Best Paper

Transformer-based Long-Term Viewport Prediction in 360° Video: Scanpath is All You Need
Chao, Fang-Yi (1); Ozicnar, Cagri (2); Smolic, Aljosa (1)
1: Trinity College Dublin, Ireland; 2: Samsung Research UK

Best Paper Runner-up

Reliability of Crowdsourcing for Subjective Quality Evaluation of Tone Mapping Operators
Goswami, Abhishek (1,3); Ak, Ali (2); Hauser, Wolf (1); Le Callet, Patrick (2); Dufaux, Frederic (3)
1: DxO Labs, France; 2: Image Perception Interaction Team, LS2N, University of Nantes, France; 3: Universite Paris-Saclay, CNRS, CentraleSupelec, Laboratoire des Signaux et Systemes, France

Best Student Paper

Visually Supervised Speaker Detection and Localization via Microphone Array
Berghi, Davide; Hilton, Adrian; Jackson, Philip J.B.
CVSSP, University of Surrey, United Kingdom

List of nominated papers:

Split Rendering of the Transparent Channel for Cloud AR
Kato, Haruhisa; Kobayashi, Tatsuya; Sugano, Masaru; Naito, Sei
KDDI Research Inc., Japan

Large-vocabulary Audio-visual Speech Recognition in Noisy Environments
Yu, Wentao; Zeiler, Steffen; Kolossa, Dorothea
Ruhr University Bochum, Germany

Transformer-based Long-Term Viewport Prediction in 360° Video: Scanpath is All You Need
Chao, Fang-Yi (1); Ozicnar, Cagri (2); Smolic, Aljosa (1)
1: Trinity College Dublin, Ireland; 2: Samsung Research UK
(BEST PAPER)

DeFake: Decentralized ENF-Consensus Based DeepFake Detection in Video Conferencing
Nagothu, Deeraj (1); Xu, Ronghua (1); Chen, Yu (1); Blasch, Erik (2); Aved, Alexander (2)
1: Binghamton University, United States of America; 2: U.S. Air Force Research Laboratory, United States of America

Time Difference of Arrival Estimation of Multiple Simultaneous Speakers Using Deep Clustering Neural Networks
Parviainen, Mikko; Pertilä, Pasi
Tampere University, Finland

Optimal Frame Duration for Oracle Audio Signal Separation is Determined by Joint Minimization of Two Antagonistic Artifacts
Voran, Stephen
Institute for Telecommunication Sciences, United States of America

Reliability of Crowdsourcing for Subjective Quality Evaluation of Tone Mapping Operators
Goswami, Abhishek (1,3); Ak, Ali (2); Hauser, Wolf (1); Le Callet, Patrick (2); Dufaux, Frederic (3)
1: DxO Labs, France; 2: Image Perception Interaction Team, LS2N, University of Nantes, France; 3: Universite Paris-Saclay, CNRS, CentraleSupelec, Laboratoire des Signaux et Systemes, France
(BEST PAPER RUNNER UP)

AVrate Voyager: An Open Source Online Testing Platform
Göring, Steve; Ramachandra Rao, Rakesh Rao; Fremerey, Stephan; Raake, Alexander
Audio Visual Technology Group; Technische Universität Ilmenau, Germany

A Calibration Method for Subaperture Views of Plenoptic 2.0 Camera Arrays
Fachada, Sarah (1); Losfeld, Armand (1); Senoh, Takanori (2); Lafruit, Gauthier (1); Teratani, Mehrdad (1)
1: Université Libre de Bruxelles, Belgium; 2: Tokyo Denki University, Tokyo, Japan

Estimating Image Quality for Person Re-Identification
Chen, Haoyu; Delp, Edward J.; Reibman, Amy R.
Purdue University

Neural Network Modeling of Probabilities for Coding the Octree Representation of Point Clouds
Kaya, Emre Can; Tabus, Ioan
Tampere University, Finland

A Point-to-Distribution Joint Geometry and Color Metric for Point Cloud Quality Assessment
Javaheri, Alireza (1,2); Brites, Catarina (1,2); Pereira, Fernando (1,2); Ascenso, João (1,2)
1: Instituto de Telecomunicações, Lisbon, Portugal; 2: Instituto Superior Técnico, Lisbon, Portugal

Improving Generalization of Deepfake Detection by Training for Attribution
Jain, Anubhav; Korshunov, Pavel; Marcel, Sebastien
Idiap Research Institute, Switzerland

Visually Supervised Speaker Detection and Localization via Microphone Array
Berghi, Davide; Hilton, Adrian; Jackson, Philip J.B.
CVSSP, University of Surrey, United Kingdom
(BEST STUDENT PAPER)

Best Paper Awards Sponsored by YouTube