Embodied AI (EAI) research requires high-quality, diverse 3D scenes to effectively support skill acquisition, sim-to-real transfer, and generalization. Achieving these quality standards, however, necessitates the precise replication of real-world object diversity. Existing datasets demon strate that this process heavily relies on artist-driven designs, which demand substantial human effort and present significant scalability challenges. To scalably produce realistic and interactive 3D scenes, we first present MetaScenes, a large-scale simulatable 3D scene dataset constructed from real-world scans, which includes 15366 objects spanning 831 fine-grained categories. Then, we introduce SCAN2SIM, a robust multi-modal alignment model, which enables the automated, high-quality replacement of assets, thereby eliminating the reliance on artist-driven designs for scaling 3D scenes. We further propose two benchmarks to evaluate MetaScenes: a detailed scene synthesis task focused on small item layouts for robotic manipulation and a domain transfer task in vision-and-language navigation (VLN) to validate cross-domain transfer. Results confirm MetaScenes ’s potential to enhance EAI by supporting more generalizable agent learning and sim-to-real applications, introducing new possibilities for EAI research.

Recent years have witnessed a tremendous increase of first-person videos captured by wearable devices. Such videos record information from different perspectives than the traditional third-person view, and thus show a wide range of potential usages. However, techniques for analyzing videos from different views can be fundamentally different, not to mention co-analyzing on both views to explore the shared information. In this paper, we take the challenge of cross-view video co-analysis and deliver a novel learning-based method. At the core of our method is the notion of "joint attention", indicating the shared attention regions that link the corresponding views, and eventually guide the shared representation learning across views. To this end, we propose a multi-branch deep network, which extracts cross-view joint attention and shared representation from static frames with spatial constraints, in a self-supervised and simultaneous manner. In addition, by incorporating the temporal transition model of the joint attention, we obtain spatial-temporal joint attention that can robustly capture the essential information extending through time. Our method outperforms the state-of-the-art on the standard cross-view video matching tasks on public datasets. Furthermore, we demonstrate how the learnt joint information can benefit various applications through a set of qualitative and quantitative experiments.

Multimodal interaction has become a recent research focus since it offers better user experience in augmented reality (AR) systems. However, most existing works only combine two modalities at a time, e.g., gesture and speech. Multimodal interactive system integrating gaze cue has rarely been investigated. In this article, we propose a multimodal interactive system that integrates gaze, gesture, and speech in a flexibly configurable AR system. Our lightweight head-mounted device supports accurate gaze tracking, hand gesture recognition, and speech recognition simultaneously. The system can be easily configured into various modality combinations, which enables us to investigate the effects of different interaction techniques. We evaluate the efficiency of these modalities using two tasks: the lamp brightness adjustment task and the cube manipulation task. We also collect subjective feedback when using such systems. The experimental results demonstrate that theGaze+Gesture+Speechmodality is superior in terms of efficiency, and theGesture+Speechmodality is more preferred by users. Our system opens the pathway toward a multimodal interactive AR system that enables flexible configuration.

In recent years, more and more videos are captured from the first-person 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.

The emergence of user-operated media motivates the explosive growth of online videos. Browsing these large amounts of videos is time-consuming and tedious, which makes finding the moments of user major or special preference (i.e. highlights extraction) becomes an urgent problem. Moreover, the user subjectivity over a video makes no fixed extraction meets all user preferences. This paper addresses these problems by posing a query-related highlight extraction framework which optimizes selected frames to both semantically query-related and visually representative of the entire video. Under this framework, relevance between the query text and the video frames is first computed on a visual-semantic feature embedding space induced by a convolutional neural network (Query-Inception network). Then we enforce the diversity on the video frames with the determinantal point process (DPP), a recently introduced probabilistic model for diverse subset selection. The experimental results show that our query-related highlight extraction method is particularly useful for news videos content fetching, e.g. showing the abstraction of the entire video while playing focus on the parts that matches the user queries.