Search Results for author:
Found 257 papers, 123 papers with code
Amplifying Key Cues for Human-Object-Interaction Detection
In this paper we introduce two methods to amplify key cues in the image, and also a method to combine these and other cues when considering the interaction between a human and an object.
Perception Test 2024: Challenge Summary and a Novel Hour-Long VideoQA Benchmark
We summarise in this report the challenge tasks and results, and introduce in detail the novel hour-long video QA benchmark 1h-walk VQA.
The Sound of Water: Inferring Physical Properties from Pouring Liquids
We study the connection between audio-visual observations and the underlying physics of a mundane yet intriguing everyday activity: pouring liquids.
A Short Note on Evaluating RepNet for Temporal Repetition Counting in Videos
We discuss some consistent issues on how RepNet has been evaluated in various papers.
Automated Spinal MRI Labelling from Reports Using a Large Language Model
We propose a general pipeline to automate the extraction of labels from radiology reports using large language models, which we validate on spinal MRI reports.
It's Just Another Day: Unique Video Captioning by Discriminative Prompting
We introduce two benchmarks for unique captioning, based on egocentric footage and timeloop movies - where repeating actions are common.
Character-aware audio-visual subtitling in context
We validate the method on a dataset with 12 TV shows, demonstrating superior performance in speaker diarisation and character recognition accuracy compared to existing approaches.
The VoxCeleb Speaker Recognition Challenge: A Retrospective
In this paper, we provide a review of these challenges that covers: what they explored; the methods developed by the challenge participants and how these evolved; and also the current state of the field for speaker verification and diarisation.
3D-Aware Instance Segmentation and Tracking in Egocentric Videos
Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility.
Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Names
Enabling engagement of manga by visually impaired individuals presents a significant challenge due to its inherently visual nature.
OVR: A Dataset for Open Vocabulary Temporal Repetition Counting in Videos
The model is trained and evaluated on the OVR dataset, and its performance assessed with and without using text to specify the target class to count.
AutoAD-Zero: A Training-Free Framework for Zero-Shot Audio Description
Our objective is to generate Audio Descriptions (ADs) for both movies and TV series in a training-free manner.
TAPVid-3D: A Benchmark for Tracking Any Point in 3D
We introduce a new benchmark, TAPVid-3D, for evaluating the task of long-range Tracking Any Point in 3D (TAP-3D).
CountGD: Multi-Modal Open-World Counting
The goal of this paper is to improve the generality and accuracy of open-vocabulary object counting in images.
Ranked #1 on
Object Counting
on FSC147
Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language
We show that DenseAV can discover the ``meaning'' of words and the ``location'' of sounds without explicit localization supervision.
Ranked #1 on
Speech Prompted Semantic Segmentation
on ADE20K
A Tale of Two Languages: Large-Vocabulary Continuous Sign Language Recognition from Spoken Language Supervision
To this end, we introduce a multi-task Transformer model, CSLR2, that is able to ingest a signing sequence and output in a joint embedding space between signed language and spoken language text.
Made to Order: Discovering monotonic temporal changes via self-supervised video ordering
We also introduce a transformer-based model for ordering of image sequences of arbitrary length with built-in attribution maps.
AutoAD III: The Prequel -- Back to the Pixels
Generating Audio Description (AD) for movies is a challenging task that requires fine-grained visual understanding and an awareness of the characters and their names.
Moving Object Segmentation: All You Need Is SAM (and Flow)
The objective of this paper is motion segmentation -- discovering and segmenting the moving objects in a video.
TIM: A Time Interval Machine for Audio-Visual Action Recognition
We address the interplay between the two modalities in long videos by explicitly modelling the temporal extents of audio and visual events.
FlexCap: Generating Rich, Localized, and Flexible Captions in Images
The model, FlexCap, is trained to produce length-conditioned captions for input bounding boxes, and this allows control over the information density of its output, with descriptions ranging from concise object labels to detailed captions.
N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
To address this, we introduce Nested Neural Feature Fields (N2F2), a novel approach that employs hierarchical supervision to learn a single feature field, wherein different dimensions within the same high-dimensional feature encode scene properties at varying granularities.
