In this paper, we tackle the problem of detecting objects in 3D and forecasting their future motion in the context of self-driving. Towards this goal, we design a novel approach that explicitly takes into account the interactions between actors. To capture their spatial-temporal dependencies, we propose a recurrent neural network with a novel Transformer architecture, which we call the Interaction Transformer. Importantly, our model can be trained end-to-end, and runs in real-time. We validate our approach on two challenging real-world datasets: ATG4D and nuScenes. We show that our approach can outperform the state-of-the-art on both datasets. In particular, we significantly improve the social compliance between the estimated future trajectories, resulting in far fewer collisions between the predicted actors.
FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems
Fraunhofer Institute for Transportation and Infrastructure Systems IVI（弗劳恩霍夫交通与基础设施系统研究所IVI）；Technical University of Munich（慕尼黑工业大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Technische Hochschule Ingolstadt（英戈尔施塔特应用技术大学）
WD-DETR: Wavelet Denoising-Enhanced Real-Time Object Detection Transformer for Robot Perception with Event Cameras
School of Aeronautic Science and Engineering, Beihang University（航空科学与工程学院，北京航空航天大学）；Hangzhou Innovation Institute of Beihang University（北京航空航天大学杭州创新研究院）；Institute of Unmanned System, Beihang University（无人系统研究院，北京航空航天大学）；Tianmushan Laboratory Xixi Octagon City（天门山实验室西溪八角城）
针对事件相机密集表示噪声导致漏检的问题，提出 WD-DETR，通过小波去噪骨干、Transformer 检测头和 DRCB 混合编码器提升精度，并在 Jetson Orin NX 上实现约35 FPS实时推理。
Robotics has long been a field riddled with complex systems architectures whose modules and connections, whether traditional or learning-based, require significant human expertise and prior knowledge. Inspired by large pre-trained language models, this work introduces a paradigm for pre-training a general purpose representation that can serve as a starting point for multiple tasks on a given robot. We present the Perception-Action Causal Transformer (PACT), a generative transformer-based architecture that aims to build representations directly from robot data in a self-supervised fashion. Thro…
Cornell University（康奈尔大学）；The Ohio State University（俄亥俄州立大学）
Self-driving cars must detect vehicles, pedestrians, and other traffic participants accurately to operate safely. Small, far-away, or highly occluded objects are particularly challenging because there is limited information in the LiDAR point clouds for detecting them. To address this challenge, we leverage valuable information from the past: in particular, data collected in past traversals of the same scene. We posit that these past data, which are typically discarded, provide rich contextual information for disambiguating the above-mentioned challenging cases. To this end, we propose a novel…
Understanding manipulation scenarios allows intelligent robots to plan for appropriate actions to complete a manipulation task successfully. It is essential for intelligent robots to semantically interpret manipulation knowledge by describing entities, relations and attributes in a structural manner. In this paper, we propose an implementing framework to generate high-level conceptual dynamic knowledge graphs from video clips. A combination of a Vision-Language model and an ontology system, in correspondence with visual perception and contextual semantics, is used to represent robot manipulati…
University of Arkansas（阿肯色大学）；FPT Software（FPT软件公司）
Video understanding is a growing field and a subject of intense research, which includes many interesting tasks to understanding both spatial and temporal information, e.g., action detection, action recognition, video captioning, video retrieval. One of the most challenging problems in video understanding is dealing with feature extraction, i.e. extract contextual visual representation from given untrimmed video due to the long and complicated temporal structure of unconstrained videos. Different from existing approaches, which apply a pre-trained backbone network as a black-box to extract vis…
University of California, Los Angeles（加州大学洛杉矶分校）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google Research（谷歌研究院）；University of California, Merced（加州大学默塞德分校）
In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles. We present a robust cooperative perception framework with V2X communication using a novel vision Transformer. Specifically, we build a holistic attention model, namely V2X-ViT, to effectively fuse information across on-road agents (i.e., vehicles and infrastructure). V2X-ViT consists of alternating layers of heterogeneous multi-agent self-attention and multi-scale window self-attention, which captures inter-agent interaction and per-agent spat…
Conservatoire National des Arts et Métiers（法国国立工艺学院）；IRCAD（消化外科研究所）；Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；ISIR（巴黎智能系统与机器人研究所）
Transformers have proved to be very effective for visual recognition tasks. In particular, vision transformers construct compressed global representations through self-attention and learnable class tokens. Multi-resolution transformers have shown recent successes in semantic segmentation but can only capture local interactions in high-resolution feature maps. This paper extends the notion of global tokens to build GLobal Attention Multi-resolution (GLAM) transformers. GLAM is a generic module that can be integrated into most existing transformer backbones. GLAM includes learnable global tokens…
