Michael Wray

Kristen Grauman, Andrew Westbury, Lorenzo Torresani et al. · cmu, gatech

We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge. Ego-Exo4D centers around simultaneously-captured egocentric and exocentric video of skilled human activities (e.g., sports, music, dance, bike repair). 740 participants from 13 cities worldwide performed these activities in 123 different natural scene contexts, yielding long-form captures from 1 to 42 minutes each and 1,286 hours of video combined. The multimodal nature of the dataset is unprecedented: the video is accompanied by multichannel audio, eye gaze, 3D point clouds, camera poses, IMU, and multiple paired language descriptions -- including a novel "expert commentary" done by coaches and teachers and tailored to the skilled-activity domain. To push the frontier of first-person video understanding of skilled human activity, we also present a suite of benchmark tasks and their annotations, including fine-grained activity understanding, proficiency estimation, cross-view translation, and 3D hand/body pose. All resources are open sourced to fuel new research in the community. Project page: http://ego-exo4d-data.org/

Kevin Qinghong Lin, Alex Jinpeng Wang, Mattia Soldan et al. · microsoft-research, uw

Video-Language Pretraining (VLP), which aims to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention. Best performing works rely on large-scale, 3rd-person video-text datasets, such as HowTo100M. In this work, we exploit the recently released Ego4D dataset to pioneer Egocentric VLP along three directions. (i) We create EgoClip, a 1st-person video-text pretraining dataset comprising 3.8M clip-text pairs well-chosen from Ego4D, covering a large variety of human daily activities. (ii) We propose a novel pretraining objective, dubbed EgoNCE, which adapts video-text contrastive learning to the egocentric domain by mining egocentric-aware positive and negative samples. (iii) We introduce EgoMCQ, a development benchmark that is close to EgoClip and hence can support effective validation and fast exploration of our design decisions in EgoClip and EgoNCE. Furthermore, we demonstrate strong performance on five egocentric downstream tasks across three datasets: video-text retrieval on EPIC-KITCHENS-100; action recognition on Charades-Ego; natural language query, moment query, and object state change classification on Ego4D challenge benchmarks. The dataset and code are available at https://github.com/showlab/EgoVLP.

Kevin Qinghong Lin, Alex Jinpeng Wang, Mattia Soldan et al. · microsoft-research, uw

In this report, we propose a video-language pretraining (VLP) based solution \cite{kevin2022egovlp} for four Ego4D challenge tasks, including Natural Language Query (NLQ), Moment Query (MQ), Object State Change Classification (OSCC), and PNR Localization (PNR). Especially, we exploit the recently released Ego4D dataset \cite{grauman2021ego4d} to pioneer Egocentric VLP from pretraining dataset, pretraining objective, and development set. Based on the above three designs, we develop a pretrained video-language model that is able to transfer its egocentric video-text representation or video-only representation to several video downstream tasks. Our Egocentric VLP achieves 10.46R@1&IoU @0.3 on NLQ, 10.33 mAP on MQ, 74% Acc on OSCC, 0.67 sec error on PNR. The code is available at https://github.com/showlab/EgoVLP.

Kevin Flanagan, Dima Damen, Michael Wray

The onset of long-form egocentric datasets such as Ego4D and EPIC-Kitchens presents a new challenge for the task of Temporal Sentence Grounding (TSG). Compared to traditional benchmarks on which this task is evaluated, these datasets offer finer-grained sentences to ground in notably longer videos. In this paper, we develop an approach for learning to ground sentences in these datasets using only narrations and their corresponding rough narration timestamps. We propose to artificially merge clips to train for temporal grounding in a contrastive manner using text-conditioning attention. This Clip Merging (CliMer) approach is shown to be effective when compared with a high performing TSG method -- e.g. mean R@1 improves from 3.9 to 5.7 on Ego4D and from 10.7 to 13.0 on EPIC-Kitchens. Code and data splits available from: https://github.com/keflanagan/CliMer

Adriano Fragomeni, Michael Wray, Dima Damen

In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video segments) can be used to improve the retrieval performance. We propose Context Transformer (ConTra); an encoder architecture that models the interaction between a video clip and its local temporal context in order to enhance its embedded representations. Importantly, we supervise the context transformer using contrastive losses in the cross-modal embedding space. We explore context transformers for video and text modalities. Results consistently demonstrate improved performance on three datasets: YouCook2, EPIC-KITCHENS and a clip-sentence version of ActivityNet Captions. Exhaustive ablation studies and context analysis show the efficacy of the proposed method.

