The workshop on COGNITIVE VISION is oganised as part of ACS 2019, the Seventh Annual Conference on Advances in Cognitive Systems (ACS 2019, http://www.cogsys.org/conference/2019) to be held at the Massachusetts Institute of Technology (Cambridge, Massachusetts). The workshop will be held as a full-day event on Friday August 2 2019.


Mehul Bhatt
Örebro University, Sweden

Daniel Levin
Vanderbilt University, United States

Parisa Kordjamshidi
Tulane University, United States

Örebro University, Sweden

Vanderbilt Universit, United States

Tulane University, United States

Call for Papers

The workshop on COGNITIVE VISION solicits contributions addressing computational vision and perception at the interface of language, logic, cognition, and artificial intelligence. The workshop brings together a novel & unique combination of academics and research methodologies encompassing AI, Cognition, Psychology, Perception, Interaction, and Visuospatial Cognition.

The workshop will feature invited and contributed research advancing the practice of Cognitive Vision particularly from the viewpoints of theories and methods developed within the fields of:

  • Artificial Intelligence
  • Computer Vision
  • Spatial Cognition and Computation
  • Cognitive Linguistics
  • Cognitive Science and Psychology
  • Visual Attention, Perception. and Awareness
  • Neuroscience

Application domains being addressed include, but are not limited to:

  • autonomous driving
  • cognitive robotics - social robotics
  • vision for psychology, human behaviour studies
  • visuo-auditory perception in multimodality studies
  • vision for social science, humanities
  • social signal processing, social media
  • visual art, fashion, cultural heritage
  • vision in biology (e.g., animal, plant)
  • vision and VR / AR
  • vision for UAVs
  • remote sensing, GIS
  • medical imaging

Technical Focus. The principal emphasis of the workshop is on the integration of vision and artificial intelligence from the viewpoints of embodied perception, interaction, and autonomous control. In addition to basic research questions, the workshop addresses diverse application areas where, for instance, the processing and semantic interpretation of (potentially large volumes of) highly dynamic visuo-spatial imagery is central: autonomous systems, cognitive robotics, medical & biological computing, social media, cultural heritage & art, social media, psychology and behavioural research domains where data-centred analytical methods are gaining momentum. One particular challenge in these domains is to balance large-scale statistical analyses with much more selective rule-governed analysis of sparse data. These analyses may be guided by, for instance, recent research exploring the role of knowledge in constraining dynamic changes in awareness during the perception of meaningful events. Particular themes of high interest solicited by the workshop include:

  • methodological integrations between Vision and AI
  • declarative representation and reasoning about spatio-temporal dynamics
  • deep semantics and explainable visual computing (e.g., about space and motion)
  • vision and computational models of narrative
  • cognitive vision and multimodality (e.g., multimodal semantic interpretation)
  • visual perception (e.g., high-level event perception, eye-tracking, biological motion)
  • applications of visual sensemanking for social science, humanities, and human behaviour studies

The workshop emphasises application areas where explainability and semantic interpretation of dynamic visuo-spatial imagery are central, e.g., for commonsense scene understanding; vision for robotics and HRI; narrative interpretation from the viewpoints of visuo-auditory perception & digital media, sensemaking from (possibly multimodal) human-behaviour data where the principal component is visual imagery.

We welcome contributions addressing the workshop themes from formal, cognitive, computational, engineering, empirical, psychological, and philosophical perspectives. Select indicative topics include:

  • deep visuo-spatial semantics
  • commonsense scene understanding
  • semantic question-answering with image, video, point-clouds
  • explainable visual interpretation
  • concept learning and inference from visual stimuli
  • learning relational knowledge from dynamic visuo-spatial stimuli
  • knowledge-based vision systems
  • ontological modelling for scene semantics
  • visual analysis of sketches
  • motion representation (e.g., for embodied control)
  • action, anticipation, joint attention, and visual stimuli
  • vision, AI, and eye-tracking
  • neuro-symbolic integration (for cognitive vision)

  • high-level visual perception and eye-tracking
  • high-level event perception
  • egocentric vision and perception
  • declarative reasoning about space and motion
  • computational models of narratives
  • narrative models for storytelling (from stimuli)
  • vision and linguistic summarization
    (e.g., of social interaction, human behavior)
  • visual perception and embodiment research
    (e.g., involving eye-tracking)
  • biological and artificial vision
  • biological motion
  • visuo-auditory perception
  • multimodal media annotation tools

Submission Requirements. Submitted papers must be formatted according to ACS 2019 guidelines (details here: ACS 2019 guidelines). Contributions may be submitted as:

  1. technical papers (max 12 pages)
  2. position / vision statements (max 7 pages)
  3. work in progress reports or ``new'' project / initiative positioning (max 7 pages)
  4. poster abstract (e.g., for early stage PhD candidates) (max 4 pages)
  5. system demonstrations (max 4 pages)

The above page lengths DO NOT include references: contribution categories (1-3) should contain a maximum of two pages of references, whereas contribution categories (4-5) may add one page of reference to their respective page limits. Each contibution (type) will be allocated an adequate duration of presentation to be determined by the workshop committees. Poster contributions are additionally expected to bring their poster for presentation and discussion during a poster session.

Submissions should include a label describing the category of submission (as per 1-5 above) as a footnote on the first page of the paper.

All submissions should only be made (in English) electronically as PDF documents via the paper submission site at: (CogVis 2019 - Easychair).