A SOUND APPROACH: Using Large Language Models to generate audio descriptions for egocentric text-audio retrieval
Furthermore, we show that using the same prompts, we can successfully employ LLMs to improve the retrieval on EpicSounds, compared to using the original audio class labels of the dataset.
BootsTAP: Bootstrapped Training for Tracking-Any-Point
To endow models with greater understanding of physics and motion, it is useful to enable them to perceive how solid surfaces move and deform in real scenes.
Ranked #1 on
Point Tracking
on TAP-Vid-RGB-Stacking
Synchformer: Efficient Synchronization from Sparse Cues
Our objective is audio-visual synchronization with a focus on 'in-the-wild' videos, such as those on YouTube, where synchronization cues can be sparse.
Look, Listen and Recognise: Character-Aware Audio-Visual Subtitling
The goal of this paper is automatic character-aware subtitle generation.
The Manga Whisperer: Automatically Generating Transcriptions for Comics
In the past few decades, Japanese comics, commonly referred to as Manga, have transcended both cultural and linguistic boundaries to become a true worldwide sensation.
AutoAD III: The Prequel - Back to the Pixels
Generating Audio Description (AD) for movies is a challenging task that requires fine-grained visual understanding and an awareness of the characters and their names.
Amodal Ground Truth and Completion in the Wild
In contrast, we use 3D data to establish an automatic pipeline to determine authentic ground truth amodal masks for partially occluded objects in real images.
Perception Test 2023: A Summary of the First Challenge And Outcome
The First Perception Test challenge was held as a half-day workshop alongside the IEEE/CVF International Conference on Computer Vision (ICCV) 2023, with the goal of benchmarking state-of-the-art video models on the recently proposed Perception Test benchmark.
Text-Conditioned Resampler For Long Form Video Understanding
In this paper we present a text-conditioned video resampler (TCR) module that uses a pre-trained and frozen visual encoder and large language model (LLM) to process long video sequences for a task.
Ranked #15 on
Video Question Answering
on NExT-QA
Appearance-Based Refinement for Object-Centric Motion Segmentation
The goal of this paper is to discover, segment, and track independently moving objects in complex visual scenes.
A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames
Understanding long, real-world videos requires modeling of long-range visual dependencies.
Learning from One Continuous Video Stream
We introduce a framework for online learning from a single continuous video stream -- the way people and animals learn, without mini-batches, data augmentation or shuffling.
Predicting Spine Geometry and Scoliosis from DXA Scans
Our objective in this paper is to estimate spine curvature in DXA scans.
Show from Tell: Audio-Visual Modelling in Clinical Settings
Auditory and visual signals usually present together and correlate with each other, not only in natural environments but also in clinical settings.
AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description
Audio Description (AD) is the task of generating descriptions of visual content, at suitable time intervals, for the benefit of visually impaired audiences.
A General Protocol to Probe Large Vision Models for 3D Physical Understanding
To this end, we make the following contributions: (i) We introduce a general and lightweight protocol to evaluate whether features of an off-the-shelf large vision model encode a number of physical 'properties' of the 3D scene, by training discriminative classifiers on the features for these properties.
GestSync: Determining who is speaking without a talking head
In this paper we introduce a new synchronisation task, Gesture-Sync: determining if a person's gestures are correlated with their speech or not.
Ranked #1 on
Active Speaker Detection
on LRS3-TED
The Making and Breaking of Camouflage
We also incorporate the proposed camouflage score into a generative model as an auxiliary loss and show that effective camouflage images or videos can be synthesised in a scalable manner.
The Change You Want to See (Now in 3D)
The goal of this paper is to detect what has changed, if anything, between two "in the wild" images of the same 3D scene acquired from different camera positions and at different temporal instances.
Helping Hands: An Object-Aware Ego-Centric Video Recognition Model
We demonstrate the performance of the object-aware representations learnt by our model, by: (i) evaluating it for strong transfer, i. e. through zero-shot testing, on a number of downstream video-text retrieval and classification benchmarks; and (ii) by using the representations learned as input for long-term video understanding tasks (e. g. Episodic Memory in Ego4D).
OxfordVGG Submission to the EGO4D AV Transcription Challenge
This report presents the technical details of our submission on the EGO4D Audio-Visual (AV) Automatic Speech Recognition Challenge 2023 from the OxfordVGG team.
TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
We present a novel model for Tracking Any Point (TAP) that effectively tracks any queried point on any physical surface throughout a video sequence.
Ranked #1 on
Visual Tracking
on Kinetics
Multi-Modal Classifiers for Open-Vocabulary Object Detection
The goal of this paper is open-vocabulary object detection (OVOD) $\unicode{x2013}$ building a model that can detect objects beyond the set of categories seen at training, thus enabling the user to specify categories of interest at inference without the need for model retraining.
Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
Our approach outperforms the state-of-the-art on challenging scenes from the ScanNet, Hypersim, and Replica datasets, as well as on our newly created Messy Rooms dataset, demonstrating the effectiveness and scalability of our slow-fast clustering method.
Open-world Text-specified Object Counting
Our objective is open-world object counting in images, where the target object class is specified by a text description.
Ranked #4 on
Zero-Shot Counting
on FSC147
Perception Test: A Diagnostic Benchmark for Multimodal Video Models
We propose a novel multimodal video benchmark - the Perception Test - to evaluate the perception and reasoning skills of pre-trained multimodal models (e. g. Flamingo, SeViLA, or GPT-4).
Ranked #1 on
Point Tracking
on Perception Test
Verbs in Action: Improving verb understanding in video-language models
Understanding verbs is crucial to modelling how people and objects interact with each other and the environment through space and time.
Ranked #21 on
Zero-Shot Video Question Answer
on NExT-QA
Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime
This paper explores training medical vision-language models (VLMs) -- where the visual and language inputs are embedded into a common space -- with a particular focus on scenarios where training data is limited, as is often the case in clinical datasets.
AutoAD: Movie Description in Context
The objective of this paper is an automatic Audio Description (AD) model that ingests movies and outputs AD in text form.
Three ways to improve feature alignment for open vocabulary detection
The core problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes.
VoxSRC 2022: The Fourth VoxCeleb Speaker Recognition Challenge
This paper summarises the findings from the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22), which was held in conjunction with INTERSPEECH 2022.
Epic-Sounds: A Large-scale Dataset of Actions That Sound
We introduce Epic-Sounds, a large-scale dataset of audio annotations capturing temporal extents and class labels within the audio stream of the egocentric videos.
Zorro: the masked multimodal transformer
Attention-based models are appealing for multimodal processing because inputs from multiple modalities can be concatenated and fed to a single backbone network - thus requiring very little fusion engineering.
AutoAD II: The Sequel - Who, When, and What in Movie Audio Description
Audio Description (AD) is the task of generating descriptions of visual content, at suitable time intervals, for the benefit of visually impaired audiences.
A Light Touch Approach to Teaching Transformers Multi-view Geometry
Transformers are powerful visual learners, in large part due to their conspicuous lack of manually-specified priors.
Weakly-supervised Fingerspelling Recognition in British Sign Language Videos
Through extensive evaluations, we verify our method for automatic annotation and our model architecture.
TAP-Vid: A Benchmark for Tracking Any Point in a Video
Generic motion understanding from video involves not only tracking objects, but also perceiving how their surfaces deform and move.
End-to-end Tracking with a Multi-query Transformer
Multiple-object tracking (MOT) is a challenging task that requires simultaneous reasoning about location, appearance, and identity of the objects in the scene over time.
A Tri-Layer Plugin to Improve Occluded Detection
To this end we make the following four contributions: (1) We propose a simple 'plugin' module for the detection head of two-stage object detectors to improve the recall of partially occluded objects.
Ranked #1 on
Instance Segmentation
on Separated COCO
Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors
This contrasts with the case of synchronising videos of talking heads, where audio-visual correspondence is dense in both time and space.
Turbo Training with Token Dropout
The objective of this paper is an efficient training method for video tasks.
Compressed Vision for Efficient Video Understanding
In this work, we propose a framework enabling research on hour-long videos with the same hardware that can now process second-long videos.
CounTR: Transformer-based Generalised Visual Counting
In this paper, we consider the problem of generalised visual object counting, with the goal of developing a computational model for counting the number of objects from arbitrary semantic categories, using arbitrary number of "exemplars", i. e. zero-shot or few-shot counting.
