Several animal species (e.g., bats, dolphins, and whales) and even visually impaired humans have the remarkable ability to perform echolocation: a biological sonar used to perceive spatial layout and locate objects in the world. We explore the spatial cues contained in echoes and how they can benefit vision tasks that require spatial reasoning. First we capture echo responses in photo-realistic 3D indoor scene environments. Then we propose a novel interaction-based representation learning framework that learns useful visual features via echolocation. We show that the learned image features are useful for multiple downstream vision tasks requiring spatial reasoning---monocular depth estimation, surface normal estimation, and visual navigation---with results comparable or even better than heavily supervised pre-training. Our work opens a new path for representation learning for embodied agents, where supervision comes from interacting with the physical world.
Detection and Classification of Cetacean Echolocation Clicks using Image-based Object Detection Methods applied to Advanced Wavelet-based Transformations
Technical University of Denmark（丹麦技术大学）；UC Berkeley（加州大学伯克利分校）；ICSI（国际计算机科学研究所）
Many species have evolved advanced non-visual perception while artificial systems fall behind. Radar and ultrasound complement camera-based vision but they are often too costly and complex to set up for very limited information gain. In nature, sound is used effectively by bats, dolphins, whales, and humans for navigation and communication. However, it is unclear how to best harness sound for machine perception. Inspired by bats' echolocation mechanism, we design a low-cost BatVision system that is capable of seeing the 3D spatial layout of space ahead by just listening with two ears. Our syst…
Harbin Institute of Technology（哈尔滨工业大学）；University of Science and Technology（中国科学技术大学）；SenseTime Research（商汤科技研究院）；The Chinese University of Hong Kong（香港中文大学）；IIIS, Tsinghua University（清华大学交叉信息研究院）
Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional space, such pre-trained models fail to perceive spatial information and serve as sub-optimal solutions for 3D-related tasks. To bridge this gap, we aim to learn a spatial-aware visual representation that can describe the three-dimensional space and is more suitable and effective for these tasks. To leverage point clouds, which are much more superior in prov…
3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and octrees) or from unstructured representations (graphs and point clouds). Learning features from such structured representations is limited by the restriction on resolution and tree depth while unstructured representations creates a challenge due to non-uniformity among data sample…
Instituto Politécnico Nacional (IPN)（国立理工学院）；Centro de Innovación y Desarrollo Tecnológico en Cómputo (CIDETEC)（计算技术创新与发展中心）
Neural rendering has emerged as a powerful paradigm for synthesizing images, offering many benefits over classical rendering by using neural networks to reconstruct surfaces, represent shapes, and synthesize novel views, either for objects or scenes. In this neural rendering, the environment is encoded into a neural network. We believe that these new representations can be used to codify the scene for a mobile robot. Therefore, in this work, we perform a comparison between a trending neural rendering, called tiny-NeRF, and other volume representations that are commonly used as maps in robotics…
We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual correspondence (AVC) predict whether audio and video clips originate from the same or different video instances. Audio-visual temporal synchronization (AVTS) further discriminates negative pairs originated from the same video instance but at different moments in time. While these approaches learn high-quality representations for downstream tasks such as action r…
University of Kansas（堪萨斯大学）；Ryerson University（瑞尔森大学）
Human beings can recognize new objects with only a few labeled examples, however, few-shot learning remains a challenging problem for machine learning systems. Most previous algorithms in few-shot learning only utilize spatial information of the images. In this paper, we propose to integrate the frequency information into the learning model to boost the discrimination ability of the system. We employ Discrete Cosine Transformation (DCT) to generate the frequency representation, then, integrate the features from both the spatial domain and frequency domain for classification. The proposed strat…
We propose a novel approach for few-shot talking-head synthesis. While recent works in neural talking heads have produced promising results, they can still produce images that do not preserve the identity of the subject in source images. We posit this is a result of the entangled representation of each subject in a single latent code that models 3D shape information, identity cues, colors, lighting and even background details. In contrast, we propose to factorize the representation of a subject into its spatial and style components. Our method generates a target frame in two steps. First, it p…
In digital pathology, both detection and classification of cells are important for automatic diagnostic and prognostic tasks. Classifying cells into subtypes, such as tumor cells, lymphocytes or stromal cells is particularly challenging. Existing methods focus on morphological appearance of individual cells, whereas in practice pathologists often infer cell classes through their spatial context. In this paper, we propose a novel method for both detection and classification that explicitly incorporates spatial contextual information. We use the spatial statistical function to describe local den…
