Pavlo Molchanov ![](/sites/default/files/person/Pavlo_Molchano_480x480.jpg) Pavlo Molchanov obtained PhD from Tampere University of Technology, Finland in the area of signal processing in 2014. His dissertation was focused on designing automatic target recognition systems for radars. Since 2015 he is with Learning and Perception Research team at NVIDIA, currently holding a senior research scientist position. His research is focused on methods for neural network acceleration, and designing novel human-computer interaction systems and human understanding. On the network acceleration he is interested in neural network pruning methods and conditional inference. For human understanding he is working on landmark estimation, gesture recognition, hand pose estimation. He received EuRAD best paper award in 2011 and EuRAD young engineer award in 2013. Research Area(s) [Algorithms and Numerical Methods](/index.php/research-area/algorithms) [Computer Vision](/index.php/research-area/computer-vision) [Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence) Main Field of Interest [Artificial Intelligence and Machine Learning ](/index.php/research-area/machine-learning-artificial-intelligence) Google Scholar [https://scholar.google.com/citations?user=J9PoyoIAAAAJ&hl=en](https://scholar.google.com/citations?user=J9PoyoIAAAAJ&hl=en) ### Publications ### 2026 [Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding](/publication/2026-05_nemotron-labs-diffusion-tri-mode-language-model-unifying-autoregressive) [Yonggan Fu](/person/yonggan-fu), Lexington Whalen, Abhinav Garg, Chengyue Wu, Maksim Khadkevich, Nicolai Oswald, Enze Xie, Daniel Egert, Sharath Turuvekere Sreenivas,, Shizhe Diao, Chenhan Yu, Ye Yu, Weijia Chen, Sajad Norouzi, Jingyu Liu, Shiyi Lan, Ligeng Zhu, Jin Wang, Jindong Jiang, Morteza Mardani, Mehran Maghoumi, Song Han, Ante Jukić, Nima Tajbakhsh, Jan Kautz, [Pavlo Molchanov](/person/pavlo-molchanov) ### 2025 [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](/index.php/publication/2025-04_longvila-scaling-long-context-visual-language-models-long-videos) [Yukang Chen](/index.php/person/yukang-chen), Fuzhao Xue, Dacheng Li, Qinghao Hu, [Ligeng Zhu](/index.php/person/ligeng-zhu), Xiuyu Li, Yunhao Fang, Haotian Tang, Shang Yang, Zhijian Liu, Ethan He, Hongxu Yin, [Pavlo Molchanov](/index.php/person/pavlo-molchanov), [Jan Kautz](/index.php/person/jan-kautz), Linxi Fan, [Yuke Zhu](/index.php/person/yuke-zhu), Yao Lu (Jason), [Song Han](/index.php/person/song-han) [Hymba: A Hybrid-head Architecture for Small Language Models](/publication/2025-04_hymba-hybrid-head-architecture-small-language-models) Xin Dong, [Yonggan Fu\*](/person/yonggan-fu), Shizhe Diao, [Wonmin Byeon](/person/wonmin-byeon), Zijia Chen, Ameya Sunil Mahabaleshwarkar, Shih-Yang Liu, [Matthijs Van keirsbilck](/person/matthijs-van-keirsbilck), [Min-Hung Chen](/person/min-hung-chen), [Yoshi Nishi](/person/yoshi-nishi), Yingyan Celine Lin, [Jan Kautz](/person/jan-kautz), [Pavlo Molchanov](/person/pavlo-molchanov) [Hymba - ICLR 2025](https://jankautz.com/publications/Hymba_ICLR25.pdf) ICLR spotlight paper [Minitron-SSM: Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning](/index.php/publication/2025-04_minitron-ssm-efficient-hybrid-language-model-compression-through-group-aware) Ali Taghibakhshi, Sharath Turuvekere