Ranked #3 on
Exemplar-Free Counting
on FSC147
Automatic dense annotation of large-vocabulary sign language videos
Recently, sign language researchers have turned to sign language interpreted TV broadcasts, comprising (i) a video of continuous signing and (ii) subtitles corresponding to the audio content, as a readily available and large-scale source of training data.
Is an Object-Centric Video Representation Beneficial for Transfer?
The model learns a set of object-centric summary vectors for the video, and uses these vectors to fuse the visual and spatio-temporal trajectory 'modalities' of the video clip.
Segmenting Moving Objects via an Object-Centric Layered Representation
The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video.
Ranked #3 on
Unsupervised Object Segmentation
on FBMS-59
Context-Aware Transformers For Spinal Cancer Detection and Radiological Grading
(iii) We also apply SCT to an existing problem: radiological grading of inter-vertebral discs (IVDs) in lumbar MR scans for common degenerative changes. We show that by considering the context of vertebral bodies in the image, SCT improves the accuracy for several gradings compared to previously published model.
A CLIP-Hitchhiker's Guide to Long Video Retrieval
Our goal in this paper is the adaptation of image-text models for long video retrieval.
Ranked #4 on
Zero-Shot Action Recognition
on Charades
Scaling up sign spotting through sign language dictionaries
The focus of this work is $\textit{sign spotting}$ - given a video of an isolated sign, our task is to identify $\textit{whether}$ and $\textit{where}$ it has been signed in a continuous, co-articulated sign language video.
SpineNetV2: Automated Detection, Labelling and Radiological Grading Of Clinical MR Scans
This technical report presents SpineNetV2, an automated tool which: (i) detects and labels vertebral bodies in clinical spinal magnetic resonance (MR) scans across a range of commonly used sequences; and (ii) performs radiological grading of lumbar intervertebral discs in T2-weighted scans for a range of common degenerative changes.
Flamingo: a Visual Language Model for Few-Shot Learning
Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research.
Ranked #1 on
Action Recognition
on RareAct
Temporal Alignment Networks for Long-term Video
The objective of this paper is a temporal alignment network that ingests long term video sequences, and associated text sentences, in order to: (1) determine if a sentence is alignable with the video; and (2) if it is alignable, then determine its alignment.
Object discovery and representation networks
The promise of self-supervised learning (SSL) is to leverage large amounts of unlabeled data to solve complex tasks.
HiP: Hierarchical Perceiver
This however hinders them from scaling up to the inputs sizes required to process raw high-resolution images or video.
Generalized Category Discovery
Here, the unlabelled images may come from labelled classes or from novel ones.
Ranked #1 on
Open-World Semi-Supervised Learning
on CIFAR-10
(Seen accuracy (50% Labeled) metric)
Fine-Grained Visual Recognition
Open-World Semi-Supervised Learning
+1
Reading To Listen at the Cocktail Party: Multi-Modal Speech Separation
The goal of this paper is speech separation and enhancement in multi-speaker and noisy environments using a combination of different modalities.
Persistent Animal Identification Leveraging Non-Visual Markers
Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research.
Label, Verify, Correct: A Simple Few Shot Object Detection Method
The objective of this paper is few-shot object detection (FSOD) -- the task of expanding an object detector for a new category given only a few instances for training.
Audio-Visual Synchronisation in the wild
Finally, we set the first benchmark for general audio-visual synchronisation with over 160 diverse classes in the new VGG-Sound Sync video dataset.
Input-level Inductive Biases for 3D Reconstruction
Much of the recent progress in 3D vision has been driven by the development of specialized architectures that incorporate geometrical inductive biases.
It's About Time: Analog Clock Reading in the Wild
In this paper, we present a framework for reading analog clocks in natural images or videos.
BBC-Oxford British Sign Language Dataset
In this work, we introduce the BBC-Oxford British Sign Language (BOBSL) dataset, a large-scale video collection of British Sign Language (BSL).
With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition
We capitalise on the action's temporal context and propose a method that learns to attend to surrounding actions in order to improve recognition performance.
Visual Keyword Spotting with Attention
In this paper, we consider the task of spotting spoken keywords in silent video sequences -- also known as visual keyword spotting.