Recently, the image-wise implicit neural representation of videos, NeRV, has gained popularity for its promising results and swift speed compared to regular pixel-wise implicit representations. However, the redundant parameters within the network structure can cause a large model size when scaling up for desirable performance. The key reason of this phenomenon is the coupled formulation of NeRV, which outputs the spatial and temporal information of video frames directly from the frame index input. In this paper, we propose E-NeRV, which dramatically expedites NeRV by decomposing the image-wise…
The Hong Kong Polytechnic University（香港理工大学）；Sensetime Research（商汤科技研究院）
Group activity recognition is a crucial yet challenging problem, whose core lies in fully exploring spatial-temporal interactions among individuals and generating reasonable group representations. However, previous methods either model spatial and temporal information separately, or directly aggregate individual features to form group features. To address these issues, we propose a novel group activity recognition network termed GroupFormer. It captures spatial-temporal contextual information jointly to augment the individual and group representations effectively with a clustered spatial-tempo…
Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While these contrastive methods mainly focus on generating invariant global representations at the image-level under semantic-preserving transformations, they are prone to overlook spatial consistency of local representations and therefore have a limitation in pretraining for localization tasks such as object detection and instance segmentation. Moreover, aggressi…
Hunan University（湖南大学）；State Grid Hunan Electric Power Company Limited Economical Technical Research Institute（国网湖南省电力有限公司经济技术研究院）
Online multi-object tracking (MOT) is a longstanding task for computer vision and intelligent vehicle platform. At present, the main paradigm is tracking-by-detection, and the main difficulty of this paradigm is how to associate current candidate detections with historical tracklets. However, in the MOT scenarios, each historical tracklet is composed of an object sequence, while each candidate detection is just a flat image, which lacks temporal features of the object sequence. The feature difference between current candidate detections and historical tracklets makes the object association muc…
Learning object-centric scene representations is essential for attaining structural understanding and abstraction of complex scenes. Yet, as current approaches for unsupervised object-centric representation learning are built upon either a stationary observer assumption or a static scene assumption, they often: i) suffer single-view spatial ambiguities, or ii) infer incorrectly or inaccurately object representations from dynamic scenes. To address this, we propose Dynamics-aware Multi-Object Network (DyMON), a method that broadens the scope of multi-view object-centric representation learning …
University of Rennes 1（雷恩第一大学）；INSERM（法国国家健康与医学研究院）；Gazi University（加齐大学）
Modeling and recognition of surgical activities poses an interesting research problem. Although a number of recent works studied automatic recognition of surgical activities, generalizability of these works across different tasks and different datasets remains a challenge. We introduce a modality that is robust to scene variation, and that is able to infer part information such as orientational and relative spatial relationships. The proposed modality is based on spatial temporal graph representations of surgical tools in videos, for surgical activity recognition. To explore its effectiveness,…
National Cheng Kung University（国立成功大学）；National Tsing Hua University（国立清华大学）；National Taiwan University（国立台湾大学）
Geometry-aware modules are widely applied in recent deep learning architectures for scene representation and rendering. However, these modules require intrinsic camera information that might not be obtained accurately. In this paper, we propose a Spatial Transformation Routing (STR) mechanism to model the spatial properties without applying any geometric prior. The STR mechanism treats the spatial transformation as the message passing process, and the relation between the view poses and the routing weights is modeled by an end-to-end trainable neural network. Besides, an Occupancy Concept Mapp…
University of Science and Technology of China（中国科学技术大学）；Huawei Inc.（华为公司）；Shanghai Jiao Tong University（上海交通大学）；Chinese Academy of Sciences（中国科学院）
Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation. This paper presents heterogeneous contrastive learning (HCL), an effective approach that adds spatial information to the encoding stage to alleviate the learning inconsistency between the contrastive objective and strong data augmentation operations. We demonstrate the effectiveness of HCL by showing that (i) it achieves higher accuracy in instance discrimination and (ii) it surpasses exis…
University of Notre Dame（圣母大学）；First Affiliated Hospital of Anhui Medical University（安徽医科大学第一附属医院）
High annotation costs and limited labels for dense 3D medical imaging tasks have recently motivated an assortment of 3D self-supervised pretraining methods that improve transfer learning performance. However, these methods commonly lack spatial awareness despite its centrality in enabling effective 3D image analysis. More specifically, position, scale, and orientation are not only informative but also automatically available when generating image crops for training. Yet, to date, no work has proposed a pretext task that distills all key spatial features. To fulfill this need, we develop a new …
