skip to main content

Title: EPIC-KITCHENS VISOR Benchmark: VIdeo Segmentations and Object Relations
We introduce VISOR, a new dataset of pixel annotations and a benchmark suite for segmenting hands and active objects in egocentric video. VISOR annotates videos from EPIC-KITCHENS, which comes with a new set of challenges not encountered in current video segmentation datasets. Specifically, we need to ensure both short- and long-term consistency of pixel-level annotations as objects undergo transformative interactions, e.g. an onion is peeled, diced and cooked - where we aim to obtain accurate pixel-level annotations of the peel, onion pieces, chopping board, knife, pan, as well as the acting hands. VISOR introduces an annotation pipeline, AI-powered in parts, for scalability and quality. In total, we publicly release 272K manual semantic masks of 257 object classes, 9.9M interpolated dense masks, 67K hand-object relations, covering 36 hours of 179 untrimmed videos. Along with the annotations, we introduce three challenges in video object segmentation, interaction understanding and long-term reasoning. For data, code and leaderboards:  more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Publisher / Repository:
Date Published:
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Neural rendering is fuelling a unification of learning, 3D geometry and video understanding that has been waiting for more than two decades. Progress, however, is still hampered by a lack of suitable datasets and benchmarks. To address this gap, we introduce EPIC Fields, an augmentation of EPIC-KITCHENS with 3D camera information. Like other datasets for neural rendering, EPIC Fields removes the complex and expensive step of reconstructing cameras using photogrammetry, and allows researchers to focus on modelling problems. We illustrate the challenge of photogrammetry in egocentric videos of dynamic actions and propose innovations to address them. Compared to other neural rendering datasets, EPIC Fields is better tailored to video understanding because it is paired with labelled action segments and the recent VISOR segment annotations. To further motivate the community, we also evaluate three benchmark tasks in neural rendering and segmenting dynamic objects, with strong baselines that showcase what is not possible today. We also highlight the advantage of geometry in semi-supervised video object segmentations on the VISOR annotations. EPIC Fields reconstructs 96% of videos in EPICKITCHENS, registering 19M frames in 99 hours recorded in 45 kitchens, and is available from: 
    more » « less
  2. Abstract

    Advances in visual perceptual tasks have been mainly driven by the amount, and types, of annotations of large-scale datasets. Researchers have focused on fully-supervised settings to train models using offline epoch-based schemes. Despite the evident advancements, limitations and cost of manually annotated datasets have hindered further development for event perceptual tasks, such as detection and localization of objects and events in videos. The problem is more apparent in zoological applications due to the scarcity of annotations and length of videos-most videos are at most ten minutes long. Inspired by cognitive theories, we present a self-supervised perceptual prediction framework to tackle the problem of temporal event segmentation by building a stable representation of event-related objects. The approach is simple but effective. We rely on LSTM predictions of high-level features computed by a standard deep learning backbone. For spatial segmentation, the stable representation of the object is used by an attention mechanism to filter the input features before the prediction step. The self-learned attention maps effectively localize the object as a side effect of perceptual prediction. We demonstrate our approach on long videos from continuous wildlife video monitoring, spanning multiple days at 25 FPS. We aim to facilitate automated ethogramming by detecting and localizing events without the need for labels. Our approach is trained in an online manner on streaming input and requires only a single pass through the video, with no separate training set. Given the lack of long and realistic (includes real-world challenges) datasets, we introduce a new wildlife video dataset–nest monitoring of the Kagu (a flightless bird from New Caledonia)–to benchmark our approach. Our dataset features a video from 10 days (over 23 million frames) of continuous monitoring of the Kagu in its natural habitat. We annotate every frame with bounding boxes and event labels. Additionally, each frame is annotated with time-of-day and illumination conditions. We will make the dataset, which is the first of its kind, and the code available to the research community. We find that the approach significantly outperforms other self-supervised, traditional (e.g., Optical Flow, Background Subtraction) and NN-based (e.g., PA-DPC, DINO, iBOT), baselines and performs on par with supervised boundary detection approaches (i.e., PC). At a recall rate of 80%, our best performing model detects one false positive activity every 50 min of training. On average, we at least double the performance of self-supervised approaches for spatial segmentation. Additionally, we show that our approach is robust to various environmental conditions (e.g., moving shadows). We also benchmark the framework on other datasets (i.e., Kinetics-GEBD, TAPOS) from different domains to demonstrate its generalizability. The data and code are available on our project page:

    more » « less
  3. Human visual understanding of action is reliant on anticipation of contact as is demonstrated by pioneering work in cognitive science. Taking inspiration from this, we introduce representations and models centered on contact, which we then use in action prediction and anticipation. We annotate a subset of the EPIC Kitchens dataset to include time-to-contact between hands and objects, as well as segmentations of hands and objects. Using these annotations we train the Anticipation Module, a module producing Contact Anticipation Maps and Next Active Object Segmentations - novel low-level representations providing temporal and spatial characteristics of anticipated near future action. On top of the Anticipation Module we apply Egocentric Object Manipulation Graphs (Ego-OMG), a framework for action anticipation and prediction. Ego-OMG models longer-term temporal semantic relations through the use of a graph modeling transitions between contact delineated action states. Use of the Anticipation Module within Ego-OMG produces state-of-the-art results, achieving 1st and 2nd place on the unseen and seen test sets, respectively, of the EPIC Kitchens Action Anticipation Challenge, and achieving state-of-the-art results on the tasks of action anticipation and action prediction over EPIC Kitchens. We perform ablation studies over characteristics of the Anticipation Module to evaluate their utility. 
    more » « less
  4. null (Ed.)
    First-person-view videos of hands interacting with tools are widely used in the computer vision industry. However, creating a dataset with pixel-wise segmentation of hands is challenging since most videos are captured with fingertips occluded by the hand dorsum and grasped tools. Current methods often rely on manually segmenting hands to create annotations, which is inefficient and costly. To relieve this challenge, we create a method that utilizes thermal information of hands for efficient pixel-wise hand segmentation to create a multi-modal activity video dataset. Our method is not affected by fingertip and joint occlusions and does not require hand pose ground truth. We show our method to be 24 times faster than the traditional polygon labeling method while maintaining high quality. With the segmentation method, we propose a multi-modal hand activity video dataset with 790 sequences and 401,765 frames of "hands using tools" videos captured by thermal and RGB-D cameras with hand segmentation data. We analyze multiple models for hand segmentation performance and benchmark four segmentation networks. We show that our multi-modal dataset with fusing Long-Wave InfraRed (LWIR) and RGB-D frames achieves 5% better hand IoU performance than using RGB frames. 
    more » « less
  5. Our method uses manipulation in video to learn to understand held-objects and hand-object contact. We train a system that takes a single RGB image and produces a pixel-embedding that can be used to answer grouping questions (do these two pixels go together) as well as hand-association questions (is this hand holding that pixel). Rather than painstakingly annotate segmentation masks, we observe people in realistic video data. We show that pairing epipolar geometry with modern optical flow produces simple and effective pseudo-labels for grouping. Given people segmentations, we can further associate pixels with hands to understand contact. Our system achieves competitive results on hand and hand-held object tasks. 
    more » « less