Ranked #1 on
Visual Keyword Spotting
on LRS2
Sub-word Level Lip Reading With Visual Attention
To this end, we make the following contributions: (1) we propose an attention-based pooling mechanism to aggregate visual speech representations; (2) we use sub-word units for lip reading for the first time and show that this allows us to better model the ambiguities of the task; (3) we propose a model for Visual Speech Detection (VSD), trained on top of the lip reading network.
Ranked #1 on
Visual Speech Recognition
on LRS2
(using extra training data)
Audio-Visual Active Speaker Detection
Automatic Speech Recognition
+5
Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
In this paper, we first demonstrate that the ability of a classifier to make the 'none-of-above' decision is highly correlated with its accuracy on the closed-set classes.
Ranked #10 on
Out-of-Distribution Detection
on CIFAR-100 vs CIFAR-10
PASS: An ImageNet replacement for self-supervised pretraining without humans
On the other hand, state-of-the-art pretraining is nowadays obtained with unsupervised methods, meaning that labelled datasets such as ImageNet may not be necessary, or perhaps not even optimal, for model pretraining.
Perceiver IO: A General Architecture for Structured Inputs & Outputs
A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible.
Ranked #1 on
Optical Flow Estimation
on KITTI 2015
(Average End-Point Error metric)
Self-Supervised Multi-Modal Alignment for Whole Body Medical Imaging
This paper explores the use of self-supervised deep learning in medical imaging in cases where two scan modalities are available for the same subject.
AutoNovel: Automatically Discovering and Learning Novel Visual Categories
We present a new approach called AutoNovel to address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labelled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use ranking statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.
Ranked #1 on
Novel Class Discovery
on SVHN
NeRF in detail: Learning to sample for view synthesis
In this work we address a clear limitation of the vanilla coarse-to-fine approach -- that it is based on a heuristic and not trained end-to-end for the task at hand.
Face, Body, Voice: Video Person-Clustering with Multiple Modalities
In this paper we make contributions to address both these deficiencies: first, we introduce a Multi-Modal High-Precision Clustering algorithm for person-clustering in videos using cues from several modalities (face, body, and voice).
Comment on Stochastic Polyak Step-Size: Performance of ALI-G
This is a short note on the performance of the ALI-G algorithm (Berrada et al., 2020) as reported in (Loizou et al., 2021).
Omnimatte: Associating Objects and Their Effects in Video
We show results on real-world videos containing interactions between different types of subjects (cars, animals, people) and complex effects, ranging from semi-transparent elements such as smoke and reflections, to fully opaque effects such as objects attached to the subject.
Aligning Subtitles in Sign Language Videos
The goal of this work is to temporally align asynchronous subtitles in sign language videos.
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53. 8% to 56. 5%.
Ranked #1 on
Image Classification
on PASCAL VOC 2007
Temporal Query Networks for Fine-grained Video Understanding
It attends to relevant segments for each query with a temporal attention mechanism, and can be trained using only the labels for each query.
Ranked #13 on
Action Recognition
on Diving-48
TEACHTEXT: CrossModal Generalized Distillation for Text-Video Retrieval
In recent years, considerable progress on the task of text-video retrieval has been achieved by leveraging large-scale pretraining on visual and audio datasets to construct powerful video encoders.
Self-supervised Video Object Segmentation by Motion Grouping
We additionally evaluate on a challenging camouflage dataset (MoCA), significantly outperforming the other self-supervised approaches, and comparing favourably to the top supervised approach, highlighting the importance of motion cues, and the potential bias towards visual appearance in existing video segmentation models.
Ranked #7 on
Unsupervised Object Segmentation
on DAVIS 2016
Localizing Visual Sounds the Hard Way
We show that our algorithm achieves state-of-the-art performance on the popular Flickr SoundNet dataset.
Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
Our objective in this work is video-text retrieval - in particular a joint embedding that enables efficient text-to-video retrieval.
Ranked #4 on
Video Retrieval
on QuerYD
(using extra training data)
Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers
We also extend our method to the video domain, improving the state of the art on the VATEX dataset.
Read and Attend: Temporal Localisation in Sign Language Videos
Our contributions are as follows: (1) we demonstrate the ability to leverage large quantities of continuous signing videos with weakly-aligned subtitles to localise signs in continuous sign language; (2) we employ the learned attention to automatically generate hundreds of thousands of annotations for a large sign vocabulary; (3) we collect a set of 37K manually verified sign instances across a vocabulary of 950 sign classes to support our study of sign language recognition; (4) by training on the newly annotated data from our method, we outperform the prior state of the art on the BSL-1K sign language recognition benchmark.