The workflow of extracting features from images using convolutional neural networks (CNN) and generating captions with recurrent neural networks (RNN) has become a de-facto standard for image captioning task. However, since CNN features are originally designed for classification task, it is mostly concerned with the main conspicuous element of the image, and often fails to correctly convey information on local, secondary elements. We propose to incorporate coding with vector of locally aggregated descriptors (VLAD) on spatial pyramid for CNN features of sub-regions in order to generate image r…
University of Maryland（马里兰大学）；Snap Inc.（Snap公司）；Google Inc.（谷歌公司）
This paper proposes an automatic spatially-aware concept discovery approach using weakly labeled image-text data from shopping websites. We first fine-tune GoogleNet by jointly modeling clothing images and their corresponding descriptions in a visual-semantic embedding space. Then, for each attribute (word), we generate its spatially-aware representation by combining its semantic word vector representation with its spatial representation derived from the convolutional maps of the fine-tuned network. The resulting spatially-aware representations are further used to cluster attributes into multi…
In the majority of GAN architectures, the latent space is defined as a set of vectors of given dimensionality. Such representations are not easily interpretable and do not capture spatial information of image content directly. In this work, we define a family of spatial latent spaces for StyleGAN2, capable of capturing more details and representing images that are out-of-sample in terms of the number and arrangement of object parts, such as an image of multiple faces or a face with more than two eyes. We propose a method for encoding images into our spaces, together with an attribute model cap…
Zhejiang University（浙江大学）；DJI（大疆创新）；Shanghai Institute for Advanced Study of Zhejiang University（浙江大学上海高等研究院）；Shanghai AI Lab（上海人工智能实验室）
Bird's eye view (BEV) representation is a new perception formulation for autonomous driving, which is based on spatial fusion. Further, temporal fusion is also introduced in BEV representation and gains great success. In this work, we propose a new method that unifies both spatial and temporal fusion and merges them into a unified mathematical formulation. The unified fusion could not only provide a new perspective on BEV fusion but also brings new capabilities. With the proposed unified spatial-temporal fusion, our method could support long-range fusion, which is hard to achieve in convention…
Institute of Geographical Sciences, Remote Sensing and Geoinformatics, Freie Universität Berlin（柏林自由大学地理科学、遥感与地理信息研究所）
This paper presents a sparse representation-based classification approach with a novel dictionary construction procedure. By using the constructed dictionary sophisticated prior knowledge about the spatial nature of the image can be integrated. The approach is based on the assumption that each image patch can be factorized into characteristic spatial patterns, also called shapelets, and patch-specific spectral information. A set of shapelets is learned in an unsupervised way and spectral information are embodied by training samples. A combination of shapelets and spectral information are repre…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Self-attention has been successfully applied to video representation learning due to the effectiveness of modeling long range dependencies. Existing approaches build the dependencies merely by computing the pairwise correlations along spatial and temporal dimensions simultaneously. However, spatial correlations and temporal correlations represent different contextual information of scenes and temporal reasoning. Intuitively, learning spatial contextual information first will benefit temporal modeling. In this paper, we propose a separable self-attention (SSA) module, which models spatial and t…
Southwest University of Science and Technology（西南科技大学）；Civil Aviation Flight College of China（中国民用航空飞行学院）；Sichuan University（四川大学）
Images taken under low-light conditions tend to suffer from poor visibility, which can decrease image quality and even reduce the performance of the downstream tasks. It is hard for a CNN-based method to learn generalized features that can recover normal images from the ones under various unknow low-light conditions. In this paper, we propose to incorporate the contrastive learning into an illumination correction network to learn abstract representations to distinguish various low-light conditions in the representation space, with the purpose of enhancing the generalizability of the network. C…
Sequential manipulation tasks require a robot to perceive the state of an environment and plan a sequence of actions leading to a desired goal state. In such tasks, the ability to reason about spatial relations among object entities from raw sensor inputs is crucial in order to determine when a task has been completed and which actions can be executed. In this work, we propose SORNet (Spatial Object-Centric Representation Network), a framework for learning object-centric representations from RGB images conditioned on a set of object queries, represented as image patches called canonical object…
Unleashing Spatial Reasoning in Multimodal Large Language Models via Textual Representation Guided Reasoning
College of AI, Tsinghua University, Beijing, China（清华大学人工智能学院，北京，中国）；Shanghai Artificial Intelligence Laboratory, Shanghai, China（上海人工智能实验室，上海，中国）；The University of Tokyo, Tokyo, Japan（东京大学，东京，日本）
Renmin University of China（中国人民大学）；CSIRO（联邦科学与工业研究组织）