Workshop | Talks


    Ray and Maria Stata Center, Massachusetts Institute of Technology
    Cambridge, Massachusetts, USA
    MIT Building 32 / Located at 32 Vassar Street
    Room: 32D-463 / 09:00 AM Onwards



  • How Language and Perception Give Rise to Flexible Intelligence
    Andrei Barbu
    Massachusetts Institute of Technology, US

    (Not in order of presentation / schedule will be announced to participants by email).

  • Balancing Flexiblity and Integrity: Lessons from Research in Visual Awareness, Learning and the Arts for the Process of Intelligent Seeing
    Daniel Levin
    Vanderbilt University, US
  • Visual Question Answering Through Strategic Perception
    Andrew Lovett, Gordon Briggs, Brian McClimens, Will Bridewell, Paul Bello
    U. S. Naval Research Laboratory, US
  • Non-monotonic Logical Reasoning Guiding Deep Learning for Scene Understanding on Robots
    Tiago Mota, Mohan Sridharan
    University of Auckland, NZ  /  University of Birmingham, UK
  • Deep Semantics for Commonsense Visuospatial Intelligence: On Integrated Reasoning and Learning about Space and Motion
    Mehul Bhatt, Jakob Suchan, Srikrishna Varadarajan
    Örebro University, SE  /  University of Bremen, DE  /  CoDesign Lab
  • Risk-Aware Design of AI-Based Road Vehicle Autopilots — Is End-to-End Learning a Serious Option?
    Rudolf Mester
    Norwegian University of Science and Technology, NO
  • To AIR is Human, or is it? The Role of High-Level Representations and Conscious Awareness in Biological Motion Perception
    Paul Hemeren
    University of Skövde, SE
  • Newtonian Predictions are Utilised in the Perception of Colliding Objects
    Abdul Deeb, Evan Cesanek, Fulvio Domini
    Brown University, US  /  Columbia University, US
  • U-net Super-Neural Segmentation and Similarity Calculation to Realize Vegetation Change Assessment in Satellite Imagery
    Chunxue Wu, Bobo Ju, Naixue Xiong, Guisong Yang, Yan Wu, Hongming Yang, Jiaying Huang
    University of Shanghai for Science and Technology, CN  /  Indiana University Bloomington, US  /  Tianjin University, CN
  • One-Object Decision-Making model: Fast and Frugal Heuristic for Human Activity Classification
    Karan Sharma, Suchendra Bhandarkar
    Keysight Technologies, US  /  University of Georgia, US
  • Multimodality for Intention in Human-Robot Interactions (cancelled)
    Melanie Jouaiti, Patrick Hénaff, Mehul Bhatt, Jakob Suchan
    Laboratoire LORIA, FR  /  Örebro University, SE  /  University of Bremen, DE
  • Multimodal Continuation-Style Architectures for Human-Robot Interaction
    Nikhil Krishnaswamy, James Pustejovsky
    Brandeis University, US
  • XMRs: Uniform Semantic Representations for Intermodular Communication in Cognitive Robots
    Jesse English, Sergei Nirenberg
    Rensselaer Polytechnic InsWtute, US

Important Dates in 2019

  • We encourage expression of interest and / or registering an abstract and title: (anytime before full submission deadline)
  • Submissions: June 14 (June 3)
  • Notification: June 30
  • Camera Ready: July 8
  • Workshop Date: August 2
  • ACS 2019 Conference: August 2 - 5 2019



CoDesign Lab  >  Cognitive Vision
www.codesign-lab.org  |  www.cognitive-vision.org

Contact:   Please direct all inquiries to Mehul Bhatt via email at  >  [ mehul.bhatt AT oru.se ]



  • Somak Aditya (Adobe Research - BEL, India)
  • Amir Aly (Ritsumeikan University, Japan)
  • Bonny Banerjee (University of Memphis, United States)
  • Chitta Baral (Arizona State University, United States)
  • Andrei Barbu (Massachusetts Institute of Technology, United States)
  • Melissa Beck (Louisiana State University, United States)
  • Ralph Ewerth (Leibniz Universität, Germany)
  • Zoe Falomir (University of Bremen, Germany)
  • Roberta Ferrario (Italian National Research Council - CNR, Italy)
  • Hiranmay Ghosh (Tata Consultancy Services, India)
  • Shyamanta M. Hazarika (Indian Institute of Technology Guwahati, India)
  • Paul Hemeren (University of Skövde, Sweden)
  • Maithilee Kunda (Vanderbilt University, United States)
  • Francesca Lisi (Università degli Studi di Bari "Aldo Moro", Italy)
  • Antonio Lieto (University of Turin, Italy)
  • Yanxi Liu (Penn State University, United States)
  • Rudolf Mester (Norwegian University of Science and Technology, Norway)
  • Frank Pollick (University of Glasgow, United Kingdom)
  • Paulo E. Santos (Centro Universitário da FEI, Brazil)
  • Michael Spranger (Sony CSL, Japan)
  • Mohan Sridharan (University of Birmingham, United Kingdom)
  • Jakob Suchan (University of Bremen, Germany)
  • David Vernon (Carnegie Mellon University Africa, Rwanda)


The workshop on COGNITIVE VISION is oganised as part of ACS 2019, the Seventh Annual Conference on Advances in Cognitive Systems (ACS 2019, http://www.cogsys.org/conference/2019). ACS 2019 is chaired by Michael T. Cox (Wright State Universiy, US).