Broaden Your Views for Self-Supervised Video Learning
Most successful self-supervised learning methods are trained to align the representations of two independent views from the data.
Slow-Fast Auditory Streams For Audio Recognition
We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs.
Ranked #1 on
Human Interaction Recognition
on EPIC-SOUNDS
Perceiver: General Perception with Iterative Attention
The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models.
Ranked #35 on
3D Point Cloud Classification
on ModelNet40
(Mean Accuracy metric)
Automated Video Labelling: Identifying Faces by Corroborative Evidence
We present a method for automatically labelling all faces in video archives, such as TV broadcasts, by combining multiple evidence sources and multiple modalities (visual and audio).
LAEO-Net++: revisiting people Looking At Each Other in videos
For this purpose, we propose LAEO-Net++, a new deep CNN for determining LAEO in videos.
VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
We held the second installment of the VoxCeleb Speaker Recognition Challenge in conjunction with Interspeech 2020.
Betrayed by Motion: Camouflaged Object Discovery via Motion Segmentation
We make the following three contributions: (i) We propose a novel architecture that consists of two essential components for breaking camouflage, namely, a differentiable registration module to align consecutive frames based on the background, which effectively emphasises the object boundary in the difference image, and a motion segmentation module with memory that discovers the moving objects, while maintaining the object permanence even when motion is absent at some point.
QuerYD: A video dataset with high-quality text and audio narrations
We introduce QuerYD, a new large-scale dataset for retrieval and event localisation in video.
A Short Note on the Kinetics-700-2020 Human Action Dataset
We describe the 2020 edition of the DeepMind Kinetics human action dataset, which replenishes and extends the Kinetics-700 dataset.
Self-supervised Co-training for Video Representation Learning
The objective of this paper is visual-only self-supervised video representation learning.
Ranked #8 on
Self-Supervised Action Recognition Linear
on HMDB51
Watch, read and lookup: learning to spot signs from multiple supervisors
The focus of this work is sign spotting - given a video of an isolated sign, our task is to identify whether and where it has been signed in a continuous, co-articulated sign language video.
Layered Neural Rendering for Retiming People in Video
We present a method for retiming people in an ordinary, natural video -- manipulating and editing the time in which different motions of individuals in the video occur.
Adaptive Text Recognition through Visual Matching
In this work, our objective is to address the problems of generalization and flexibility for text recognition in documents.
Seeing wake words: Audio-visual Keyword Spotting
The goal of this work is to automatically determine whether and when a word of interest is spoken by a talking face, with or without the audio.
Inducing Predictive Uncertainty Estimation for Face Recognition
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.
Self-Supervised Learning of Audio-Visual Objects from Video
Our objective is to transform a video into a set of discrete audio-visual objects using self-supervised learning.
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
This report summarizes the results of the first edition of the challenge together with the findings of the participants.
RareAct: A video dataset of unusual interactions
This paper introduces a manually annotated video dataset of unusual actions, namely RareAct, including actions such as "blend phone", "cut keyboard" and "microwave shoes".
Memory-augmented Dense Predictive Coding for Video Representation Learning
The objective of this paper is self-supervised learning from video, in particular for representations for action recognition.
Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval
Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods.
Ranked #4 on
Vehicle Re-Identification
on VehicleID Medium
BSL-1K: Scaling up co-articulated sign language recognition using mouthing cues
Recent progress in fine-grained gesture and action classification, and machine translation, point to the possibility of automated sign language recognition becoming a reality.
Ranked #6 on
Sign Language Recognition
on WLASL-2000
CrossTransformers: spatially-aware few-shot transfer
In this work, we illustrate how the neural network representations which underpin modern vision systems are subject to supervision collapse, whereby they lose any information that is not necessary for performing the training task, including information that may be necessary for transfer to new tasks or domains.
Co-Attention for Conditioned Image Matching
We propose a new approach to determine correspondences between image pairs in the wild under large changes in illumination, viewpoint, context, and material.
