We propose a novel approach for captioning and object grounding in video, where the objects in the caption are grounded in the video via temporally dense bounding boxes. We introduce the following contributions. First, we present a large-scale automatic annotation method that aggregates frame-level captions grounded with bounding boxes into temporally dense and consistent annotations. We apply this approach on the HowTo100M dataset to construct a large-scale pre-training dataset, named HowToGround1M. We also introduce a Grounded Video Caption Generation model, dubbed GROVE, and pre-train the model on HowToGround1M. Second, we introduce iGround--a dataset of 3513 videos with manually annotated captions and dense spatio-temporally grounded bounding boxes. This allows us to measure progress on this challenging problem, as well as to fine-tune our model on this small-scale but high-quality data. Third, we demonstrate that our approach achieves state-of-the-art results on the proposed iGround dataset, as well as on the VidSTG, ActivityNet-Entities, GroundingYouTube, and YouCook-Interactions datasets. Our ablations demonstrate the importance of pre-training on our automatically annotated HowToGround1M dataset followed by fine-tuning on the manually annotated iGround dataset and validate the key technical contributions of our model. The dataset and code are available at https://ekazakos.github.io/grounded_video_caption_generation/.

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. We propose an annotation pipeline where annotators temporally label distinguishable audio segments and describe the action that could have caused this sound. We identify actions that can be discriminated purely from audio, through grouping these free-form descriptions of audio into classes. For actions that involve objects colliding, we collect human annotations of the materials of these objects (e.g., a glass object being placed on a wooden surface), which we verify from video, discarding ambiguities. Overall, EPIC-SOUNDS includes 78.4 k categorised segments of audible events and actions, distributed across 44 classes as well as 39.2 k non-categorised segments. We train and evaluate state-of-the-art audio recognition and detection models on our dataset, for both audio-only and audio-visual methods. We also conduct analysis on: the temporal overlap between audio events, the temporal and label correlations between audio and visual modalities, the ambiguities in annotating materials from audio-only input, the importance of audio-only labels and the limitations of current models to understand actions that sound.

Diverse actions give rise to rich audio-visual signals in long videos. Recent works showcase that the two modalities of audio and video exhibit different temporal extents of events and distinct labels. We address the interplay between the two modalities in long videos by explicitly modelling the temporal extents of audio and visual events. We propose the Time Interval Machine (TIM) where a modality-specific time interval poses as a query to a transformer encoder that ingests a long video input. The encoder then attends to the specified interval, as well as the surrounding context in both modalities, in order to recognise the ongoing action. We test TIM on three long audio-visual video datasets: EPIC-KITCHENS, Perception Test, and AVE, reporting state-of-the-art (SOTA) for recognition. On EPIC-KITCHENS, we beat previous SOTA that utilises LLMs and significantly larger pre-training by 2.9% top-1 action recognition accuracy. Additionally, we show that TIM can be adapted for action detection, using dense multi-scale inter-val queries, outperforming SOTA on EPIC-KITCHENS-IOO for most metrics, and showing strong performance on the Perception Test. Our ablations show the critical role of in-tegrating the two modalities and modelling their time inter-vals in achieving this performance. Code and models at: https://github.com/JacobChalk/TIM.

Hai Pham, Isma Hadji, Xinnuo Xu, Ziedune Degutyte, Jay Rainey, Evangelos Kazakos, Afsaneh Fazly, Georgios Tzimiropoulos, Brais Martinez. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

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 from EPIC-KITCHENS-100. We propose an annotation pipeline where annotators temporally label distinguishable audio segments and describe the action that could have caused this sound. We identify actions that can be discriminated purely from audio, through grouping free-form descriptions into classes. For actions that involve objects colliding, we collect human annotations of the materials of these objects (e.g. a glass object being placed on a wooden surface), which we verify from visual labels, discarding ambiguities. Overall, EPIC-SOUNDS includes 78.4k categorised segments of audible events and actions, distributed across 44 classes, as well as 39.2k non-categorised segments, totalling 117.6k segments spanning 100 hours of audio, capturing diverse actions that sound in home kitchens. We train and evaluate two state-of-the-art audio recognition models on our dataset, highlighting the importance of audio-only labels and the limitations of current models to recognise actions that sound.EPIC-SOUNDS and baseline source code is available from: https://epic-kitchens.github.io/epic-sounds.

Abstract 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 (Damen in Scaling egocentric vision: ECCV, 2018), 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.

We propose a two-stream convolutional network for audio recognition, that operates on time-frequency spectrogram inputs. Following similar success in visual recognition, we learn Slow-Fast auditory streams with separable convolutions and multi-level lateral connections. The Slow pathway has high channel capacity while the Fast pathway operates at a fine-grained temporal resolution. We showcase the importance of our two-stream proposal on two diverse datasets: VGG-Sound and EPIC-KITCHENS-100, and achieve state- of-the-art results on both.

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 four countries by participants belonging to ten 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).

We focus on multi-modal fusion for egocentric action recognition, and propose a novel architecture for multimodal temporal-binding, i.e. the combination of modalities within a range of temporal offsets. We train the architecture with three modalities - RGB, Flow and Audio - and combine them with mid-level fusion alongside sparse temporal sampling off used representations. In contrast with previous works, modalities are fused before temporal aggregation, with shared modality and fusion weights over time. Our proposed architecture is trained end-to-end, outperforming individual modalities as well as late-fusion of modalities. We demonstrate the importance of audio in egocentric vision, on per-class basis, for identifying actions as well as interacting objects. Our method achieves state of the art results on both the seen and unseen test sets of the largest egocentric dataset: EPIC-Kitchens, on all metrics using the public leaderboard.

Recent advances in deep learning have spurred 3D hand pose estimation, as convolutional network (ConvNet) based methods outperformed random forests. However, in the state of the art, ConvNet based methods employ only depth images of the hand without leveraging color and texture information from the RGB domain. In this paper, we investigate whether ConvNets can learn more rich and discriminative em-beddings, by combining RGB and depth information. To answer this question, we propose the fusion of RGB and depth information in a double-stream architecture. More specifically, RGB and depth images are fed into two separate networks by extracting features, which are subsequently fused at an intermediate layer of the ConvNet, implementing input-level fusion, feature-level fusion and score-level fusion. The double-stream scheme is coupled with a deep ConvNet, contrary to the shallow networks that are mostly proposed in the literature. Experimental results show that while the depth of the network is crucial for hand pose estimation, the double-stream nets perform very similarly with the net trained only with depth images. This may suggest that training double-stream architectures purely with supervision may be insufficient for hand pose estimation with RGB-D fusion.