Occluded video instance segmentation: A benchmark by Qi, J, Gao, Y, Hu, Y, Wang, X, Liu, X, Bai, X, Belongie, S, Yuille, A, Torr, PHS, Bai, S

Multi-shot temporal event localization: a benchmark by Liu, X, Hu, Y, Bai, S, Ding, F, Bai, X, Torr, PHS

Lifelong benchmarks: efficient model evaluation in an era of rapid progress by Prabhu, A, Udandarao, V, Torr, PHS, Bethge, M, Bibi, A, Albanie, S

“…Standardized benchmarks drive progress in machine learning. However, with repeated testing, the risk of overfitting grows as algorithms overexploit benchmark idiosyncrasies. …”

Adversarial metric attack and defense for person re-identification by Bai, S, Li, Y, Zhou, Y, Li, Q, Torr, PHS

“…Meanwhile, we also present an early attempt of training a metric-preserving network, thereby defending the metric against adversarial attacks. At last, by benchmarking various adversarial settings, we expect that our work can facilitate the development of adversarial attack and defense in metric-based applications. …”

The seventh visual object tracking VOT2019 Challenge results by Kristanl, M, Matas, J, Leonardis, A, Zhang, L, Torr, PHS

“…The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. …”

No "zero-shot" without exponential data: pretraining concept frequency determines multimodal model performance by Udandarao, V, Prabhu, A, Ghosh, A, Sharma, Y, Torr, PHS, Bibi, A, Albanie, S, Bethge, M

“…Furthermore, upon benchmarking models on long-tailed data sampled based on our analysis, we demonstrate that multimodal models across the board perform poorly. …”

Raising the bar on the evaluation of out-of-distribution detection by Mukhoti, J, Lin, T-Y, Chen, B-C, Shah, A, Torr, PHS, Dokania, PK, Lim, S-N

“…Through extensive experiments on MNIST, CIFAR-10/100 and ImageNet, we show that a) state-of-the-art OoD detection methods which perform exceedingly well on conventional benchmarks are significantly less robust to our proposed benchmark. …”

Gradient matching for domain generalization by Shi, Y, Seely, J, Torr, PHS, Siddharth, N, Hannun, A, Usunier, N, Synnaeve, G

“…We perform experiments on the WILDS benchmark, which captures distribution shift in the real world, as well as the DOMAINBED benchmark that focuses more on synthetic-to-real transfer. …”

SiamMask: A framework for fast online object tracking and segmentation by Hu, W, Wang, Q, Zhang, L, Bertinetto, L, Torr, PHS

“…It yields real-time state-of-the art results on visual-object tracking benchmarks, while at the same time demonstrating competitive performance at a high speed for video object segmentation benchmarks.…”

Holistically-attracted wireframe parsing by Xue, N, Wu, T, Bai, S, Wang, F, Xia, G-S, Zhang, L, Torr, PHS

“…On both benchmarks, it obtains state-of-the-art performance in terms of accuracy and efficiency. …”

Automated and verified deep learning by Behl, HS

“…Third, we show an application by tackling video segmentation as a meta learning problem and demonstrating state-of-the-art results on common benchmarks.</p>…”

Devon: deformable volume network for learning optical flow by Lu, Y, Valmadre, J, Wang, H, Kannala, J, Harandi, M, Torr, PHS, Soc, IEEEC

“…Experiments show Devon is more suitable in handling small objects moving fast and achieves comparable results to the state-of-the-art methods in public benchmarks.…”

Separable flow: learning motion cost volumes for optical flow estimation by Zhang, F, Woodford, OJ, Prisacariu, V, Torr, PHS

“…Our method leads both the now standard Sintel and KITTI optical flow benchmarks in terms of accuracy, and is also shown to generalize better from synthetic to real data.…”

The Thermal Infrared Visual Object Tracking VOT-TIR2015 challenge results by Felsberg, M, Vojır, T, Nebehay, G, Pflugfelder, R, Lukezic, A, Garcia-Martin, A, Saffari, A, Li, A, Montero, AS, Zhao, B, Schmid, C, Berg, A, Chen, D, Du, D, Khan, FS, Porikli, F, Zhu, G, Zhu, G, Lu, H, Kieritz, H, Li, H, Qi, H, Hager, G, Jeong, J-C, Cho, J-I, Lee, J-Y, Zhu, J, Li, J, Feng, J, Wang, J, Kim, J-W, Lang, J, Martinez, JM, Ahlberg, J, Xue, K, Alahari, K, Ma, L, Ke, L, Wen, L, Bertinetto, L, Danelljan, M, Arens, M, Tang, M, Chang, M-C, Kristan, M, Miksik, O, Torr, PHS, Martin-Nieto, R, Laganiere, R, Hare, S, Golodetz, S

“…VOT-TIR2015 is the first benchmark on short-term tracking in TIR sequences. …”

The visual object tracking VOT2015 challenge results by Kristan, M, Matas, J, Leonardis, A, Bibi, A, Bertinetto, L, Miksik, O, Torr, PHS, Hicks, SL, Golodetz, S

“…The number of tested trackers makes VOT 2015 the largest benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the appendix. …”

Fully-convolutional Siamese networks for object tracking by Bertinetto, L, Valmadre, J, Henriques, JF, Vedaldi, A, Torr, PHS

“…Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks.…”

Siam R-CNN: visual tracking by re-detection by Voigtlaender, P, Luiten, J, Torr, PHS, Leibe, B

“…Siam R-CNN achieves the current best performance on ten tracking benchmarks, with especially strong results for long-term tracking. …”

The visual object tracking VOT2016 challenge results by Kristan, M, Leonardis, A, Matas, J, Felsberg, M, Pflugfelder, R, Čehovin, L, Vojír̃, T, Häger, G, Lukežič, A, Fernández, G, Gupta, A, Petrosino, A, Memarmoghadam, A, Garcia-Martin, A, Solís Montero, A, Vedaldi, A, Robinson, A, Ma, AJ, Varfolomieiev, A, Alatan, A, Erdem, A, Ghanem, B, Liu, B, Han, B, Martinez, B, Chang, C-M, Xu, C, Sun, C, Kim, D, Chen, D, Du, D, Mishra, D, Yeung, D-Y, Gundogdu, E, Erdem, E, Khan, F, Porikli, F, Zhao, F, Bunyak, F, Battistone, F, Zhu, G, Roffo, G, Subrahmanyam, GRKS, Bastos, G, Seetharaman, G, Medeiros, H, Li, H, Qi, H, Bischof, H, Possegger, H, Henriques, JF, Torr, PHS

“…The number of tested state-of-the-art trackers makes the VOT 2016 the largest and most challenging benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the Appendix. …”

Continual learning in low-rank orthogonal subspaces by Chaudhry, A, Khan, N, Dokania, PK, Torr, PHS

“…To the best of our understanding, we report, for the first time, strong results over experience-replay baseline with and without memory on standard classification benchmarks in continual learning.…”

Open vocabulary semantic segmentation with Patch Aligned Contrastive Learning by Mukhoti, J, Lin, T-Y, Poursaeed, O, Wang, R, Shah, A, Torr, PHS, Lim, S-N

“…Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabulary zero-shot segmentation on 4 different segmentation benchmarks: Pascal VOC, Pascal Context, COCO Stuff and ADE20K. …”