Indoor scene recognition is a growing field with great potential for behaviour understanding, robot localization, and elderly monitoring, among others. In this study, we approach the task of scene recognition from a novel standpoint, using multi-modal learning and video data gathered from social media. The accessibility and variety of social media videos can provide realistic data for modern scene recognition techniques and applications. We propose a model based on fusion of transcribed speech to text and visual features, which is used for classification on a novel dataset of social media videos of indoor scenes named InstaIndoor. Our model achieves up to 70% accuracy and 0.7 F1-Score. Furthermore, we highlight the potential of our approach by benchmarking on a YouTube-8M subset of indoor scenes as well, where it achieves 74% accuracy and 0.74 F1-Score. We hope the contributions of this work pave the way to novel research in the challenging field of indoor scene recognition.
Providing omnidirectional depth along with RGB information is important for numerous applications, eg, VR/AR. However, as omnidirectional RGB-D data is not always available, synthesizing RGB-D panorama data from limited information of a scene can be useful. Therefore, some prior works tried to synthesize RGB panorama images from perspective RGB images; however, they suffer from limited image quality and can not be directly extended for RGB-D panorama synthesis. In this paper, we study a new problem: RGB-D panorama synthesis under the arbitrary configurations of cameras and depth sensors. Accor…
Navigation inside a closed area with no GPS-signal accessibility is a highly challenging task. In order to tackle this problem, recently the imaging-based methods have grabbed the attention of many researchers. These methods either extract the features (e.g. using SIFT, or SOSNet) and map the descriptive ones to the camera position and rotation information, or deploy an end-to-end system that directly estimates this information out of RGB images, similar to PoseNet. While the former methods suffer from heavy computational burden during the test process, the latter suffers from lack of accuracy…
This paper considers indoor localization using multi-modal wireless signals including Wi-Fi, inertial measurement unit (IMU), and ultra-wideband (UWB). By formulating the localization as a multi-modal sequence regression problem, a multi-stream recurrent fusion method is proposed to combine the current hidden state of each modality in the context of recurrent neural networks while accounting for the modality uncertainty which is directly learned from its own immediate past states. The proposed method was evaluated on the large-scale SPAWC2021 multi-modal localization dataset and compared with …
DiffPixelFormer: Differential Pixel-Aware Transformer for RGB-D Indoor Scene Segmentation
State Key Laboratory of Robotics and System, Harbin Institute of Technology（机器人系统国家重点实验室，哈尔滨工业大学）；Institute for Infocomm Research, A*STAR（信息通信研究机构，A*STAR）；College of Information Science and Electronic Engineering, Zhejiang University（信息科学与电子工程学院，浙江大学）
Seamless Human-Robot Interaction is the ultimate goal of developing service robotic systems. For this, the robotic agents have to understand their surroundings to better complete a given task. Semantic scene understanding allows a robotic agent to extract semantic knowledge about the objects in the environment. In this work, we present a semantic scene understanding pipeline that fuses 2D and 3D detection branches to generate a semantic map of the environment. The 2D mask proposals from state-of-the-art 2D detectors are inverse-projected to the 3D space and combined with 3D detections from poi…
Stanford University（斯坦福大学）；University of California Berkeley（加州大学伯克利分校）
We present a dataset of large-scale indoor spaces that provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. The dataset covers over 6,000m2 and contains over 70,000 RGB images, along with the corresponding depths, surface normals, semantic annotations, global XYZ images (all in forms of both regular and 360° equirectangular images) as well as camera information. It also includes registered raw and semantically annotated 3D meshes and point clouds. The dataset enables development of joint and cross-modal learn…
Loughborough University London（拉夫堡大学伦敦校区）；Institute for Digital Technologies（数字技术研究所）
Human Activity Recognition (HAR) is a key building block of many emerging applications such as intelligent mobility, sports analytics, ambient-assisted living and human-robot interaction. With robust HAR, systems will become more human-aware, leading towards much safer and empathetic autonomous systems. While human pose detection has made significant progress with the dawn of deep convolutional neural networks (CNNs), the state-of-the-art research has almost exclusively focused on a single sensing modality, especially video. However, in safety critical applications it is imperative to utilize …