A Convolutional Approach to Vertebrae Detection and Labelling in Whole Spine MRI
We propose a novel convolutional method for the detection and identification of vertebrae in whole spine MRIs.
Spot the conversation: speaker diarisation in the wild
Finally, we use this pipeline to create a large-scale diarisation dataset called VoxConverse, collected from 'in the wild' videos, which we will release publicly to the research community.
Self-Supervised MultiModal Versatile Networks
In particular, we explore how best to combine the modalities, such that fine-grained representations of the visual and audio modalities can be maintained, whilst also integrating text into a common embedding.
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild
We present an approach for estimating the period with which an action is repeated in a video.
Ranked #1 on
Repetitive Action Counting
on Countix
LSD-C: Linearly Separable Deep Clusters
We present LSD-C, a novel method to identify clusters in an unlabeled dataset.
Condensed Movies: Story Based Retrieval with Contextual Embeddings
Our objective in this work is long range understanding of the narrative structure of movies.
The AVA-Kinetics Localized Human Actions Video Dataset
The dataset is collected by annotating videos from the Kinetics-700 dataset using the AVA annotation protocol, and extending the original AVA dataset with these new AVA annotated Kinetics clips.
VGGSound: A Large-scale Audio-Visual Dataset
Our goal is to collect a large-scale audio-visual dataset with low label noise from videos in the wild using computer vision techniques.
Monocular Depth Estimation with Self-supervised Instance Adaptation
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision.
Speech2Action: Cross-modal Supervision for Action Recognition
We train a BERT-based Speech2Action classifier on over a thousand movie screenplays, to predict action labels from transcribed speech segments.
Compact Deep Aggregation for Set Retrieval
The objective of this work is to learn a compact embedding of a set of descriptors that is suitable for efficient retrieval and ranking, whilst maintaining discriminability of the individual descriptors.
Visual Grounding in Video for Unsupervised Word Translation
Given this shared embedding we demonstrate that (i) we can map words between the languages, particularly the 'visual' words; (ii) that the shared embedding provides a good initialization for existing unsupervised text-based word translation techniques, forming the basis for our proposed hybrid visual-text mapping algorithm, MUVE; and (iii) our approach achieves superior performance by addressing the shortcomings of text-based methods -- it is more robust, handles datasets with less commonality, and is applicable to low-resource languages.
Disentangled Speech Embeddings using Cross-modal Self-supervision
The objective of this paper is to learn representations of speaker identity without access to manually annotated data.
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
In this work we address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labeled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use rank statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.
End-to-End Learning of Visual Representations from Uncurated Instructional Videos
Annotating videos is cumbersome, expensive and not scalable.
Ranked #3 on
Action Recognition
on RareAct
Synthetic Humans for Action Recognition from Unseen Viewpoints
Although synthetic training data has been shown to be beneficial for tasks such as human pose estimation, its use for RGB human action recognition is relatively unexplored.
VoxSRC 2019: The first VoxCeleb Speaker Recognition Challenge
The VoxCeleb Speaker Recognition Challenge 2019 aimed to assess how well current speaker recognition technology is able to identify speakers in unconstrained or `in the wild' data.
ASR is all you need: cross-modal distillation for lip reading
The goal of this work is to train strong models for visual speech recognition without requiring human annotated ground truth data.
Ranked #19 on
Lipreading
on LRS3-TED
(using extra training data)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Self-supervised learning of class embeddings from video
This work explores how to use self-supervised learning on videos to learn a class-specific image embedding that encodes pose and shape information.
Controllable Attention for Structured Layered Video Decomposition
The objective of this paper is to be able to separate a video into its natural layers, and to control which of the separated layers to attend to.
Count, Crop and Recognise: Fine-Grained Recognition in the Wild
The goal of this paper is to label all the animal individuals present in every frame of a video.
Video Representation Learning by Dense Predictive Coding
The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition.
Ranked #10 on
Self-Supervised Action Recognition Linear
on UCF101
Representation Learning
Self-Supervised Action Recognition
+3
Geometry-Aware Video Object Detection for Static Cameras
In this paper we propose a geometry-aware model for video object detection.
Learning to Discover Novel Visual Categories via Deep Transfer Clustering
The second contribution is a method to estimate the number of classes in the unlabelled data.