Sreenivas, [Saurav Muralidharan](/index.php/person/saurav-muralidharan), Marcin Chochowski, Yashaswi Karnati, Raviraj Joshi, Ameya Sunil Mahabaleshwarkar, Zijia Chen, Yoshi Suhara, Oluwatobi Olabiyi, Daniel Korzekwa, Mostofa Patwary, Mohammad Shoeybi, [Jan Kautz](/index.php/person/jan-kautz), Bryan Catanzaro, Ashwath Aithal, Nima Tajbakhsh, [Pavlo Molchanov](/index.php/person/pavlo-molchanov) [NeurIPS 2025](https://arxiv.org/abs/2504.11409) ### 2024 [LLM Pruning and Distillation in Practice: The Minitron Approach](/publication/2024-08_llm-pruning-and-distillation-practice-minitron-approach) Sharath Turuvekere Sreenivas, [Saurav Muralidharan](/person/saurav-muralidharan), Raviraj Joshi, Marcin Chochowski, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, [Jan Kautz](/person/jan-kautz), [Pavlo Molchanov](/person/pavlo-molchanov) [DoRA: Weight-Decomposed Low-Rank Adaptation](/publication/2024-07_dora-weight-decomposed-low-rank-adaptation) Shih-Yang Liu, Chien-Yi Wang, [Hongxu Danny Yin](/person/danny-yin), [Pavlo Molchanov](/person/pavlo-molchanov), [Frank Wang](/person/frank-wang), Kwang-Ting Cheng, [Min-Hung Chen](/person/min-hung-chen) [International Conference on Machine Learning (ICML) 2024](https://icml.cc/Conferences/2024) [FasterViT: Fast Vision Transformers with Hierarchical Attention](/index.php/publication/2024-05_fastervit-fast-vision-transformers-hierarchical-attention) Ali Hatamizadeh , [Greg Heinrich](/index.php/person/greg-heinrich), [Hongxu Danny Yin](/index.php/person/danny-yin), Andrew Tao, Jose M. Alvarez, [Jan Kautz](/index.php/person/jan-kautz), [Pavlo Molchanov](/index.php/person/pavlo-molchanov) [International Conference on Learning Representations (ICLR) 2024](https://iclr.cc/) ### 2023 [Global Context Vision Transformers](/publication/2023-07_global-context-vision-transformers) Ali Hatamizadeh , [Hongxu Danny Yin](/person/danny-yin), [Greg Heinrich](/person/greg-heinrich), [Jan Kautz](/person/jan-kautz), [Pavlo Molchanov](/person/pavlo-molchanov) [ International Conference on Machine Learning (ICML) 2023](https://icml.cc/Conferences/2023) ### 2022 [Structural Pruning via Latency-Saliency Knapsack](/publication/2022-11_structural-pruning-latency-saliency-knapsack) Maying Shen, [Hongxu Danny Yin](/person/danny-yin), [Pavlo Molchanov](/person/pavlo-molchanov), Lei Mao, Jianna Liu, Jose M. Alvarez [NeurIPS 2022](https://nips.cc/Conferences/2022/ScheduleMultitrack?event=52841) [LANA: Latency Aware Network Acceleration](/index.php/publication/2022-10_lana-latency-aware-network-acceleration) [Pavlo Molchanov](/index.php/person/pavlo-molchanov), Jimmy Hall, [Hongxu Danny Yin](/index.php/person/danny-yin), [Jan Kautz](/index.php/person/jan-kautz), Nicolo Fusi, [Arash Vahdat](/index.php/person/arash-vahdat) [European Conference on Computer Vision (ECCV), 2022](https://arxiv.org/abs/2107.10624) [GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras](/index.php/publication/2022-06_glamr-global-occlusion-aware-human-mesh-recovery-dynamic-cameras) [Ye Yuan](/index.php/person/ye-yuan), [Umar Iqbal](/index.php/person/umar-iqbal), [Pavlo Molchanov](/index.php/person/pavlo-molchanov), Kris Kitani, [Jan Kautz](/index.php/person/jan-kautz) IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 (Ora… [A-ViT: Adaptive Tokens for Efficient Vision