David Pujol-Perich, Albert Clapés, Dima Damen et al.

In this work, we investigate the degradation of existing VMR methods, particularly of DETR architectures, when trained on caption-based queries but evaluated on search queries. For this, we introduce three benchmarks by modifying the textual queries in three public VMR datasets -- i.e., HD-EPIC, YouCook2 and ActivityNet-Captions. Our analysis reveals two key generalization challenges: (i) A language gap, arising from the linguistic under-specification of search queries, and (ii) a multi-moment gap, caused by the shift from single-moment to multi-moment queries. We also identify a critical issue in these architectures -- an active decoder-query collapse -- as a primary cause of the poor generalization to multi-moment instances. We mitigate this issue with architectural modifications that effectively increase the number of active decoder queries. Extensive experiments demonstrate that our approach improves performance on search queries by up to 14.82% mAP_m, and up to 21.83% mAP_m on multi-moment search queries. The code, models and data are available in the project webpage: https://davidpujol.github.io/beyond-vmr/

Tomáš Souček, Prajwal Gatti, Michael Wray et al.

The goal of this work is to generate step-by-step visual instructions in the form of a sequence of images, given an input image that provides the scene context and the sequence of textual instructions. This is a challenging problem as it requires generating multi-step image sequences to achieve a complex goal while being grounded in a specific environment. Part of the challenge stems from the lack of large-scale training data for this problem. The contribution of this work is thus three-fold. First, we introduce an automatic approach for collecting large step-by-step visual instruction training data from instructional videos. We apply this approach to one million videos and create a large-scale, high-quality dataset of 0.6M sequences of image-text pairs. Second, we develop and train ShowHowTo, a video diffusion model capable of generating step-by-step visual instructions consistent with the provided input image. Third, we evaluate the generated image sequences across three dimensions of accuracy (step, scene, and task) and show our model achieves state-of-the-art results on all of them. Our code, dataset, and trained models are publicly available.

Wiktor Mucha, Michael Wray, Martin Kampel

Hand pose represents key information for action recognition in the egocentric perspective, where the user is interacting with objects. We propose to improve egocentric 3D hand pose estimation based on RGB frames only by using pseudo-depth images. Incorporating state-of-the-art single RGB image depth estimation techniques, we generate pseudo-depth representations of the frames and use distance knowledge to segment irrelevant parts of the scene. The resulting depth maps are then used as segmentation masks for the RGB frames. Experimental results on H2O Dataset confirm the high accuracy of the estimated pose with our method in an action recognition task. The 3D hand pose, together with information from object detection, is processed by a transformer-based action recognition network, resulting in an accuracy of 91.73%, outperforming all state-of-the-art methods. Estimations of 3D hand pose result in competitive performance with existing methods with a mean pose error of 28.66 mm. This method opens up new possibilities for employing distance information in egocentric 3D hand pose estimation without relying on depth sensors.

Kevin Flanagan, Dima Damen, Michael Wray

Video Moment Retrieval is a common task to evaluate the performance of visual-language models - it involves localising start and end times of moments in videos from query sentences. The current task formulation assumes that the queried moment is present in the video, resulting in false positive moment predictions when irrelevant query sentences are provided. In this paper we propose the task of Negative-Aware Video Moment Retrieval (NA-VMR), which considers both moment retrieval accuracy and negative query rejection accuracy. We make the distinction between In-Domain and Out-of-Domain negative queries and provide new evaluation benchmarks for two popular video moment retrieval datasets: QVHighlights and Charades-STA. We analyse the ability of current SOTA video moment retrieval approaches to adapt to Negative-Aware Video Moment Retrieval and propose UniVTG-NA, an adaptation of UniVTG designed to tackle NA-VMR. UniVTG-NA achieves high negative rejection accuracy (avg. $98.4\%$) scores while retaining moment retrieval scores to within $3.87\%$ Recall@1. Dataset splits and code are available at https://github.com/keflanagan/MomentofUntruth

Sam Pollard, Michael Wray

Video transformer models require huge amounts of compute resources due to the spatio-temporal scaling of the input. Tackling this, recent methods have proposed to drop or merge tokens for image models, whether randomly or via learned methods. Merging tokens has many benefits: it can be plugged into any vision transformer, does not require model re-training, and it propagates information that would otherwise be dropped through the model. Before now, video token merging has not been evaluated on temporally complex datasets for video understanding. In this work, we explore training-free token merging for video to provide comprehensive experiments and find best practices across four video transformers on three datasets that exhibit coarse and fine-grained action recognition. Our results showcase the benefits of video token merging with a speedup of around $2.5$X while maintaining accuracy (avg. $-0.55\%$ for ViViT). Code available at https://github.com/sjpollard/video-how-do-your-tokens-merge.

