相关论文: Helping Hands: An Object-Aware Ego-Centric Video R…

Humans develop visual intelligence through perceiving and interacting with their environment - a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems learn stable object…

Egocentric videos present unique challenges for 3D scene understanding due to rapid camera motion, frequent object occlusions, and limited object visibility. This paper introduces a novel approach to instance segmentation and tracking in…

Egocentric video-language pretraining is a crucial step in advancing the understanding of hand-object interactions in first-person scenarios. Despite successes on existing testbeds, we find that current EgoVLMs can be easily misled by…

This report describes our submission called "TarHeels" for the Ego4D: Object State Change Classification Challenge. We use a transformer-based video recognition model and leverage the Divided Space-Time Attention mechanism for classifying…

Object-centric representation learning has recently been successfully applied to real-world datasets. This success can be attributed to pretrained non-object-centric foundation models, whose features serve as reconstruction targets for slot…

Using an ego-centric camera to do localization and tracking is highly needed for urban navigation and indoor assistive system when GPS is not available or not accurate enough. The traditional hand-designed feature tracking and estimation…

Egocentric videos offer fine-grained information for high-fidelity modeling of human behaviors. Hands and interacting objects are one crucial aspect of understanding a viewer's behaviors and intentions. We provide a labeled dataset…

A core task in embodied intelligence is ego-centric 3D visual grounding. Existing methods typically adopt two-stage, heterogeneous pipelines that pair a detector with a separate grounding model. Incompatible decoders and box heads hinder…

Egocentric vision holds great promises for increasing access to visual information and improving the quality of life for people with visual impairments, with object recognition being one of the daily challenges for this population. While we…

Well structured visual representations can make robot learning faster and can improve generalization. In this paper, we study how we can acquire effective object-centric representations for robotic manipulation tasks without human labeling…

We present Ego-Only, the first approach that enables state-of-the-art action detection on egocentric (first-person) videos without any form of exocentric (third-person) transferring. Despite the content and appearance gap separating the two…

Visual grounding associates textual descriptions with objects in an image. Conventional methods target third-person image inputs and named object queries. In applications such as AI assistants, the perspective shifts -- inputs are…

We propose a method for incorporating object interaction and human body dynamics into the task of 3D ego-pose estimation using a head-mounted camera. We use a kinematics model of the human body to represent the entire range of human motion,…

We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to…

As the demand for analyzing egocentric videos grows, egocentric visual attention prediction, anticipating where a camera wearer will attend, has garnered increasing attention. However, it remains challenging due to the inherent complexity…

Object-centric representations enable autonomous driving algorithms to reason about interactions between many independent agents and scene features. Traditionally these representations have been obtained via supervised learning, but this…

Human actions in egocentric videos are often hand-object interactions composed from a verb (performed by the hand) applied to an object. Despite their extensive scaling up, egocentric datasets still face two limitations - sparsity of action…

This paper proposes an interaction reasoning network for modelling spatio-temporal relationships between hands and objects in video. The proposed interaction unit utilises a Transformer module to reason about each acting hand, and its…

This paper investigates the problem of understanding dynamic 3D scenes from egocentric observations, a key challenge in robotics and embodied AI. Unlike prior studies that explored this as long-form video understanding and utilized…