Transformer](/index.php/publication/2022-06_vit-adaptive-tokens-efficient-vision-transformer) [Hongxu Danny Yin](/index.php/person/danny-yin), [Arash Vahdat](/index.php/person/arash-vahdat), Jose M. Alvarez, Arun Mallya, [Jan Kautz](/index.php/person/jan-kautz), [Pavlo Molchanov](/index.php/person/pavlo-molchanov) IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 (Ora… [GradViT: Gradient Inversion of Vision Transformers](/index.php/publication/2022-05_gradvit-gradient-inversion-vision-transformers) Ali Hatamizadeh , [Hongxu Danny Yin](/index.php/person/danny-yin), [Holger Roth](/index.php/person/holger-roth), [Wenqi Li](/index.php/person/wenqi-li), [Jan Kautz](/index.php/person/jan-kautz), [Daguang Xu](/index.php/person/daguang-xu), [Pavlo Molchanov](/index.php/person/pavlo-molchanov) [IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022](https://cvpr2022.thecvf.com/) [When to Prune? A Policy towards Early Structural Pruning](/index.php/publication/2022-05_when-prune-policy-towards-early-structural-pruning) Maying Shen, [Pavlo Molchanov](/index.php/person/pavlo-molchanov), [Hongxu Danny Yin](/index.php/person/danny-yin), Jose M. Alvarez IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022 ### 2021 [KAMA: 3D Keypoint Aware Body Mesh Articulation](/publication/2021-12_kama-3d-keypoint-aware-body-mesh-articulation) [Umar Iqbal](/person/umar-iqbal), Kevin Xie, Kelly Guo, [Jan Kautz](/person/jan-kautz), [Pavlo Molchanov](/person/pavlo-molchanov) [International Conference on 3D Vision](https://3dv2021.surrey.ac.uk/) [Optimizing Selective Protection for CNN Resilience](/publication/2021-10_optimizing-selective-protection-cnn-resilience) Abdulrahman Mahmoud, [Siva Hari](/person/siva-hari), Christopher W. Fletcher, Sarita V. Adve, [Charbel Sakr](/person/charbel-sakr), Naresh Shanbhag, [Pavlo Molchanov](/person/pavlo-molchanov), [Michael B. Sullivan](/person/mike-sullivan), Timothy Tsai, [Steve Keckler](/person/stephen-keckler) [International Symposium on Software Reliability Engineering (ISSRE)](https://ieeexplore.ieee.org/document/9700317) [See through Gradients: Image Batch Recovery via GradInversion](/publication/2021-06_see-through-gradients-image-batch-recovery-gradinversion) [Hongxu Danny Yin](/person/danny-yin), Arun Mallya, [Arash Vahdat](/person/arash-vahdat), Jose M. Alvarez, [Jan Kautz](/person/jan-kautz), [Pavlo Molchanov](/person/pavlo-molchanov) [IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021](https://openaccess.thecvf.com/content/CVPR2021/papers/Yin_See_Through_Gradients_Image_Batch_Recovery_via_GradInversion_CVPR_2021_paper.pdf) [Optimal Quantization Using Scaled Codebook](/publication/2021-06_optimal-quantization-using-scaled-codebook) Yerlan Idelbayev, [Pavlo Molchanov](/person/pavlo-molchanov), Maying Shen, [Hongxu Danny Yin](/person/danny-yin), Miguel A. Carreira-Perpinan, Jose M. Alvarez [IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021](https://openaccess.thecvf.com/content/CVPR2021/html/Idelbayev_Optimal_Quantization_Using_Scaled_Codebook_CVPR_2021_paper.html) [DexYCB: A Benchmark for Capturing Hand Grasping of Objects](/publication/2021-06_dexycb-benchmark-capturing-hand-grasping-objects) [Yu-Wei Chao](/person/yu-wei-chao), [Wei Yang](/person/wei-yang), Yu Xiang, [Pavlo Molchanov](/person/pavlo-molchanov), Ankur Handa, [Jonathan Tremblay](/person/jonathan-tremblay), [Yashraj