Shijia Feng, Michael Wray, Walterio Mayol-Cuevas

Understanding human skill performance is essential for intelligent assistive systems, with struggle recognition offering a natural cue for identifying user difficulties. While prior work focuses on offline struggle classification and localization, real-time applications require models capable of detecting and anticipating struggle online. We reformulate struggle localization as an online detection task and further extend it to anticipation, predicting struggle moments before they occur. We adapt two off-the-shelf models as baselines for online struggle detection and anticipation. Online struggle detection achieves 70-80% per-frame mAP, while struggle anticipation up to 2 seconds ahead yields comparable performance with slight drops. We further examine generalization across tasks and activities and analyse the impact of skill evolution. Despite larger domain gaps in activity-level generalization, models still outperform random baselines by 4-20%. Our feature-based models run at up to 143 FPS, and the whole pipeline, including feature extraction, operates at around 20 FPS, sufficient for real-time assistive applications.

Sam Pollard, Michael Wray

As we become increasingly dependent on vision language models (VLMs) to answer questions about the world around us, there is a significant amount of research devoted to increasing both the difficulty of video question answering (VQA) datasets, and the context lengths of the models that they evaluate. The reliance on large language models as backbones has lead to concerns about potential text dominance, and the exploration of interactions between modalities is underdeveloped. How do we measure whether we're heading in the right direction, with the complexity that multi-modal models introduce? We propose a joint method of computing both feature attributions and modality scores based on Shapley values, where both the features and modalities are arbitrarily definable. Using these metrics, we compare $6$ VLM models of varying context lengths on $4$ representative datasets, focusing on multiple-choice VQA. In particular, we consider video frames and whole textual elements as equal features in the hierarchy, and the multiple-choice VQA task as an interaction between three modalities: video, question and answer. Our results demonstrate a dependence on text and show that the multiple-choice VQA task devolves into a model's ability to ignore distractors. Code available at https://github.com/sjpollard/a-video-is-not-worth-a-thousand-words.

Shijia Feng, Michael Wray, Walterio Mayol-Cuevas

The ability to determine when a person struggles during skill acquisition is crucial for both optimizing human learning and enabling the development of effective assistive systems. As skills develop, the type and frequency of struggles tend to change, and understanding this evolution is key to determining the user's current stage of learning. However, existing manipulation datasets have not focused on how struggle evolves over time. In this work, we collect a dataset for struggle determination, featuring 61.68 hours of video recordings, 2,793 videos, and 5,385 annotated temporal struggle segments collected from 76 participants. The dataset includes 18 tasks grouped into four diverse activities -- tying knots, origami, tangram puzzles, and shuffling cards, representing different task variations. In addition, participants repeated the same task five times to capture their evolution of skill. We define the struggle determination problem as a temporal action localization task, focusing on identifying and precisely localizing struggle segments with start and end times. Experimental results show that Temporal Action Localization models can successfully learn to detect struggle cues, even when evaluated on unseen tasks or activities. The models attain an overall average mAP of 34.56% when generalizing across tasks and 19.24% across activities, indicating that struggle is a transferable concept across various skill-based tasks while still posing challenges for further improvement in struggle detection. Our dataset is available at https://github.com/FELIXFENG2019/EvoStruggle.

Beth Pearson, Bilal Boulbarss, Michael Wray et al.