We propose a video feature representation learning framework called STAR-GNN, which applies a pluggable graph neural network component on a multi-scale lattice feature graph. The essence of STAR-GNN is to exploit both the temporal dynamics and spatial contents as well as visual connections between regions at different scales in the frames. It models a video with a lattice feature graph in which the nodes represent regions of different granularity, with weighted edges that represent the spatial and temporal links. The contextual nodes are aggregated simultaneously by graph neural networks with …
Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling
Institute of Trustworthy Embodied Artificial Intelligence (TEAI)（可信具身人工智能研究所）；Shanghai Key Laboratory of Multimodal Embodied AI（上海多模态具身人工智能重点实验室）；Sch. of Artificial Intelligence & Sch. of Computer Science, Shanghai Jiao Tong University（上海交通大学人工智能学院与计算机科学学院）；University of Science and Technology of China（中国科学技术大学）
University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
In this paper, we present an efficient spatial-temporal representation for video person re-identification (reID). Firstly, we propose a Bilateral Complementary Network (BiCnet) for spatial complementarity modeling. Specifically, BiCnet contains two branches. Detail Branch processes frames at original resolution to preserve the detailed visual clues, and Context Branch with a down-sampling strategy is employed to capture long-range contexts. On each branch, BiCnet appends multiple parallel and diverse attention modules to discover divergent body parts for consecutive frames, so as to obtain an …
University of Maryland（马里兰大学）；University of British Columbia（英属哥伦比亚大学）
We explore the power of spatial context as a self-supervisory signal for learning visual representations. In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch, within the same image, conditioned on their real-valued relative spatial offset. Unlike auto-encoders, that aim to encode and reconstruct original image patches, our network aims to encode and reconstruct intermediate representations of the spatially offset patches. As such, the network learns a spatially conditioned contextual representation. By testing pe…
We propose an unsupervised, mid-level representation for a generative model of scenes. The representation is mid-level in that it is neither per-pixel nor per-image; rather, scenes are modeled as a collection of spatial, depth-ordered "blobs" of features. Blobs are differentiably placed onto a feature grid that is decoded into an image by a generative adversarial network. Due to the spatial uniformity of blobs and the locality inherent to convolution, our network learns to associate different blobs with different entities in a scene and to arrange these blobs to capture scene layout. We demons…
Unlike standard object classification, where the image to be classified contains one or multiple instances of the same object, indoor scene classification is quite different since the image consists of multiple distinct objects. Further, these objects can be of varying sizes and are present across numerous spatial locations in different layouts. For automatic indoor scene categorization, large scale spatial layout deformations and scale variations are therefore two major challenges and the design of rich feature descriptors which are robust to these challenges is still an open problem. This pa…
The University of Tokyo（东京大学）；Preferred Networks, Inc.（Preferred Networks公司）
We present a novel CNN-based image editing strategy that allows the user to change the semantic information of an image over an arbitrary region by manipulating the feature-space representation of the image in a trained GAN model. We will present two variants of our strategy: (1) spatial conditional batch normalization (sCBN), a type of conditional batch normalization with user-specifiable spatial weight maps, and (2) feature-blending, a method of directly modifying the intermediate features. Our methods can be used to edit both artificial image and real image, and they both can be used togeth…
City University of Hong Kong（香港城市大学）；Kingsoft Cloud（金山云）
In this work, we propose a no-reference video quality assessment method, aiming to achieve high-generalization capability in cross-content, -resolution and -frame rate quality prediction. In particular, we evaluate the quality of a video by learning effective feature representations in spatial-temporal domain. In the spatial domain, to tackle the resolution and content variations, we impose the Gaussian distribution constraints on the quality features. The unified distribution can significantly reduce the domain gap between different video samples, resulting in a more generalized quality featu…
Guangdong University of Technology（广东工业大学）；University of Strathclyde（思克莱德大学）
Although extreme learning machine (ELM) has been successfully applied to a number of pattern recognition problems, it fails to pro-vide sufficient good results in hyperspectral image (HSI) classification due to two main drawbacks. The first is due to the random weights and bias of ELM, which may lead to ill-posed problems. The second is the lack of spatial information for classification. To tackle these two problems, in this paper, we propose a new framework for ELM based spectral-spatial classification of HSI, where probabilistic modelling with sparse representation and weighted composite fea…
We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it hierarchically to encourage multi-scale understanding. Motivated by their effectiveness in supervised learning, we first introduce spatial-temporal feature learning decoupling and hierarchical learning to the context of unsupervised video learning. We show by experiments that augmentations can be manipulated as regularization to guide the network to learn desired seman…