Narang](/person/yashraj-narang), Karl Van Wyk, [Umar Iqbal](/person/umar-iqbal), [Stan Birchfield](/person/stan-birchfield), [Jan Kautz](/person/jan-kautz), Dieter Fox [IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021](http://cvpr2021.thecvf.com) [Data-Free Knowledge Distillation for Object Detection](/index.php/publication/2021-01_data-free-knowledge-distillation-object-detection) Akshay Chawla, [Hongxu Danny Yin](/index.php/person/danny-yin), [Pavlo Molchanov](/index.php/person/pavlo-molchanov), Jose M. Alvarez [WACV 2021](https://openaccess.thecvf.com/content/WACV2021/html/Chawla_Data-Free_Knowledge_Distillation_for_Object_Detection_WACV_2021_paper.html) ### 2020 [HarDNN: Fine-Grained Vulnerability Evaluation and Protection for Convolutional Neural Networks](/publication/2020-09_hardnn-fine-grained-vulnerability-evaluation-and-protection-convolutional) Abdulrahman Mahmoud, [Siva Hari](/person/siva-hari), Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh Shanbhag, [Pavlo Molchanov](/person/pavlo-molchanov), [Michael B. Sullivan](/person/mike-sullivan), Timothy Tsai, [Steve Keckler](/person/stephen-keckler) [SRC TECHCON](https://src.secure-platform.com/a/page/techcon) [Weakly-Supervised 3D Hand Pose Estimation via Biomechanical Constraints ](/publication/2020-08_weakly-supervised-3d-hand-pose-estimation-biomechanical-constraints) Adrian Spurr, [Umar Iqbal](/person/umar-iqbal), [Pavlo Molchanov](/person/pavlo-molchanov), Otmar Hilliges, [Jan Kautz](/person/jan-kautz) [European Conference on Computer Vision, 2020](https://eccv2020.eu/) [Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion](/publication/2020-06_dreaming-distill-data-free-knowledge-transfer-deepinversion) [Hongxu Danny Yin](/person/danny-yin), [Pavlo Molchanov](/person/pavlo-molchanov), Jose M. Alvarez, Zhizhong Li, Arun Mallya, Derek Hoiem, Niraj K. Jha, [Jan Kautz](/person/jan-kautz) [IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020 (Ora…](https://openaccess.thecvf.com/content_CVPR_2020/papers/Yin_Dreaming_to_Distill_Data-Free_Knowledge_Transfer_via_DeepInversion_CVPR_2020_paper.pdf) [Weakly-Supervised 3D Human Pose Learning via Multi-view Images in the Wild](/publication/2020-06_weakly-supervised-3d-human-pose-learning-multi-view-images-wild) [Umar Iqbal](/person/umar-iqbal), [Pavlo Molchanov](/person/pavlo-molchanov), [Jan Kautz](/person/jan-kautz) [IEEE Computer Vision and Pattern Recognition](http://cvpr2020.thecvf.com/) [Feature Map Vulnerability Evaluation in CNNs](/publication/2020-03_feature-map-vulnerability-evaluation-cnns) Abdulrahman Mahmoud, [Siva Hari](/person/siva-hari), Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh Shanbhag, [Pavlo Molchanov](/person/pavlo-molchanov), [Michael B. Sullivan](/person/mike-sullivan), Timothy Tsai, [Steve Keckler](/person/stephen-keckler) [Workshop on Secure and Resilient Autonomy](http://sara-workshop.org/) [HarDNN: Feature Map Vulnerability Evaluation in CNNs](/publication/2020-02_hardnn-feature-map-vulnerability-evaluation-cnns) Abdulrahman Mahmoud, [Siva Hari](/person/siva-hari), Christopher W. Fletcher, Sarita V. Adve, Charbel Sakr, Naresh Shanbhag, [Pavlo Molchanov](/person/pavlo-molchanov), [Michael B. Sullivan](/person/mike-sullivan), Timothy Tsai, [Steve Keckler](/person/stephen-keckler) [arXiv](https://arxiv.org/abs/2002.09786) ### 