A fundamental aspect of the semantics of natural language is that novel meanings can be formed from the composition of previously known parts. Vision-language models (VLMs) have made significant progress in recent years, however, there is evidence that they are unable to perform this kind of composition. For example, given an image of a red cube and a blue cylinder, a VLM such as CLIP is likely to incorrectly label the image as a red cylinder or a blue cube, indicating it represents the image as a `bag-of-words' and fails to capture compositional semantics. Diffusion models have recently gained significant attention for their impressive generative abilities, and zero-shot classifiers based on diffusion models have been shown to perform competitively with CLIP in certain compositional tasks. In this work we explore whether the generative Diffusion Classifier has improved compositional generalisation abilities compared to discriminative models. We assess three models -- Diffusion Classifier, CLIP, and ViLT -- on their ability to bind objects with attributes and relations in both zero-shot learning (ZSL) and generalised zero-shot learning (GZSL) settings. Our results show that the Diffusion Classifier and ViLT perform well at concept binding tasks, but that all models struggle significantly with the relational GZSL task, underscoring the broader challenges VLMs face with relational reasoning. Analysis of CLIP embeddings suggests that the difficulty may stem from overly similar representations of relational concepts such as left and right. Code and dataset are available at: https://github.com/otmive/diffusion_classifier_clip

Tomáš Souček, Dima Damen, Michael Wray et al.

We address the task of generating temporally consistent and physically plausible images of actions and object state transformations. Given an input image and a text prompt describing the targeted transformation, our generated images preserve the environment and transform objects in the initial image. Our contributions are threefold. First, we leverage a large body of instructional videos and automatically mine a dataset of triplets of consecutive frames corresponding to initial object states, actions, and resulting object transformations. Second, equipped with this data, we develop and train a conditioned diffusion model dubbed GenHowTo. Third, we evaluate GenHowTo on a variety of objects and actions and show superior performance compared to existing methods. In particular, we introduce a quantitative evaluation where GenHowTo achieves 88% and 74% on seen and unseen interaction categories, respectively, outperforming prior work by a large margin.

Toby Perrett, Ahmad Darkhalil, Saptarshi Sinha et al.

We present a validation dataset of newly-collected kitchen-based egocentric videos, manually annotated with highly detailed and interconnected ground-truth labels covering: recipe steps, fine-grained actions, ingredients with nutritional values, moving objects, and audio annotations. Importantly, all annotations are grounded in 3D through digital twinning of the scene, fixtures, object locations, and primed with gaze. Footage is collected from unscripted recordings in diverse home environments, making HDEPIC the first dataset collected in-the-wild but with detailed annotations matching those in controlled lab environments. We show the potential of our highly-detailed annotations through a challenging VQA benchmark of 26K questions assessing the capability to recognise recipes, ingredients, nutrition, fine-grained actions, 3D perception, object motion, and gaze direction. The powerful long-context Gemini Pro only achieves 38.5% on this benchmark, showcasing its difficulty and highlighting shortcomings in current VLMs. We additionally assess action recognition, sound recognition, and long-term video-object segmentation on HD-EPIC. HD-EPIC is 41 hours of video in 9 kitchens with digital twins of 413 kitchen fixtures, capturing 69 recipes, 59K fine-grained actions, 51K audio events, 20K object movements and 37K object masks lifted to 3D. On average, we have 263 annotations per minute of our unscripted videos.

Siddhant Bansal, Michael Wray, Dima Damen

Large Vision Language Models (VLMs) are now the de facto state-of-the-art for a number of tasks including visual question answering, recognising objects, and spatial referral. In this work, we propose the HOI-Ref task for egocentric images that aims to understand interactions between hands and objects using VLMs. To enable HOI-Ref, we curate the HOI-QA dataset that consists of 3.9M question-answer pairs for training and evaluating VLMs. HOI-QA includes questions relating to locating hands, objects, and critically their interactions (e.g. referring to the object being manipulated by the hand). We train the first VLM for HOI-Ref on this dataset and call it VLM4HOI. Our results demonstrate that VLMs trained for referral on third person images fail to recognise and refer hands and objects in egocentric images. When fine-tuned on our egocentric HOI-QA dataset, performance improves by 27.9% for referring hands and objects, and by 26.7% for referring interactions.

Shijia Feng, Michael Wray, Brian Sullivan et al.

Determining when people are struggling allows for a finer-grained understanding of actions that complements conventional action classification and error detection. Struggle detection, as defined in this paper, is a distinct and important task that can be identified without explicit step or activity knowledge. We introduce the first struggle dataset with three real-world problem-solving activities that are labelled by both expert and crowd-source annotators. Video segments were scored w.r.t. their level of struggle using a forced choice 4-point scale. This dataset contains 5.1 hours of video from 73 participants. We conducted a series of experiments to identify the most suitable modelling approaches for struggle determination. Additionally, we compared various deep learning models, establishing baseline results for struggle classification, struggle regression, and struggle label distribution learning. Our results indicate that struggle detection in video can achieve up to $88.24\%$ accuracy in binary classification, while detecting the level of struggle in a four-way classification setting performs lower, with an overall accuracy of $52.45\%$. Our work is motivated toward a more comprehensive understanding of action in video and potentially the improvement of assistive systems that analyse struggle and can better support users during manual activities.

