Localizing Novel Attended Objects in Egocentric Views (original) (raw)
Related papers
Discovering Objects of Joint Attention via First-Person Sensing
2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2016
The goal of this work is to discover objects of joint attention, i.e., objects being viewed by multiple people using head-mounted cameras and eye trackers. Such objects of joint attention are expected to act as an important cue for understanding social interactions in everyday scenes. To this end, we develop a commonality-clustering method tailored to first-person videos combined with points-of-gaze sources. The proposed method uses multiscale spatiotemporal tubes around points of gaze as a candidate of objects, making it possible to deal with various sizes of objects observed in the first-person videos. We also introduce a new dataset of multiple pairs of first-person videos and points-of-gaze data. Our experimental results show that our approach can outperform several state-of-the-art commonality-clustering methods.
Saliency Driven Object recognition in egocentric videos with deep CNN
2016
The problem of object recognition in natural scenes has been recently successfully addressed with Deep Convolutional Neuronal Networks giving a significant break-through in recognition scores. The computational efficiency of Deep CNNs as a function of their depth, allows for their use in real-time applications. One of the key issues here is to reduce the number of windows selected from images to be submitted to a Deep CNN. This is usually solved by preliminary segmentation and selection of specific windows, having outstanding "objectiveness" or other value of indicators of possible location of objects. In this paper we propose a Deep CNN approach and the general framework for recognition of objects in a real-time scenario and in an egocentric perspective. Here the window of interest is built on the basis of visual attention map computed over gaze fixations measured by a glass-worn eye-tracker. The application of this set-up is an interactive user-friendly environment for u...
2021 IEEE Winter Conference on Applications of Computer Vision (WACV)
Wearable cameras allow to collect images and videos of humans interacting with the world. While human-object interactions have been thoroughly investigated in third person vision, the problem has been understudied in egocentric settings and in industrial scenarios. To fill this gap, we introduce MECCANO, the first dataset of egocentric videos to study human-object interactions in industrial-like settings. MECCANO has been acquired by 20 participants who were asked to build a motorbike model, for which they had to interact with tiny objects and tools. The dataset has been explicitly labeled for the task of recognizing human-object interactions from an egocentric perspective. Specifically, each interaction has been labeled both temporally (with action segments) and spatially (with active object bounding boxes). With the proposed dataset, we investigate four different tasks including 1) action recognition, 2) active object detection, 3) active object recognition and 4) egocentric human-object interaction detection, which is a revisited version of the standard human-object interaction detection task. Baseline results show that the MECCANO dataset is a challenging benchmark to study egocentric humanobject interactions in industrial-like scenarios. We publicy release the dataset at https://iplab.dmi.unict. it/MECCANO.
Making Third Person Techniques Recognize First-Person Actions in Egocentric Videos
2018 25th IEEE International Conference on Image Processing (ICIP), 2018
We focus on first-person action recognition from egocentric videos. Unlike third person domain, researchers have divided first-person actions into two categories: involving hand-object interactions and the ones without, and developed separate techniques for the two action categories. Further, it has been argued that traditional cues used for third person action recognition do not suffice, and egocentric specific features, such as head motion and handled objects have been used for such actions. Unlike the state-of-the-art approaches, we show that a regular two stream Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) architecture, having separate streams for objects and motion, can generalize to all categories of first-person actions. The proposed approach unifies the feature learned by all action categories, making the proposed architecture much more practical. In an important observation, we note that the size of the objects visible in the egocentric videos is much smaller. We show that the performance of the proposed model improves after cropping and resizing frames to make the size of objects comparable to the size of ImageNet's objects. Our experiments on the standard datasets: GTEA, EGTEA Gaze+, HUJI, ADL, UTE, and Kitchen, proves that our model significantly outperforms various state-of-the-art techniques.
