English
Related papers

Related papers: Localizing Active Objects from Egocentric Vision w…

200 papers

Household robots operate in the same space for years. Such robots incrementally build dynamic maps that can be used for tasks requiring remote object localization. However, benchmarks in robot learning often test generalization through…

Robotics · Computer Science 2023-01-31 Gunnar A. Sigurdsson , Jesse Thomason , Gaurav S. Sukhatme , Robinson Piramuthu

We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Xingyi Zhou , Anurag Arnab , Chen Sun , Cordelia Schmid

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…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Sungjune Park , Hongda Mao , Qingshuang Chen , Yong Man Ro , Yelin Kim

We present lazy visual grounding, a two-stage approach of unsupervised object mask discovery followed by object grounding, for open-vocabulary semantic segmentation. Plenty of the previous art casts this task as pixel-to-text classification…

Computer Vision and Pattern Recognition · Computer Science 2024-08-12 Dahyun Kang , Minsu Cho

Object referring has important applications, especially for human-machine interaction. While having received great attention, the task is mainly attacked with written language (text) as input rather than spoken language (speech), which is…

Computer Vision and Pattern Recognition · Computer Science 2017-12-06 Arun Balajee Vasudevan , Dengxin Dai , Luc Van Gool

Autonomous robots that interact with their environment require a detailed semantic scene model. For this, volumetric semantic maps are frequently used. The scene understanding can further be improved by including object-level information in…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Julian Hau , Simon Bultmann , Sven Behnke

Imitation learning from human demonstrations offers a promising approach for robot skill acquisition, but egocentric human data introduces fundamental challenges due to the embodiment gap. During manipulation, humans actively coordinate…

Robotics · Computer Science 2026-03-11 Justin Yu , Yide Shentu , Di Wu , Pieter Abbeel , Ken Goldberg , Philipp Wu

Recent approaches have successfully focused on the segmentation of static reconstructions, thereby equipping downstream applications with semantic 3D understanding. However, the world in which we live is dynamic, characterized by numerous…

Robotics · Computer Science 2025-03-12 Tjark Behrens , René Zurbrügg , Marc Pollefeys , Zuria Bauer , Hermann Blum

Egocentric sensors such as AR/VR devices capture human-object interactions and offer the potential to provide task-assistance by recalling 3D locations of objects of interest in the surrounding environment. This capability requires instance…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Yunhan Zhao , Haoyu Ma , Shu Kong , Charless Fowlkes

Ambiguities are inevitable in human-robot interaction, especially when a robot follows user instructions in a large, shared space. For example, if a user asks the robot to find an object in a home environment with underspecified…

Robotics · Computer Science 2025-04-03 Fethiye Irmak Dogan , Maithili Patel , Weiyu Liu , Iolanda Leite , Sonia Chernova

An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to interact with objects in 3D environments. We found that an…

Artificial Intelligence · Computer Science 2022-11-16 Kazutoshi Shinoda , Yuki Takezawa , Masahiro Suzuki , Yusuke Iwasawa , Yutaka Matsuo

Grounded understanding of natural language in physical scenes can greatly benefit robots that follow human instructions. In object manipulation scenarios, existing end-to-end models are proficient at understanding semantic concepts, but…

Robotics · Computer Science 2023-04-03 Qian Luo , Yunfei Li , Yi Wu

Generating instructional images of human daily actions from an egocentric viewpoint serves as a key step towards efficient skill transfer. In this paper, we introduce a novel problem -- egocentric action frame generation. The goal is to…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Bolin Lai , Xiaoliang Dai , Lawrence Chen , Guan Pang , James M. Rehg , Miao Liu

Embodied agents face significant challenges when tasked with performing actions in diverse environments, particularly in generalizing across object types and executing suitable actions to accomplish tasks. Furthermore, agents should exhibit…

Artificial Intelligence · Computer Science 2023-06-05 Xiaotian Liu , Hector Palacios , Christian Muise

Humans excel at acquiring knowledge through observation. For example, we can learn to use new tools by watching demonstrations. This skill is fundamental for intelligent systems to interact with the world. A key step to acquire this skill…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Gen Li , Varun Jampani , Deqing Sun , Laura Sevilla-Lara

Language is an interface to the outside world. In order for embodied agents to use it, language must be grounded in other, sensorimotor modalities. While there is an extended literature studying how machines can learn grounded language, the…

Artificial Intelligence · Computer Science 2021-10-12 Tristan Karch , Laetitia Teodorescu , Katja Hofmann , Clément Moulin-Frier , Pierre-Yves Oudeyer

We present an Open-Vocabulary 3D Scene Graph (OVSG), a formal framework for grounding a variety of entities, such as object instances, agents, and regions, with free-form text-based queries. Unlike conventional semantic-based object…

Different video understanding tasks are typically treated in isolation, and even with distinct types of curated data (e.g., classifying sports in one dataset, tracking animals in another). However, in wearable cameras, the immersive…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Zihui Xue , Yale Song , Kristen Grauman , Lorenzo Torresani

Unlike traditional third-person cameras mounted on robots, a first-person camera, captures a person's visual sensorimotor object interactions from up close. In this paper, we study the tight interplay between our momentary visual attention…

Computer Vision and Pattern Recognition · Computer Science 2017-06-13 Gedas Bertasius , Hyun Soo Park , Stella X. Yu , Jianbo Shi

Humans interpret scenes by recognizing both the identities and positions of objects in their observations. For a robot to perform tasks such as \enquote{pick and place}, understanding both what the objects are and where they are located is…