Evaluating Graphical Perception Capabilities of Vision Transformers
Viscom Group, Institute of Media Informatics, Ulm University（Viscom集团，媒体信息学研究所，乌尔姆大学）；ViRVIG Group, Universitat Politècnica de Catalunya - BarcelonaTech（ViRVIG集团，巴塞罗那技术大学-加泰罗尼亚理工大学）；Ulm University（乌尔姆大学）
Tongji University（同济大学）；National University of Singapore（新加坡国立大学）；Lenovo Research（联想研究院）
Diagram object detection is the key basis of practical applications such as textbook question answering. Because the diagram mainly consists of simple lines and color blocks, its visual features are sparser than those of natural images. In addition, diagrams usually express diverse knowledge, in which there are many low-frequency object categories in diagrams. These lead to the fact that traditional data-driven detection model is not suitable for diagrams. In this work, we propose a gestalt-perception transformer model for diagram object detection, which is based on an encoder-decoder architec…
Transformer with self-attention has led to the revolutionizing of natural language processing field, and recently inspires the emergence of Transformer-style architecture design with competitive results in numerous computer vision tasks. Nevertheless, most of existing designs directly employ self-attention over a 2D feature map to obtain the attention matrix based on pairs of isolated queries and keys at each spatial location, but leave the rich contexts among neighbor keys under-exploited. In this work, we design a novel Transformer-style module, i.e., Contextual Transformer (CoT) block, for …
Numerous significant progress on fisheye image rectification has been achieved through CNN. Nevertheless, constrained by a fixed receptive field, the global distribution and the local symmetry of the distortion have not been fully exploited. To leverage these two characteristics, we introduced Fishformer that processes the fisheye image as a sequence to enhance global and local perception. We tuned the Transformer according to the structural properties of fisheye images. First, the uneven distortion distribution in patches generated by the existing square slicing method confuses the network, r…
Although autoregressive models have achieved promising results on image generation, their unidirectional generation process prevents the resultant images from fully reflecting global contexts. To address the issue, we propose an effective image generation framework of Draft-and-Revise with Contextual RQ-transformer to consider global contexts during the generation process. As a generalized VQ-VAE, RQ-VAE first represents a high-resolution image as a sequence of discrete code stacks. After code stacks in the sequence are randomly masked, Contextual RQ-Transformer is trained to infill the masked…
Tianjin University（天津大学）；Sichuan University（四川大学）；Huazhong University of Science and Technology（华中科技大学）；Chinese Academy of Sciences（中国科学院）
Temporal action localization aims to predict the boundary and category of each action instance in untrimmed long videos. Most of previous methods based on anchors or proposals neglect the global-local context interaction in entire video sequences. Besides, their multi-stage designs cannot generate action boundaries and categories straightforwardly. To address the above issues, this paper proposes a end-to-end model, called Adaptive Perception transformer (AdaPerFormer for short). Specifically, AdaPerFormer explores a dual-branch attention mechanism. One branch takes care of the global percepti…
Transformer-based visual object tracking has been utilized extensively. However, the Transformer structure is lack of enough inductive bias. In addition, only focusing on encoding the global feature does harm to modeling local details, which restricts the capability of tracking in aerial robots. Specifically, with local-modeling to global-search mechanism, the proposed tracker replaces the global encoder by a novel local-recognition encoder. In the employed encoder, a local-recognition attention and a local element correction network are carefully designed for reducing the global redundant inf…
Camera and radar sensors have significant advantages in cost, reliability, and maintenance compared to LiDAR. Existing fusion methods often fuse the outputs of single modalities at the result-level, called the late fusion strategy. This can benefit from using off-the-shelf single sensor detection algorithms, but late fusion cannot fully exploit the complementary properties of sensors, thus having limited performance despite the huge potential of camera-radar fusion. Here we propose a novel proposal-level early fusion approach that effectively exploits both spatial and contextual properties of …
Active perception describes a broad class of techniques that couple planning and perception systems to move the robot in a way to give the robot more information about the environment. In most robotic systems, perception is typically independent of motion planning. For example, traditional object detection is passive: it operates only on the images it receives. However, we have a chance to improve the results if we allow planning to consume detection signals and move the robot to collect views that maximize the quality of the results. In this paper, we use reinforcement learning (RL) methods t…