Ego-Only: Egocentric Action Detection without Exocentric Pretraining
Cornell University - arXiv, 2023
We present Ego-Only, the first training pipeline that enables state-of-the-art action detection on egocentric (firstperson) videos without any form of exocentric (thirdperson) pretraining. Previous approaches found that egocentric models cannot be trained effectively from scratch and that exocentric representations transfer well to firstperson videos. In this paper we revisit these two observations. Motivated by the large content and appearance gap separating the two domains, we propose a strategy that enables effective training of egocentric models without exocentric pretraining. Our Ego-Only pipeline is simple. It trains the video representation with a masked autoencoder finetuned for temporal segmentation. The learned features are then fed to an off-the-shelf temporal action localization method to detect actions. We evaluate our approach on two established egocentric video datasets: Ego4D and EPIC-Kitchens-100. On Ego4D, our Ego-Only is on-par with exocentric pretraining methods that use an order of magnitude more labels. On EPIC-Kitchens-100, our Ego-Only even outperforms exocentric pretraining (by 2.1% on verbs and by 1.8% on nouns), setting a new state-of-the-art.
Next-active-object prediction from egocentric videos
Journal of Visual Communication and Image Representation
Although First Person Vision systems can sense the environment from the user's perspective, they are generally unable to predict his intentions and goals. Since human activities can be decomposed in terms of atomic actions and interactions with objects, intelligent wearable systems would benefit from the ability to anticipate user-object interactions. Even if this task is not trivial, the First Person Vision paradigm can provide important cues to address this challenge. We propose to exploit the dynamics of the scene to recognize next-active-objects before an object interaction begins. We train a classifier to discriminate trajectories leading to an object activation from all others and forecast next-active-objects by analyzing fixed-length trajectory segments within a temporal sliding window. The proposed method compares favorably with respect to several baselines on the Activity of Daily Living (ADL) egocentric dataset comprising 10 hours of videos acquired by 20 subjects while performing unconstrained interactions with several objects.
What I See Is What You See: Joint Attention Learning for First and Third Person Video Co-analysis
arXiv (Cornell University), 2019
In recent years, more and more videos are captured from the firstperson viewpoint by wearable cameras. Such first-person video provides additional information besides the traditional third-person video, and thus has a wide range of applications. However, techniques for analyzing the first-person video can be fundamentally different from those for the third-person video, and it is even more difficult to explore the shared information from both viewpoints. In this paper, we propose a novel method for first-and third-person video co-analysis. At the core of our method is the notion of "joint attention", indicating the learnable representation that corresponds to the shared attention regions in different viewpoints and thus links the two viewpoints. To this end, we develop a multi-branch deep network with a triplet loss to extract the joint attention from the first-and third-person videos via self-supervised learning. We evaluate our method on the public dataset with cross-viewpoint video matching tasks. Our method outperforms the state-of-the-art both qualitatively and quantitatively. We also demonstrate how the learned joint attention can benefit various applications through a set of additional experiments.
Localizing Objects While Learning Their Appearance
Lecture Notes in Computer Science, 2010
Learning a new object class from cluttered training images is very challenging when the location of object instances is unknown. Previous works generally require objects covering a large portion of the images. We present a novel approach that can cope with extensive clutter as well as large scale and appearance variations between object instances. To make this possible we propose a conditional random field that starts from generic knowledge and then progressively adapts to the new class. Our approach simultaneously localizes object instances while learning an appearance model specific for the class. We demonstrate this on the challenging Pascal VOC 2007 dataset. Furthermore, our method enables to train any state-of-the-art object detector in a weakly supervised fashion, although it would normally require object location annotations.
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100
International Journal of Computer Vision
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 do...
Modeling joint attention from egocentric vision
2021
Numerous studies in cognitive development have provided converging evidence that Joint Attention (JA) is crucial for children to learn about the world together with their parents. However, a closer look reveals that, in the literature, JA has been operationally defined in different ways. For example, some definitions require explicit signals of “awareness” of being in JA—such as gaze following, while others simply define JA as shared gaze to an object or activity. But what if “awareness” is possible without gaze following? The present study examines egocentric images collected via headmounted eye-trackers during parent-child toy play. A Convolutional Neural Network model was used to process and learn to classify raw egocentric images as JA vs not JA. We demonstrate individual child and parent egocentric views can be classified as being part of a JA bout at above chance levels. This provides new evidence that an individual can be “aware” they are in JA based solely on the in-the-mome...