/2020
    Grant Awarded by "UMD Brain and Behavior Initiative" (Principal Investigator)
  • 6/20/2020
    GAMMA Research Group is Developing Novel COVID-19 Prevention Robots
  • 6/10/2020
    Grant Awarded by NSF EAGER (Co-Principal Investigator)
  • 6/6/2020
    One paper accepted in IEEE Robotics and Automation Letters (RA-L)
  • 6/6/2020
    Multiple Indian media covered recent experiment on 'Pather Panchali'
  • 5/18/2020
    WIRED covered recent work on Social Robotics
  • 3/29/2020
    Forbes covered ProxEmo and recent work on Social Robotics
  • 2/25/2020
    Chair IEEE VR 2020 Session: Crowds & Perception
  • 2/25/2020
    One paper accepted at CVPR 2020
  • 2/25/2020
    One paper accepted at IEEE International Conference on Automatic Face and Gesture Recognition 2020
  • 2/15/2020
    Chaired three sessions at AAAI Conference on Artificial Intelligence 2020
  • 1/17/2020
    Two papers accepted at ICRA 2020
  • 9/17/2019
    Two papers accepted at AAAI Conference on Artificial Intelligence 2020
  • 9/20/2019
    ACM SAP Best Poster Award 2019
    Identifying Emotions from Walking using Affective and Deep Features. (Tanmay Randhavane, Uttaran Bhattacharya, Aniket Bera, Kyra Kapsaskis, Kurt Gray & Dinesh Manocha)
  • 9/17/2019
    Co-chair IROS 2019 Session: Human Detection and Tracking
  • 9/17/2019
    Presented 1 paper and 2 workshop talks at SAP 2019
  • 9/1/2019
    Started position at the University of Maryland College Park
  • 6/14/2019
    Presented 1 paper and 4 workshop talks at CVPR 2019
  • 5/31/2019
    Presented 1 paper and 3 workshop papers and talks at ICRA 2019
  • GAMMA
    GAMMA has published 5 papers in AI and Vision Conferences in 2019 (AAAI, CVPR, ICCV, NIPS)
  • GAMMA
    GAMMA has published 5 papers in IEEE VR in 2019 (AAAI, CVPR, ICCV, NIPS)
  • GAMMA
    GAMMA has published 15 papers in Robotics Conferences in 2019 (IROS, ICRA)
  • GAMMA
    GAMMA has published 4 papers in ACM SIGGRAPH 2018















Media Coverage

Latest Publications

  • Generating Emotive Gaits for Virtual Agents Using Affect-Based Autoregression
    ISMAR 2020     Conference Papers
    Uttaran Bhattacharya, Nicholas Rewkowski, Pooja Guhan, Niall L. Williams, Trisha Mittal, Aniket Bera, Dinesh Manocha

  • Emotions Don't Lie: A Deepfake Detection Method using Audio-Visual Affective Cues
    ACM MM 2020     Conference Papers
    Trisha Mittal, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera, Dinesh Manocha

  • Take an emotion walk: Perceiving emotions from gaits using hierarchical attention pooling and affective mapping
    ECCV 2020     Conference Papers
    Uttaran Bhattacharya, Christian Roncal, Trisha Mittal, Rohan Chandra, Aniket Bera, Dinesh Manocha

  • EmotiCon: Context-Aware Multimodal Emotion Recognition Using Frege's Principle
    IEEE CVPR 2020     Conference Papers
    Trisha Mittal, Pooja Guhan, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera, Dinesh Manocha

  • ProxEmo: Gait-based Emotion Learning and Multi-view Proxemic Fusion for Socially-Aware Robot Navigation
    IEEE IROS 2020     Conference Papers
    Venkatraman Narayanan, Bala Murali Manoghar, Vishnu Sashank Dorbala, Dinesh Manocha, Aniket Bera

  • CMetric: A Driving Behavior Measure Using Centrality Functions
    IEEE IROS 2020     Conference Papers
    Rohan Chandra, Uttaran Bhattacharya, Trisha Mittal, Aniket Bera, Dinesh Manocha