Adriano Fragomeni, Dima Damen, Michael Wray

Video retrieval requires aligning visual content with corresponding natural language descriptions. In this paper, we introduce Modality Auxiliary Concepts for Video Retrieval (MAC-VR), a novel approach that leverages modality-specific tags -- automatically extracted from foundation models -- to enhance video retrieval. We propose to align modalities in a latent space, along with learning and aligning auxiliary latent concepts derived from the features of a video and its corresponding caption. We introduce these auxiliary concepts to improve the alignment of visual and textual latent concepts, allowing concepts to be distinguished from one another. We conduct extensive experiments on six diverse datasets: two different splits of MSR-VTT, DiDeMo, TGIF, Charades and YouCook2. The experimental results consistently demonstrate that modality-specific tags improve cross-modal alignment, outperforming current state-of-the-art methods across three datasets and performing comparably or better across others. Project Webpage: https://adrianofragomeni.github.io/MAC-VR/

Bin Zhu, Kevin Flanagan, Adriano Fragomeni et al.

Though pre-training vision-language models have demonstrated significant benefits in boosting video-text retrieval performance from large-scale web videos, fine-tuning still plays a critical role with manually annotated clips with start and end times, which requires considerable human effort. To address this issue, we explore an alternative cheaper source of annotations, single timestamps, for video-text retrieval. We initialise clips from timestamps in a heuristic way to warm up a retrieval model. Then a video clip editing method is proposed to refine the initial rough boundaries to improve retrieval performance. A student-teacher network is introduced for video clip editing. The teacher model is employed to edit the clips in the training set whereas the student model trains on the edited clips. The teacher weights are updated from the student's after the student's performance increases. Our method is model agnostic and applicable to any retrieval models. We conduct experiments based on three state-of-the-art retrieval models, COOT, VideoCLIP and CLIP4Clip. Experiments conducted on three video retrieval datasets, YouCook2, DiDeMo and ActivityNet-Captions show that our edited clips consistently improve retrieval performance over initial clips across all the three retrieval models.

Adriano Fragomeni, Dima Damen, Michael Wray

Text-to-Video (T2V) retrieval aims to identify the most relevant item from a gallery of videos based on a user's text query. Traditional methods rely solely on aligning video and text modalities to compute the similarity and retrieve relevant items. However, recent advancements emphasise incorporating auxiliary information extracted from video and text modalities to improve retrieval performance and bridge the semantic gap between these modalities. Auxiliary information can include visual attributes, such as objects; temporal and spatial context; and textual descriptions, such as speech and rephrased captions. This survey comprehensively reviews 81 research papers on Text-to-Video retrieval that utilise such auxiliary information. It provides a detailed analysis of their methodologies; highlights state-of-the-art results on benchmark datasets; and discusses available datasets and their auxiliary information. Additionally, it proposes promising directions for future research, focusing on different ways to further enhance retrieval performance using this information.

Jonathan Munro, Michael Wray, Diane Larlus et al.

Given a gallery of uncaptioned video sequences, this paper considers the task of retrieving videos based on their relevance to an unseen text query. To compensate for the lack of annotations, we rely instead on a related video gallery composed of video-caption pairs, termed the source gallery, albeit with a domain gap between its videos and those in the target gallery. We thus introduce the problem of Unsupervised Domain Adaptation for Cross-modal Video Retrieval, along with a new benchmark on fine-grained actions. We propose a novel iterative domain alignment method by means of pseudo-labelling target videos and cross-domain (i.e. source-target) ranking. Our approach adapts the embedding space to the target gallery, consistently outperforming source-only as well as marginal and conditional alignment methods.

Kristen Grauman, Andrew Westbury, Eugene Byrne et al.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

Michael Wray, Hazel Doughty, Dima Damen

Current video retrieval efforts all found their evaluation on an instance-based assumption, that only a single caption is relevant to a query video and vice versa. We demonstrate that this assumption results in performance comparisons often not indicative of models' retrieval capabilities. We propose a move to semantic similarity video retrieval, where (i) multiple videos/captions can be deemed equally relevant, and their relative ranking does not affect a method's reported performance and (ii) retrieved videos/captions are ranked by their similarity to a query. We propose several proxies to estimate semantic similarities in large-scale retrieval datasets, without additional annotations. Our analysis is performed on three commonly used video retrieval datasets (MSR-VTT, YouCook2 and EPIC-KITCHENS).