RWTH Aachen University（亚琛工业大学）；Iran University of Science and Technology（伊朗科技大学）；Fraunhofer Institute for Digital Medicine MEVIS（弗劳恩霍夫数字医学MEVIS研究所）
Currently, convolutional neural networks (CNN) (e.g., U-Net) have become the de facto standard and attained immense success in medical image segmentation. However, as a downside, CNN based methods are a double-edged sword as they fail to build long-range dependencies and global context connections due to the limited receptive field that stems from the intrinsic characteristics of the convolution operation. Hence, recent articles have exploited Transformer variants for medical image segmentation tasks which open up great opportunities due to their innate capability of capturing long-range corre…
3D single object tracking plays an essential role in many applications, such as autonomous driving. It remains a challenging problem due to the large appearance variation and the sparsity of points caused by occlusion and limited sensor capabilities. Therefore, contextual information across two consecutive frames is crucial for effective object tracking. However, points containing such useful information are often overlooked and cropped out in existing methods, leading to insufficient use of important contextual knowledge. To address this issue, we propose CXTrack, a novel transformer-based ne…
Chongqing University of Posts and Telecommunications（重庆邮电大学）；Xidian University（西安电子科技大学）
Very high-resolution (VHR) remote sensing (RS) image classification is the fundamental task for RS image analysis and understanding. Recently, transformer-based models demonstrated outstanding potential for learning high-order contextual relationships from natural images with general resolution (224x224 pixels) and achieved remarkable results on general image classification tasks. However, the complexity of the naive transformer grows quadratically with the increase in image size, which prevents transformer-based models from VHR RS image (500x500 pixels) classification and other computationall…
Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
In this work, we consider the problem of learning a perception model for monocular robot navigation using few annotated images. Using a Vision Transformer (ViT) pretrained with a label-free self-supervised method, we successfully train a coarse image segmentation model for the Duckietown environment using 70 training images. Our model performs coarse image segmentation at the 8x8 patch level, and the inference resolution can be adjusted to balance prediction granularity and real-time perception constraints. We study how best to adapt a ViT to our task and environment, and find that some lightw…
Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院智能信息处理重点实验室，中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Microsoft Research Asia（微软亚洲研究院）
In this paper, we address the semantic segmentation problem with a focus on the context aggregation strategy. Our motivation is that the label of a pixel is the category of the object that the pixel belongs to. We present a simple yet effective approach, object-contextual representations, characterizing a pixel by exploiting the representation of the corresponding object class. First, we learn object regions under the supervision of ground-truth segmentation. Second, we compute the object region representation by aggregating the representations of the pixels lying in the object region. Last, %…
GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding
Cyber Security Research Center (CYSREN), Nanyang Technological University（南洋理工大学网络安全研究中心（CYSREN））；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Institute of Semiconductors, Chinese Academy of Sciences（中国科学院半导体研究所）
Rethinking Local Perception in Lightweight Vision Transformer
Tsinghua University（清华大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Recently, the problem of traffic accident risk forecasting has been getting the attention of the intelligent transportation systems community due to its significant impact on traffic clearance. This problem is commonly tackled in the literature by using data-driven approaches that model the spatial and temporal incident impact, since they were shown to be crucial for the traffic accident risk forecasting problem. To achieve this, most approaches build different architectures to capture the spatio-temporal correlations features, making them inefficient for large traffic accident datasets. Thus,…
Harnessing Lightweight Transformer with Contextual Synergic Enhancement for Efficient 3D Medical Image Segmentation
Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong SAR（电子工程系，香港中文大学（深圳）Hong Kong SAR）；Centre for Artificial Intelligence and Robotics (CAIR), Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences, Hong Kong SAR（人工智能与机器人中心（CAIR），香港科学与创新研究院，中国科学院，Hong Kong SAR）
Yantai University（烟台大学）；University of Rochester（罗切斯特大学）；The Chinese University of Hong Kong（香港中文大学）；Fudan University（复旦大学）；The Hong Kong Polytechnic University（香港理工大学）
Magnetic resonance imaging (MRI) can present multi-contrast images of the same anatomical structures, enabling multi-contrast super-resolution (SR) techniques. Compared with SR reconstruction using a single-contrast, multi-contrast SR reconstruction is promising to yield SR images with higher quality by leveraging diverse yet complementary information embedded in different imaging modalities. However, existing methods still have two shortcomings: (1) they neglect that the multi-contrast features at different scales contain different anatomical details and hence lack effective mechanisms to mat…