  • Forecasting trajectory and behavior of road-agents using spectral clustering in graph-lstms
    RAL/IEEE IROS 2020     Journal Papers Conference Papers
    Rohan Chandra, Tianrui Guan, Srujan Panuganti, Trisha Mittal, Uttaran Bhattacharya, Aniket Bera, Dinesh Manocha

  • GraphRQI: Classifying Driver Behaviors Using Graph Spectrums
    IEEE ICRA 2020     Conference Papers
    Rohan Chandra, Uttaran Bhattacharya, Xiaoyu Li, Trisha Mittal, Aniket Bera, Dinesh Manocha

  • How are You Feeling? Multimodal Emotion Learning for Socially-Assistive Robot Navigation
    IEEE FG 2020     Conference Papers
    Aniket Bera, Tanmay Randhavane, Rohan Prinja, Kyra Kapsaskis, Austin Wang, Kurt Gray, Dinesh Manocha

  • M3ER: Multiplicative Multimodal Emotion Recognition using Facial, Textual, and Speech Cues
    AAAI 2020     Conference Papers
    Trisha Mittal, Uttaran Bhattacharya, Rohan Chandra, Aniket Bera, Dinesh Manocha

  • STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits
    AAAI 2020     Conference Papers
    Uttaran Bhattacharya, Trisha Mittal, Rohan Chandra, Tanmay Randhavane, Aniket Bera, Dinesh Manocha

  • Modeling data-driven dominance traits for virtual characters using gait analysis
    IEEE TVCG 2019     Journal Papers
    Tanmay V Randhavane, Aniket Bera, Emily Kubin, Kurt Gray, Dinesh Manocha

  • RobustTP: End-to-end trajectory prediction for heterogeneous road-agents in dense traffic with noisy sensor inputs
    ACM Computer Science in Cars Symposium     Symposium Papers
    Rohan Chandra, Uttaran Bhattacharya, Christian Roncal, Aniket Bera, Dinesh Manocha

  • Learning perceived emotion using affective and deep features for mental health applications
    IEEE ISMAR 2019     Conference Papers
    Tanmay Randhavane, Uttaran Bhattacharya, Kyra Kapsaskis, Kurt Gray, Aniket Bera, Dinesh Manocha

  • EVA: Modeling Perceived Emotions of Virtual Agents using Expressive Features of Gait and Gaze
    ACM SAP 2019     Conference Papers Best Poster Award
    Tanmay Randhavane, Aniket Bera, Kyra Kapsaskis, Kurt Gray, Dinesh Manocha

  • DensePeds: Pedestrian Tracking in Dense Crowds Using FRVO and Sparse Features
    IROS 2019     Conference Papers
    Rohan Chandra, Uttaran Bhattacharya, Aniket Bera, Dinesh Manocha

  • FVA: Modeling Perceived Friendliness of Virtual Agents Using Movement Characteristics
    TVCG / ISMAR 2019     Journal Papers Conference Papers
    Tanmay Randhavane, Aniket Bera, Kyra Kapsaskis, Kurt Gray, Dinesh Manocha

  • TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions
    CVPR 2019     Conference Papers
    Rohan Chandra, Uttaran Bhattacharya, Aniket Bera, Dinesh Manocha

  • LCrowdV: Generating labeled videos for pedestrian detectors training and crowd be-havior learning
    Neurocomputing 2019     Journal Papers
    Ernest Cheung, Tsan Kwong Wong,Aniket Bera, Dinesh Manocha

  • Pedestrian Dominance Modeling for Socially-Aware Robot Navigation
    ICRA 2019     Conference Papers
    Tanmay Randhavane,Aniket Bera, Emily Kubin, Austin Wang, Kurt Gray, Dinesh Manocha

  • TrackNPred: A Software Framework for End-to-End Trajectory Prediction
    ACM CSCS 2019     Conference Papers
    Rohan Chandra, Uttaran Bhattacharya, Aniket Bera, Dinesh Manocha