2019 [Few-Shot Adaptive Gaze Estimation ](/publication/2019-10_few-shot-adaptive-gaze-estimation) Seonwook Park, [Shalini De Mello](/person/shalini-de-mello), [Pavlo Molchanov](/person/pavlo-molchanov), [Umar Iqbal](/person/umar-iqbal), Otmar Hilliges, [Jan Kautz](/person/jan-kautz) [International Conference on Computer Vision (ICCV) 2019](http://iccv2019.thecvf.com/program/overview) Oral [SCOPS: Self-Supervised Co-Part Segmentation](/index.php/publication/2019-06_scops-self-supervised-co-part-segmentation) Wei-Chih Hung, Varun Jampani, [Sifei Liu](/index.php/person/sifei-liu), [Pavlo Molchanov](/index.php/person/pavlo-molchanov), Ming-Hsuan Yang , [Jan Kautz](/index.php/person/jan-kautz) [CVPR 2019](https://varunjampani.github.io/scops/) [Importance Estimation for Neural Network Pruning](/publication/2019-06_importance-estimation-neural-network-pruning) [Pavlo Molchanov](/person/pavlo-molchanov), Arun Mallya, [Stephen Tyree](/person/stephen-tyree), [Iuri Frosio](/person/iuri-frosio), [Jan Kautz](/person/jan-kautz) CVPR2019 ### 2018 [Hand Pose Estimation via Latent 2.5 D Heatmap Regression](/publication/2018-09_hand-pose-estimation-latent-25-d-heatmap-regression) [Umar Iqbal](/person/umar-iqbal), [Pavlo Molchanov](/person/pavlo-molchanov), [Thomas Breuel](/person/thomas-breuel), Juergen Gall, [Jan Kautz](/person/jan-kautz) ECCV2018 [Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals](/publication/2018-06_depth-based-3d-hand-pose-estimation-current-achievements-future-goals) Shanxin Yuan, Guillermo Garcia-Hernando, Bjorn Stenger, [Pavlo Molchanov](/person/pavlo-molchanov), [Jan Kautz](/person/jan-kautz), Sina Honari [Conference on Computer Vision and Pattern Recognition](http://cvpr2018.thecvf.com) [Improving Landmark Localization with Semi-Supervised Learning](/publication/2018-06_improving-landmark-localization-semi-supervised-learning) Sina Honari, [Pavlo Molchanov](/person/pavlo-molchanov), [Stephen Tyree](/person/stephen-tyree), Pascal Vincent, Christopher Pal, [Jan Kautz](/person/jan-kautz) [CVPR](http://cvpr2018.thecvf.com) [Making Convolutional Networks Recurrent for Visual Sequence Learning](/index.php/publication/2018-06_making-convolutional-networks-recurrent-visual-sequence-learning) [Xiaodong Yang](/index.php/person/xiaodong-yang), [Pavlo Molchanov](/index.php/person/pavlo-molchanov), [Jan Kautz](/index.php/person/jan-kautz) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR)](http://xiaodongyang.org/publications/papers/prernn-cvpr18.pdf) [IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification](/publication/2018-04_iamnn-iterative-and-adaptive-mobile-neural-network-efficient-image) Sam Leroux, [Pavlo Molchanov](/person/pavlo-molchanov), Pieter Simoens, Bart Dhoedt, [Thomas Breuel](/person/thomas-breuel), [Jan Kautz](/person/jan-kautz) [International Conference on Learning Representations, Workshop](https://iclr.cc) ### 2017 [A Lightweight Approach for On-the-Fly Reflectance Estimation](/index.php/publication/2017-10_lightweight-approach-fly-reflectance-estimation) Kihwan Kim, [Jinwei Gu](/index.php/person/jinwei-gu), [Stephen Tyree](/index.php/person/stephen-tyree), [Pavlo Molchanov](/index.php/person/pavlo-molchanov), Matthias Nießner, [Jan Kautz](/index.php/person/jan-kautz) [IEEE International Conference on Computer Vision (ICCV 