The Chinese University of Hong Kong（香港中文大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Reconstructing the scene of robotic surgery from the stereo endoscopic video is an important and promising topic in surgical data science, which potentially supports many applications such as surgical visual perception, robotic surgery education and intra-operative context awareness. However, current methods are mostly restricted to reconstructing static anatomy assuming no tissue deformation, tool occlusion and de-occlusion, and camera movement. However, these assumptions are not always satisfied in minimal invasive robotic surgeries. In this work, we present an efficient reconstruction pipel…
The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Southern University of Science and Technology（南方科技大学）
Compared with the visual grounding on 2D images, the natural-language-guided 3D object localization on point clouds is more challenging. In this paper, we propose a new model, named InstanceRefer, to achieve a superior 3D visual grounding through the grounding-by-matching strategy. In practice, our model first predicts the target category from the language descriptions using a simple language classification model. Then, based on the category, our model sifts out a small number of instance candidates (usually less than 20) from the panoptic segmentation of point clouds. Thus, the non-trivial 3D…
The Chinese University of Hong Kong（香港中文大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Communication University of China（中国传媒大学）；Nanjing University（南京大学）
The ability to choose an appropriate camera view among multiple cameras plays a vital role in TV shows delivery. But it is hard to figure out the statistical pattern and apply intelligent processing due to the lack of high-quality training data. To solve this issue, we first collect a novel benchmark on this setting with four diverse scenarios including concerts, sports games, gala shows, and contests, where each scenario contains 6 synchronized tracks recorded by different cameras. It contains 88-hour raw videos that contribute to the 14-hour edited videos. Based on this benchmark, we further…
Video Anomaly Detection(VAD) has been traditionally tackled in two main methodologies: the reconstruction-based approach and the prediction-based one. As the reconstruction-based methods learn to generalize the input image, the model merely learns an identity function and strongly causes the problem called generalizing issue. On the other hand, since the prediction-based ones learn to predict a future frame given several previous frames, they are less sensitive to the generalizing issue. However, it is still uncertain if the model can learn the spatio-temporal context of a video. Our intuition…
RETR: Multi-View Radar Detection Transformer for Indoor Perception
Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室（MERL））；University of Bologna（博洛尼亚大学）；Information Technology R&D Center (ITC), Mitsubishi Electric Corporation（三菱电机公司信息技术研发中心（ITC））
Tokyo Institute of Technology（东京工业大学）；Baidu Inc.（百度公司）；The University of Sydney（悉尼大学）；Monash University（莫纳什大学）；Nanyang Technological University（南洋理工大学）
Previous studies have explored generating accurately lip-synced talking faces for arbitrary targets given audio conditions. However, most of them deform or generate the whole facial area, leading to non-realistic results. In this work, we delve into the formulation of altering only the mouth shapes of the target person. This requires masking a large percentage of the original image and seamlessly inpainting it with the aid of audio and reference frames. To this end, we propose the Audio-Visual Context-Aware Transformer (AV-CAT) framework, which produces accurate lip-sync with photo-realistic q…
Brain Tumor Segmentation in MRI Images with 3D U-Net and Contextual Transformer
University of Information Technology（信息科技大学）；Vietnam National University（越南国家大学）；College of Technology and Design, University of Economics Ho Chi Minh City（胡志明市经济大学技术与设计学院）；Ho Chi Minh City Open University（胡志明市开放大学）
Northeastern University（东北大学）；Shenyang University of Technology（沈阳工业大学）；The Chinese University of Hong Kong（香港中文大学）；Second Affiliated Hospital of Dalian Medical University（大连医科大学附属第二医院）；Central Hospital Affiliated to Shenyang Medical College（沈阳医学院附属中心医院）
Accurate airway extraction from computed tomography (CT) images is a critical step for planning navigation bronchoscopy and quantitative assessment of airway-related chronic obstructive pulmonary disease (COPD). The existing methods are challenging to sufficiently segment the airway, especially the high-generation airway, with the constraint of the limited label and cannot meet the clinical use in COPD. We propose a novel two-stage 3D contextual transformer-based U-Net for airway segmentation using CT images. The method consists of two stages, performing initial and refined airway segmentation…
EviViT: Evidence-Adaptive Vision Transformers for Fine-Grained Perception
Tsinghua University（清华大学）；Peng Cheng Laboratory（鹏城实验室）；The Hong Kong University of Science and Technology（香港科技大学）；LMMs-Lab；Beijing Institute of Technology（北京理工大学）；University of New South Wales（新南威尔士大学）
