PASS: An ImageNet replacement for self-supervised pretraining without humans by Asano, YM, Rupprecht, C, Zisserman, A, Vedaldi, A

“…PASS does not make existing datasets obsolete, as for instance it is insufficient for benchmarking. However, it shows that model pretraining is often possible while using safer data, and it also provides the basis for a more robust evaluation of pretraining methods.…”

Label, verify, correct: a simple few shot object detection method by Kaul, P, Xie, W, Zisserman, A

“…Additionally, we demonstrate our method maintains base class performance, and the utility of simple augmentations in FSOD. While benchmarking on PASCAL VOC and MS-COCO, our method achieves stateof-the-art or second-best performance compared to existing approaches across all number of shots.…”

Open-set recognition: a good closed-set classifier is all you need? by Vaze, S, Han, K, Vedaldi, A, Zisserman, A

“…We find that this relationship holds across loss objectives and architectures, and further demonstrate the trend both on the standard OSR benchmarks as well as on a large-scale ImageNet evaluation. …”

The Pascal Visual Object Classes (VOC) Challenge by Everingham, M, Van Gool, L, Williams, C, Winn, J, Zisserman, A

“…The Pascal Visual Object Classes (VOC) challenge is a benchmark in visual object category recognition and detection, providing the vision and machine learning communities with a standard dataset of images and annotation, and standard evaluation procedures. …”

It's in the bag: stronger supervision for automated face labelling by Parkhi, O, Rahtu, E, Zisserman, A

“…Each of these contributions delivers a significant boost in performance, and we demonstrate this on standard benchmarks using tracks provided by authors of prior work. …”

Emotion Recognition in Speech using Cross-Modal Transfer in the Wild by Albanie, S, Nagrani, A, Vedaldi, A, Zisserman, A

“…We make the following contributions: (i) we develop a strong teacher network for facial emotion recognition that achieves the state of the art on a standard benchmark; (ii) we use the teacher to train a student, tabula rasa, to learn representations (embeddings) for speech emotion recognition without access to labelled audio data; and (iii) we show that the speech emotion embedding can be used for speech emotion recognition on external benchmark datasets. …”

Audio-visual synchronisation in the wild by Chen, H, Xie, W, Afouras, T, Nagrani, A, Vedaldi, A, Zisserman, A

“…We apply our method on standard lip reading speech benchmarks, LRS2 and LRS3, with ablations on various aspects. …”

Automated video face labelling for films and TV material by Parkhi, OM, Rahtu, E, Cao, Q, Zisserman, A

“…Each of these contributions delivers a boost in performance, and we demonstrate this on standard benchmarks using tracks provided by authors of prior work. …”

Deep structured output learning for unconstrained text recognition by Jaderberg, M, Simonyan, K, Vedaldi, A, Zisserman, A

“…The resulting model is a more accurate system on standard real-world text recognition benchmarks than character prediction alone, setting a benchmark for systems that have not been trained on a particular lexicon. …”

Multicolumn networks for face recognition by Xie, W, Zisserman, A

“…Comparing with the previous state-of-the-art architectures trained with the same dataset (VGGFace2), our Multicolumn Networks show an improvement of between 2-6% on the IARPA IJB face recognition benchmarks, and exceed the state of the art for all methods on these benchmarks.…”

Inducing predictive uncertainty estimation for face recognition by Xie, W, Byrne, J, Zisserman, A

“…We describe three use cases on the public IJB-C face verification benchmark: (i) to improve 1:1 image-based verification error rates by rejecting low-quality face images; (ii) to improve quality score based fusion performance on the 1:1 set-based verification benchmark; and (iii) its use as a quality measure for selecting high quality (unblurred, good lighting, more frontal) faces from a collection, e.g. for automatic enrolment or display.…”

Quo Vadis, action recognition? A new model and the kinetics dataset by Carreira, J, Zisserman, A

“…We provide an analysis on how current architectures fare on the task of action classification on this dataset and how much performance improves on the smaller benchmark datasets after pre-training on Kinetics. …”

Sub-word level lip reading with visual attention by Prajwal, KR, Afouras, T, Zisserman, A

“…Moreover, on the AVA-ActiveSpeaker benchmark, our VSD model surpasses all visual-only baselines and even outperforms several recent audio-visual methods.…”

Personalizing human video pose estimation by Charles, J, Pfister, T, Maggee, D, Hogg, D, Zisserman, A

“…Furthermore, we show that training from the automatically generated annotations can be used to improve the performance of a generic ConvNet on other benchmarks.</p>…”

BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues by Albanie, S, Varol, G, Momeni, L, Afouras, T, Chung, JS, Fox, N, Zisserman, A

“…We make the following contributions: (1) We show how to use mouthing cues from signers to obtain high-quality annotations from video data—the result is the BSL-1K dataset, a collection of British Sign Language (BSL) signs of unprecedented scale; (2) We show that we can use BSL-1K to train strong sign recognition models for co-articulated signs in BSL and that these models additionally form excellent pretraining for other sign languages and benchmarks—we exceed the state of the art on both the MSASL and WLASL benchmarks. …”

No representation rules them all in category discovery by Vaze, S, Vedaldi, A, Zisserman, A

“…Finally, when we transfer these findings to real data on the challenging Semantic Shift Benchmark suite, we find that μGCD outperforms all prior work, setting a new state-of-the-art.…”

On segmenting moving objects with minimal visibility by Lamdouar, H

“…To validate our motion segmentation models, we collect a highly challenging dataset for Moving Camouflaged Animals (MoCA), which is today the largest benchmark for video camouflage object detection.</p> <p>Second, we explore object-centric approaches to motion segmentation. …”

Out of time: automated lip sync in the wild by Chung, J, Zisserman, A

“…On both tasks we set a new state-of-the-art on standard benchmark datasets.</p>…”

Input-level inductive biases for 3D reconstruction by Yifan, W, Doersch, C, Arandjelović, R, Carreira, J, Zisserman, A

“…In particular we study how to encode cameras, projective ray incidence and epipolar geometry as model inputs, and demonstrate competitive multi-view depth estimation performance on multiple benchmarks.…”

Look, listen and learn by Arandjelovic, R, Zisserman, A

“…These features set the new state-of-the-art on two sound classification benchmarks, and perform on par with the state-of-the-art selfsupervised approaches on ImageNet classification. …”