Technical University of Munich（慕尼黑工业大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Siemens AG（西门子股份公司）
Depth estimation is a core task in 3D computer vision. Recent methods investigate the task of monocular depth trained with various depth sensor modalities. Every sensor has its advantages and drawbacks caused by the nature of estimates. In the literature, mostly mean average error of the depth is investigated and sensor capabilities are typically not discussed. Especially indoor environments, however, pose challenges for some devices. Textureless regions pose challenges for structure from motion, reflective materials are problematic for active sensing, and distances for translucent material ar…
Recognition of Daily Activities through Multi-Modal Deep Learning: A Video, Pose, and Object-Aware Approach for Ambient Assisted Living
Alicante Institute for Health and Biomedical Research (ISABIAL)（阿利坎特健康与生物医学研究所（ISABIAL））；ValgrAI - Valencian Graduate School and Research Network of Artificial Intelligence（瓦尔格AI——瓦伦西亚人工智能研究生院与研究网络）
Whole-body-based human authentication is a promising approach for remote biometrics scenarios. Current literature focuses on either body recognition based on RGB images or gait recognition based on body shapes and walking patterns; both have their advantages and drawbacks. In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition. Within DME, we propose GaitPattern, which is inspired by the double helical gait pattern used in traditional gait analysis. The GaitPattern c…
Nanyang Technological University（南洋理工大学）；Advanced Digital Sciences Center (ADSC), Illinois at Singapore Pt Ltd（新加坡伊利诺伊高级数字科学中心私人有限公司）
This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation. It is optimized to classify image pixels given two input sources: RGB color channels and Depth maps. It simultaneously performs training of two recurrent neural networks (RNNs) that are crossly connected through information transfer layers, which are learnt to adaptively extract relevant cross-modality features. Each RNN model learns its representations from its own previous hidden states and transferred patterns from the other RNNs previous hidden states; thus, both model-specific and crossmodality …
Multi-modal fusion has been proved to help enhance the performance of scene classification tasks. This paper presents a 2D-3D Fusion stage that combines 3D Geometric Features with 2D Texture Features obtained by 2D Convolutional Neural Networks. To get a robust 3D Geometric embedding, a network that uses two novel layers is proposed. The first layer, Multi-Neighbourhood Graph Convolution, aims to learn a more robust geometric descriptor of the scene combining two different neighbourhoods: one in the Euclidean space and the other in the Feature space. The second proposed layer, Nearest Voxel Po…
The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc. Nonetheless, this direction has not been well-explored in comparison with models for outdoor environments (e.g., the autonomous driving system that includes pedestrian prediction, car detection, traffic sign recognition, etc.). In this paper, we first discuss the main challenge: insufficient, or even no, labeled data for real-world indoor environments, and other challenges such as fusion between heter…
Feasibility of Indoor Frame-Wise Lidar Semantic Segmentation via Distillation from Visual Foundation Model
1 Department of Earth Observation Science, Faculty of Geo-Information Science；Earth Observation (ITC), University of Twente, 7522 NB Enschede, The Netherlands
We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment. Point cloud patches are extracted, canonicalised with respect to their estimated local reference frame and encoded into rotation-invariant compact descriptors by a PointNet-based deep neural network. DIPs can effectively generalise across different sensor modalities because they are learnt end-to-end from locally and randomly sampled points. Because DIPs encode only local geometric information, they are robust t…
We present a challenging dataset, ChangeSim, aimed at online scene change detection (SCD) and more. The data is collected in photo-realistic simulation environments with the presence of environmental non-targeted variations, such as air turbidity and light condition changes, as well as targeted object changes in industrial indoor environments. By collecting data in simulations, multi-modal sensor data and precise ground truth labels are obtainable such as the RGB image, depth image, semantic segmentation, change segmentation, camera poses, and 3D reconstructions. While the previous online SCD …
Neural Radiance Fields (NeRF) has achieved impressive results in single object scene reconstruction and novel view synthesis, which have been demonstrated on many single modality and single object focused indoor scene datasets like DTU, BMVS, and NeRF Synthetic.However, the study of NeRF on large-scale outdoor scene reconstruction is still limited, as there is no unified outdoor scene dataset for large-scale NeRF evaluation due to expensive data acquisition and calibration costs. In this paper, we propose a large-scale outdoor multi-modal dataset, OMMO dataset, containing complex land objects …
