Keynote speaker: Yann LeCun
"The Future of Computer Vision is Self-Supervised Learning"
"Homogeneous Linear Inequality Constraints for Neural Network Activations" by T. Frerix, M. Niessner, and D. Cremers
"SUW-Learn: Joint Supervised, Unsupervised, Weakly Supervised Deep Learning for Monocular Depth Estimation" by H. Ren, A. Raj, M. El-Khamy, and J. Lee
"Top-Down Networks: A coarse-to-fine reimagination of CNNs" by I. Lelekas, N. Tomen, S.L. Pintea, and J. van Gemert
"MUTE: Inter-class Ambiguity Driven Multi-hot Target Encoding for Deep Neural Network Design" by M. Jaiswal, B. Kang, J. Lee, and M. Cho
"SmoothMix: a Simple Yet Effective Data Augmentation to Train Robust Classifiers" by J.H. Lee, M.Z. Zaheer, M. Astrid, and S.I. Lee
"S2LD: Semi-Supervised Landmark Detection in Low Resolution Images and Impact on Face Verification" by A. Kumar and Rama Chellappa
"P2L: Predicting Transfer Learning for Images and Semantic Relations" by B. Bhattacharjee, J. Kender, M. Hill, P. Dube, S. Huo, M.R. Glass, B.M. Belgodere, S. Pankanti, N.C. Codella, and P. Watson
"Semi-Supervised Learning with Scarce Annotations" by S-A. Rebuffi, S. Ehrhardt, K. Han, A. Vedaldi, A. Zisserman
"Spatio-temporal action detection and localization using a hierarchical LSTM" by A. Ramaswamy, K. Seemakurthy, J. Gubbi, and B. Purushothaman
"Can We Learn Heuristics For Graphical Model Inference Using Reinforcement Learning?" by S. Messaoud, M. Kumar, and A. Schwing
"Distilling Knowledge from Refinement in Multiple Instance Detection Networks" by L.F.A. Zeni and C.R. Jung
"Robust One Shot Audio to Video Generation" by N. Kumar, S. Goel, A. Narang, M. Hasan
"Deflating Dataset Bias Using Synthetic Data Augmentation" by N. Jaipuria, X. Zhang, R. Bhasin, M. Arafa, P. Chakravarty, S. Shrivastava, S. Manglani, V.N. Murali