Dima Damen, Michael Wray

We propose a three-dimensional discrete and incremental scale to encode a method's level of supervision - i.e. the data and labels used when training a model to achieve a given performance. We capture three aspects of supervision, that are known to give methods an advantage while requiring additional costs: pre-training, training labels and training data. The proposed three-dimensional scale can be included in result tables or leaderboards to handily compare methods not only by their performance, but also by the level of data supervision utilised by each method. The Supervision Levels Scale (SLS) is first presented generally fo any task/dataset/challenge. It is then applied to the EPIC-KITCHENS-100 dataset, to be used for the various leaderboards and challenges associated with this dataset.

Dima Damen, Hazel Doughty, Giovanni Maria Farinella et al.

This paper introduces the pipeline to extend the largest dataset in egocentric vision, EPIC-KITCHENS. The effort culminates in EPIC-KITCHENS-100, a collection of 100 hours, 20M frames, 90K actions in 700 variable-length videos, capturing long-term unscripted activities in 45 environments, using head-mounted cameras. Compared to its previous version, EPIC-KITCHENS-100 has been annotated using a novel pipeline that allows denser (54% more actions per minute) and more complete annotations of fine-grained actions (+128% more action segments). This collection enables new challenges such as action detection and evaluating the "test of time" - i.e. whether models trained on data collected in 2018 can generalise to new footage collected two years later. The dataset is aligned with 6 challenges: action recognition (full and weak supervision), action detection, action anticipation, cross-modal retrieval (from captions), as well as unsupervised domain adaptation for action recognition. For each challenge, we define the task, provide baselines and evaluation metrics

Dima Damen, Hazel Doughty, Giovanni Maria Farinella et al.

Since its introduction in 2018, EPIC-KITCHENS has attracted attention as the largest egocentric video benchmark, offering a unique viewpoint on people's interaction with objects, their attention, and even intention. In this paper, we detail how this large-scale dataset was captured by 32 participants in their native kitchen environments, and densely annotated with actions and object interactions. Our videos depict nonscripted daily activities, as recording is started every time a participant entered their kitchen. Recording took place in 4 countries by participants belonging to 10 different nationalities, resulting in highly diverse kitchen habits and cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labelled for a total of 39.6K action segments and 454.2K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos after recording, thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and. anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens. We introduce new baselines that highlight the multimodal nature of the dataset and the importance of explicit temporal modelling to discriminate fine-grained actions e.g. 'closing a tap' from 'opening' it up.

Michael Wray, Diane Larlus, Gabriela Csurka et al.

We address the problem of cross-modal fine-grained action retrieval between text and video. Cross-modal retrieval is commonly achieved through learning a shared embedding space, that can indifferently embed modalities. In this paper, we propose to enrich the embedding by disentangling parts-of-speech (PoS) in the accompanying captions. We build a separate multi-modal embedding space for each PoS tag. The outputs of multiple PoS embeddings are then used as input to an integrated multi-modal space, where we perform action retrieval. All embeddings are trained jointly through a combination of PoS-aware and PoS-agnostic losses. Our proposal enables learning specialised embedding spaces that offer multiple views of the same embedded entities. We report the first retrieval results on fine-grained actions for the large-scale EPIC dataset, in a generalised zero-shot setting. Results show the advantage of our approach for both video-to-text and text-to-video action retrieval. We also demonstrate the benefit of disentangling the PoS for the generic task of cross-modal video retrieval on the MSR-VTT dataset.

Michael Wray, Dima Damen

This work introduces verb-only representations for both recognition and retrieval of visual actions, in video. Current methods neglect legitimate semantic ambiguities between verbs, instead choosing unambiguous subsets of verbs along with objects to disambiguate the actions. We instead propose multiple verb-only labels, which we learn through hard or soft assignment as a regression. This enables learning a much larger vocabulary of verbs, including contextual overlaps of these verbs. We collect multi-verb annotations for three action video datasets and evaluate the verb-only labelling representations for action recognition and cross-modal retrieval (video-to-text and text-to-video). We demonstrate that multi-label verb-only representations outperform conventional single verb labels. We also explore other benefits of a multi-verb representation including cross-dataset retrieval and verb type manner and result verb types) retrieval.