2017)](http://iccv2017.thecvf.com/) [Pruning Convolutional Neural Networks for Resource Efficient Inference](/publication/2017-04_pruning-convolutional-neural-networks-resource-efficient-inference) [Pavlo Molchanov](/person/pavlo-molchanov), [Stephen Tyree](/person/stephen-tyree), [Tero Karras](/person/tero-karras), [Timo Aila](/person/timo-aila), [Jan Kautz](/person/jan-kautz) [International Conference on Learning Representations (ICLR 2017)](https://openreview.net/forum?id=SJGCiw5gl¬eId=SJGCiw5gl) ### 2016 [Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification](/publication/2016-10_multilayer-and-multimodal-fusion-deep-neural-networks-video-classification) [Xiaodong Yang](/person/xiaodong-yang), [Pavlo Molchanov](/person/pavlo-molchanov), [Jan Kautz](/person/jan-kautz) [ACM Multimedia](http://www.acmmm.org/2016/) [Towards Selecting Robust Hand Gestures for Automotive Interfaces](/index.php/publication/2016-06_towards-selecting-robust-hand-gestures-automotive-interfaces-0) [Shalini Gupta](/index.php/person/shalini-de-mello), [Pavlo Molchanov](/index.php/person/pavlo-molchanov), Xiaodong Yang, [Stephen Tyree](/index.php/person/stephen-tyree), [Jan Kautz](/index.php/person/jan-kautz) [IEEE Intelligent Vehicles Symposium (IV) 2016](http://iv2016.org/) [Towards Selecting Robust Hand Gestures for Automotive Interfaces ](/publication/2016-06_towards-selecting-robust-hand-gestures-automotive-interfaces) Shalini Gupta, [Pavlo Molchanov](/person/pavlo-molchanov), [Xiaodong Yang](/person/xiaodong-yang), Kihwan Kim, [Stephen Tyree](/person/stephen-tyree), [Jan Kautz](/person/jan-kautz) [IEEE Intelligent Vehicles Symposium](http://iv2016.org/) [Online Detection and Classification of Dynamic Hand Gestures with Recurrent 3D Convolutional Neural Networks ](/index.php/publication/2016-06_online-detection-and-classification-dynamic-hand-gestures-recurrent-3d) [Pavlo Molchanov](/index.php/person/pavlo-molchanov), [Xiaodong Yang](/index.php/person/xiaodong-yang), [Shaline Gupta](/index.php/person/shalini-de-mello), Kihwan Kim, [Stephen Tyree](/index.php/person/stephen-tyree), [Jan Kautz](/index.php/person/jan-kautz) [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016](http://cvpr2016.thecvf.com/) ### 2015 [Hand Gesture Recognition with 3D Convolutional Neural Networks ](/index.php/publication/2015-06_hand-gesture-recognition-3d-convolutional-neural-networks) [Pavlo Molchanov](/index.php/person/pavlo-molchanov), [Shalini Gupta](/index.php/person/shalini-de-mello), Kihwan Kim, [Jan Kautz](/index.php/person/jan-kautz) [IEEE Computer Vision and Pattern Recognition Workshop (CVPRW) 2015](http://www.pamitc.org/cvpr15/) Winner (1st place) Hand Gesture Recognition Challenge [Short-Range FMCW Monopulse Radar for Hand-Gesture Sensing ](/publication/2015-05_short-range-fmcw-monopulse-radar-hand-gesture-sensing) [Pavlo Molchanov](/person/pavlo-molchanov), Shalini Gupta, Kihwan Kim, Kari Pulli [IEEE International Radar Conference](http://www.ieeeintlradar2015.com/program/) [Multi-sensor System for Driver’s Hand-Gesture Recognition ](/publication/2015-05_multi-sensor-system-driver-s-hand-gesture-recognition) [Pavlo Molchanov](/person/pavlo-molchanov), [Shalini Gupta](/person/shalini-de-mello), Kihwan Kim, Kari Pulli [IEEE International Conference on Automatic Face and Gesture Recognition (FG) 20…](http://www.fg2015.org/)