Pixel-level scene understanding with deep structured models by Arnab, A

Pixelwise instance segmentation with a dynamically instantiated network by Arnab, A, Torr, P

Bottom-up Instance Segmentation using Deep Higher-Order CRFs by Arnab, A, Torr, PHS

Holistic, instance-level human parsing by Li, Q, Arnab, A, Torr, P

Higher Order Conditional Random Fields in Deep Neural Networks by Arnab, A, Jayasumana, S, Zheng, S, Torr, P

Weakly- and semi-supervised panoptic segmentation by Li, Q, Arnab, A, Torr, P

On the robustness of semantic segmentation models to adversarial attacks by Arnab, A, Miksik, O, Torr, PHS

On the robustness of semantic segmentation models to adversarial attacks by Arnab, A, Miksik, O, Torr, P

Exploiting temporal context for 3D human pose estimation in the wild by Arnab, A, Doersch, C, Zisserman, A

Simplifying TugGraph using zipping algorithms by Golodetz, S, Arnab, A, Voiculescu, ID, Cameron, SA

Dynamic graph message passing networks by Zhang, L, Xu, D, Arnab, A, Torr, PHS

Meta-learning deep visual words for fast video object segmentation by Behl, HS, Najaf, M, Arnab, A, Torr, PHS

Revisiting deep structured models for pixel-level labeling with gradient-based inference by Larsson, M, Arnab, A, Zheng, S, Torr, P, Kahl, F

A projected gradient descent method for CRF inference allowing end-to-end training of arbitrary pairwise potentials by Larsson, M, Arnab, A, Kahl, F, Zheng, S, Torr, P

Dynamic graph message passing networks for visual recognition by Zhang, L, Chen, M, Arnab, A, Xue, X, Torr, PHS

Deep fully-connected part-based models for human pose estimation by De Bem, R, Arnab, A, Golodetz, S, Sapienza, M, Torr, P

Joint object-material category segmentation from audio-visual cues by Arnab, A, Sapienza, M, Golodetz, S, Valentin, J, Miksik, O, Izadi, S, Torr, P

Dual graph convolutional network for semantic segmentation by Zhang, L, Li, X, Arnab, A, Yang, K, Tong, Y, Torr, P

An automated method for tendon image segmentation on ultrasound using grey-level co-occurrence matrix features and hidden Gaussian Markov random fields by Scott, I, Connell, D, Moulton, D, Waters, S, Namburete, A, Arnab, A, Malliaras, P

Conditional random fields meet deep neural networks for semantic segmentation: combining probabilistic graphical models with deep learning for structured prediction by Arnab, A, Zheng, S, Jayasumana, S, Romera-Paredes, B, Larsson, M, Kirillov, A, Savchynskyy, B, Rother, C, Kahl, F, Torr, P