MV2MAE: Multi-View Video Masked Autoencoders

no code implementations • 29 Jan 2024 • Ketul Shah, Robert Crandall, Jie Xu, Peng Zhou, Marian George, Mayank Bansal, Rama Chellappa

We report state-of-the-art results on the NTU-60, NTU-120 and ETRI datasets, as well as in the transfer learning setting on NUCLA, PKU-MMD-II and ROCOG-v2 datasets, demonstrating the robustness of our approach.

Action Recognition Decoder +2

Semantic Clustering for Robust Fine-Grained Scene Recognition

no code implementations • 26 Jul 2016 • Marian George, Mandar Dixit, Gábor Zogg, Nuno Vasconcelos

In this work, we propose a novel domain generalization approach for fine-grained scene recognition.

Clustering Domain Generalization +2

Image Parsing with a Wide Range of Classes and Scene-Level Context

no code implementations • CVPR 2015 • Marian George

We achieve state-of-the-art performance on the SIFTflow dataset and near-record results on LMSun.

General Classification Image Retrieval +3

Fine-Grained Product Class Recognition for Assisted Shopping

no code implementations • 14 Oct 2015 • Marian George, Dejan Mircic, Gábor Sörös, Christian Floerkemeier, Friedemann Mattern

We present a system that visually recognizes the fine-grained product classes of items on a shopping list, in shelves images taken with a smartphone in a grocery store.

Active Learning