Research Interests

Students Supervised/Co-Supervised

Current Students:

  • · Pooja Guhan (University of Maryland at College Park)
    · Niall Williams (University of Maryland at College Park)
    · Rohan Chandra (University of Maryland at College Park)
    · Jiayi Xu (April) (University of North Carolina at Chapel Hill)
    · Uttaran Bhattacharya (University of Maryland at College Park)
    · Trisha Mittal (University of Maryland at College Park)
    · Bala Sai Sudhakar (University of Maryland at College Park)
    · Venkatraman Narayanan (University of Maryland at College Park)
    · Vishnu Sashank Dorbala (University of Maryland at College Park)
    · Abhishek Banerjee (University of Maryland at College Park)
    · Rama Prashanth Ramasamy Vijayakumar (University of Maryland at College Park)
    · Arjun Ambalam (University of Maryland at College Park)
    · Arpit Maclay (University of Maryland at College Park)
    · Videsh Suman (University of Massachusetts Amherst)
    · Pooja Kabra (University of Maryland at College Park)
    · Ritwika Das (University of Maryland at College Park)
    · Anshuman Singh (University of Maryland at College Park)
    · Rahul Madhogarhia (National Institute of Technology Karnataka, India)
    · Mehul Arora (Indian Institute of Information Technology Allahabad, India)

Past Students:

  • · Tanmay Randhavane (University Of North Carolina at Chapel Hill, now at Microsoft)
    · Ernest Cheung (University Of North Carolina at Chapel Hill, now at Samsung)
    · Vasavi Gajarla (University Of North Carolina at Chapel Hill, now at Facebook)
    · Janakiraman Kirthivasan (University of Maryland at College Park)
    · Jack Sturtevant (University of Maryland at College Park)
    · Rohan Chabra (University Of North Carolina at Chapel Hill, now at Facebook Reality Labs)
    · Rohan Prinja (University Of North Carolina at Chapel Hill, now at Google)
    · Austin Wang (University Of North Carolina at Chapel Hill)
    · Anson Wong (The Chinese University of Hong Kong)
    · Husam Shaik (University Of North Carolina at Chapel Hill)
    · Changhao Liu (University Of North Carolina at Chapel Hill)
    · Josh Taekman (University Of North Carolina at Chapel Hill)

Public Datasets

  • Simulated pedestrian dataset with varying crowd density, population, lighting conditions, background scene, camera angles, agent personality and noise level to help in training models for crowd understanding, including pedestrian detection, crowd classification, etc.
    Link: http://gamma.cs.unc.edu/LCrowdV/#dataset
  • A public domain dataset, EWalk, with videos of walking individuals. We also provide their gaits in the form of 3D positions of 16 joints and labeled emotions obtained using a perception study
    Link: http://gamma.cs.unc.edu/GAIT/##EWalk
  • High resolution crowd dataset captured in dense pedestrian crossings in India. Dataset consists of videos of indoor and outdoor scenes recorded at different locations, each with 30-80 pedestrians.
    Link: http://gamma.cs.unc.edu/RCrowdT/
  • A traffic dataset (TRAF) comprising of dense and heterogeneous traffic. The dataset consists of the following road-agents: cars, buses, trucks, rickshaws, pedestrians, scooters, motorcycles, carts, and animals and is collected in dense Asian cities.
    Link: https://go.umd.edu/TRAF-Dataset
  • A dense crowd dataset (DensePeds) captured in dense crowd and multi-agent environments. The dataset contains detailed labels and trajectories for dense crowd scenes.
    Link: https://www.gamma.umd.edu/researchdirections/autonomousdriving/densepeds/

Funding agencies and collaborators



  






"I think everyone should learn how to program a computer, because it teaches you how to think. I view computer science as a liberal art, something everyone should learn to do." - Steve Jobs

Artwork by Ashley Trinh, Inspiration by Paul Kube