Michael Wray, Davide Moltisanti, Dima Damen

This work introduces verb-only representations for actions and interactions; the problem of describing similar motions (e.g. 'open door', 'open cupboard'), and distinguish differing ones (e.g. 'open door' vs 'open bottle') using verb-only labels. Current approaches for action recognition neglect legitimate semantic ambiguities and class overlaps between verbs (Fig. 1), relying on the objects to disambiguate interactions. We deviate from single-verb labels and introduce a mapping between observations and multiple verb labels - in order to create an Unequivocal Representation of Actions. The new representation benefits from increased vocabulary and a soft assignment to an enriched space of verb labels. We learn these representations as multi-output regression, using a two-stream fusion CNN. The proposed approach outperforms conventional single-verb labels (also known as majority voting) on three egocentric datasets for both recognition and retrieval.

Dima Damen, Hazel Doughty, Giovanni Maria Farinella et al.

First-person vision is gaining interest as it offers a unique viewpoint on people's interaction with objects, their attention, and even intention. However, progress in this challenging domain has been relatively slow due to the lack of sufficiently large datasets. In this paper, we introduce EPIC-KITCHENS, a large-scale egocentric video benchmark recorded by 32 participants in their native kitchen environments. Our videos depict nonscripted daily activities: we simply asked each participant to start recording every time they entered their kitchen. Recording took place in 4 cities (in North America and Europe) by participants belonging to 10 different nationalities, resulting in highly diverse cooking styles. Our dataset features 55 hours of video consisting of 11.5M frames, which we densely labeled for a total of 39.6K action segments and 454.3K object bounding boxes. Our annotation is unique in that we had the participants narrate their own videos (after recording), thus reflecting true intention, and we crowd-sourced ground-truths based on these. We describe our object, action and anticipation challenges, and evaluate several baselines over two test splits, seen and unseen kitchens. Dataset and Project page: http://epic-kitchens.github.io

Davide Moltisanti, Michael Wray, Walterio Mayol-Cuevas et al.

Manual annotations of temporal bounds for object interactions (i.e. start and end times) are typical training input to recognition, localization and detection algorithms. For three publicly available egocentric datasets, we uncover inconsistencies in ground truth temporal bounds within and across annotators and datasets. We systematically assess the robustness of state-of-the-art approaches to changes in labeled temporal bounds, for object interaction recognition. As boundaries are trespassed, a drop of up to 10% is observed for both Improved Dense Trajectories and Two-Stream Convolutional Neural Network. We demonstrate that such disagreement stems from a limited understanding of the distinct phases of an action, and propose annotating based on the Rubicon Boundaries, inspired by a similarly named cognitive model, for consistent temporal bounds of object interactions. Evaluated on a public dataset, we report a 4% increase in overall accuracy, and an increase in accuracy for 55% of classes when Rubicon Boundaries are used for temporal annotations.

Michael Wray, Davide Moltisanti, Walterio Mayol-Cuevas et al.

This work deviates from easy-to-define class boundaries for object interactions. For the task of object interaction recognition, often captured using an egocentric view, we show that semantic ambiguities in verbs and recognising sub-interactions along with concurrent interactions result in legitimate class overlaps (Figure 1). We thus aim to model the mapping between observations and interaction classes, as well as class overlaps, towards a probabilistic multi-label classifier that emulates human annotators. Given a video segment containing an object interaction, we model the probability for a verb, out of a list of possible verbs, to be used to annotate that interaction. The proba- bility is learnt from crowdsourced annotations, and is tested on two public datasets, comprising 1405 video sequences for which we provide annotations on 90 verbs. We outper- form conventional single-label classification by 11% and 6% on the two datasets respectively, and show that learning from annotation probabilities outperforms majority voting and enables discovery of co-occurring labels.

Michael Wray, Davide Moltisanti, Walterio Mayol-Cuevas et al.

We present SEMBED, an approach for embedding an egocentric object interaction video in a semantic-visual graph to estimate the probability distribution over its potential semantic labels. When object interactions are annotated using unbounded choice of verbs, we embrace the wealth and ambiguity of these labels by capturing the semantic relationships as well as the visual similarities over motion and appearance features. We show how SEMBED can interpret a challenging dataset of 1225 freely annotated egocentric videos, outperforming SVM classification by more than 5%.