University of Oulu（奥卢大学）；University of Waterloo（滑铁卢大学）；University of Canberra（堪培拉大学）
Millions of images on the web enable us to explore images from social events such as a family party, thus it is of interest to understand and model the affect exhibited by a group of people in images. But analysis of the affect expressed by multiple people is challenging due to varied indoor and outdoor settings, and interactions taking place between various numbers of people. A few existing works on Group-level Emotion Recognition (GER) have investigated on face-level information. Due to the challenging environments, face may not provide enough information to GER. Relatively few studies have …
A Large Cross-Modal Video Retrieval Dataset with Reading Comprehension
University of Chinese Academy of Sciences（中国科学院大学）；National University of Singapore（新加坡国立大学）；Zhejiang University（浙江大学）；Kuaishou Technology（快手科技）；Huazhong University of Science and Technology（华中科技大学）
Image-based vibration mode identification gained increased attentions in civil and construction communities. A recent video-based motion magnification method was developed to measure and visualize small structure motions. This new approach presents a potential for low-cost vibration measurement and mode shape identification. Pilot studies using this approach on simple rigid body structures was reported. Its validity on complex outdoor structures have not been investigated. The objective is to investigate the capacity of video-based motion magnification approach in measuring the modal frequency…
Indoor scene images usually contain scattered objects and various scene layouts, which make RGB-D scene classification a challenging task. Existing methods still have limitations for classifying scene images with great spatial variability. Thus, how to extract local patch-level features effectively using only image labels is still an open problem for RGB-D scene recognition. In this paper, we propose an efficient framework for RGB-D scene recognition, which adaptively selects important local features to capture the great spatial variability of scene images. Specifically, we design a differenti…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Dalian Naval Academy（大连海军学院）；Lingnan University（岭南大学）；Hong Kong Metropolitan University（香港都会大学）；The Polytechnic University of Hong Kong（香港理工大学）
There is a trend to fuse multi-modal information for 3D object detection (3OD). However, the challenging problems of low lightweightness, poor flexibility of plug-and-play, and inaccurate alignment of features are still not well-solved, when designing multi-modal fusion newtorks. We propose PointSee, a lightweight, flexible and effective multi-modal fusion solution to facilitate various 3OD networks by semantic feature enhancement of LiDAR point clouds assembled with scene images. Beyond the existing wisdom of 3OD, PointSee consists of a hidden module (HM) and a seen module (SM): HM decorates …
We present NAVREN-RL, an approach to NAVigate an unmanned aerial vehicle in an indoor Real ENvironment via end-to-end reinforcement learning RL. A suitable reward function is designed keeping in mind the cost and weight constraints for micro drone with minimum number of sensing modalities. Collection of small number of expert data and knowledge based data aggregation is integrated into the RL process to aid convergence. Experimentation is carried out on a Parrot AR drone in different indoor arenas and the results are compared with other baseline technologies. We demonstrate how the drone succe…
Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning
Faculty of Automatic Control and Computer Science, Politehnica University of Bucharest（自动化控制与计算机科学系，布加勒斯特理工大学）；Institute of Mathematics of the Romanian Academy（罗马尼亚科学院数学研究所）
Sign language recognition is a challenging problem where signs are identified by simultaneous local and global articulations of multiple sources, i.e. hand shape and orientation, hand movements, body posture, and facial expressions. Solving this problem computationally for a large vocabulary of signs in real life settings is still a challenge, even with the state-of-the-art models. In this study, we present a new largescale multi-modal Turkish Sign Language dataset (AUTSL) with a benchmark and provide baseline models for performance evaluations. Our dataset consists of 226 signs performed by 4…
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
University of Amsterdam（阿姆斯特丹大学）；Computer Vision Lab, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）；INSAIT, Sofia University ”St. Kliment Ohridski”（索菲亚大学”圣克莱门特·欧赫里迪斯”研究所）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；University of Pisa（比萨大学）；University of Trento（特伦特大学）
