Long-term temporal fusion is a crucial but often overlooked technique in camera-based Bird's-Eye-View (BEV) 3D perception. Existing methods are mostly in a parallel manner. While parallel fusion can benefit from long-term information, it suffers from increasing computational and memory overheads as the fusion window size grows. Alternatively, BEVFormer adopts a recurrent fusion pipeline so that history information can be efficiently integrated, yet it fails to benefit from longer temporal frames. In this paper, we explore an embarrassingly simple long-term recurrent fusion strategy built upon the LSS-based methods and find it already able to enjoy the merits from both sides, i.e., rich long-term information and efficient fusion pipeline. A temporal embedding module is further proposed to improve the model's robustness against occasionally missed frames in practical scenarios. We name this simple but effective fusing pipeline VideoBEV. Experimental results on the nuScenes benchmark show that VideoBEV obtains strong performance on various camera-based 3D perception tasks, including object detection (55.4\% mAP and 62.9\% NDS), segmentation (48.6\% vehicle mIoU), tracking (54.8\% AMOTA), and motion prediction (0.80m minADE and 0.463 EPA).
Berkeley Deep Drive（伯克利深度驾驶）；University of California, Berkeley（加州大学伯克利分校）
Deep convolutional neural networks (CNNs) have been shown to perform extremely well at a variety of tasks including subtasks of autonomous driving such as image segmentation and object classification. However, networks designed for these tasks typically require vast quantities of training data and long training periods to converge. We investigate the design rationale behind end-to-end driving network designs by proposing and comparing three small and computationally inexpensive deep end-to-end neural network models that generate driving control signals directly from input images. In contrast t…
OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perception
Autonomous Driving Development Center, Hyundai Motors（韩世汽车自动驾驶开发中心）；Department of Electrical Engineering, Hanyang University（翰阳大学电气工程系）；Interdisciplinary Program in Artificial Intelligence, Seoul National University（首尔国立大学人工智能跨学科项目）；Department of Electrical and Computer Engineering, Seoul National University（首尔国立大学电气与计算机工程系）
Autonomous and semi-autonomous vehicles' perception algorithms can encounter situations with erroneous object detection, such as misclassification of objects on the road, which can lead to safety violations and potentially fatal consequences. While there has been substantial work in the robustness of object detection algorithms and online metric learning, there is little research on benchmarking scoring metrics to determine any possible indicators of potential misclassification. An emphasis is put on exploring the potential of taking these scoring metrics online in order to allow the AV to mak…
Streaming perception is a critical task in autonomous driving that requires balancing the latency and accuracy of the autopilot system. However, current methods for streaming perception are limited as they only rely on the current and adjacent two frames to learn movement patterns. This restricts their ability to model complex scenes, often resulting in poor detection results. To address this limitation, we propose LongShortNet, a novel dual-path network that captures long-term temporal motion and integrates it with short-term spatial semantics for real-time perception. LongShortNet is notable…
Waabi；University of Toronto（多伦多大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；Cornell University（康奈尔大学）
Modern self-driving perception systems have been shown to improve upon processing complementary inputs such as LiDAR with images. In isolation, 2D images have been found to be extremely vulnerable to adversarial attacks. Yet, there have been limited studies on the adversarial robustness of multi-modal models that fuse LiDAR features with image features. Furthermore, existing works do not consider physically realizable perturbations that are consistent across the input modalities. In this paper, we showcase practical susceptibilities of multi-sensor detection by placing an adversarial object on…
LongSpace: Exploring Long-Horizon Spatial Memory from Perception to Recall in Video
Beijing University of Posts and Telecommunications（北京邮电大学）；Zhongguancun Academy（中关村学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；The Chinese University of Hong Kong（香港中文大学）；Xi’an Jiaotong University（西安交通大学）
We develop a novel framework to assess the risk of misperception in a traffic sign classification task in the presence of exogenous noise. We consider the problem in an autonomous driving setting, where visual input quality gradually improves due to improved resolution, and less noise since the distance to traffic signs decreases. Using the estimated perception statistics obtained using the standard classification algorithms, we aim to quantify the risk of misperception to mitigate the effects of imperfect visual observation. By exploring perception outputs, their expected high-level actions, …
Exploring Radar Data Representations in Autonomous Driving: A Comprehensive Review
School of Information Engineering, Yancheng Institute Technology（盐城理工学院信息工程学院）；Thrust of Artificial Intelligence and Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）人工智能与智能交通研究所）；Faculty of Science and Engineering, University of Liverpool（利物浦大学科学与工程学院）；School of Advanced Technology, Xi’an Jiaotong-Liverpool University（西安交通大学利物浦大学高级技术学院）；School of Information Science and Technology, Nantong University（南通大学信息科学与技术学院）
Uber Advanced Technologies Group（优步先进技术集团）；University of Toronto（多伦多大学）
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 ca…
Massachusetts Institute of Technology（麻省理工学院）；Buckingham Browne & Nichols School（白金汉布朗与尼科尔斯学校）；Fujitsu Limited（富士通有限公司）
Symmetry is omnipresent in nature and perceived by the visual system of many species, as it facilitates detecting ecologically important classes of objects in our environment. Symmetry perception requires abstraction of long-range spatial dependencies between image regions, and its underlying neural mechanisms remain elusive. In this paper, we evaluate Deep Neural Network (DNN) architectures on the task of learning symmetry perception from examples. We demonstrate that feed-forward DNNs that excel at modelling human performance on object recognition tasks, are unable to acquire a general notio…
We present a recurrent network for the 3D reconstruction of neurons that sequentially generates binary masks for every object in an image with spatio-temporal consistency. Our network models consistency in two parts: (i) local, which allows exploring non-occluding and temporally-adjacent object relationships with bi-directional recurrence. (ii) non-local, which allows exploring long-range object relationships in the temporal domain with skip connections. Our proposed network is end-to-end trainable from an input image to a sequence of object masks, and, compared to methods relying on object bo…
CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception
Institute for AI Industry Research, Tsinghua University（人工智能产业研究所，清华大学）；The Hong Kong Polytechnic University（香港理工大学）；The University of Hong Kong（香港大学）；School of Vehicle and Mobility, Tsinghua University（车辆与移动技术学院，清华大学）；Baidu Inc.（百度公司）
Tongji University（同济大学）；Technical University of Munich（慕尼黑工业大学）；ETH Zurich（苏黎世联邦理工学院）；fortiss GmbH（福蒂斯有限公司）
The rapid growth of IoT era is shaping the future of mobile services. Advanced communication technology enables a heterogeneous connectivity where mobile devices broadcast information to everything. Mobile applications such as robotics and vehicles connecting to cloud and surroundings transfer the short-range on-board sensor perception system to long-range mobile-sensing perception system. However, the mobile sensing perception brings new challenges for how to efficiently analyze and intelligently interpret the deluge of IoT data in mission- critical services. In this article, we model the cha…
Measuring the perception of visual content is a long-standing problem in computer vision. Many mathematical models have been developed to evaluate the look or quality of an image. Despite the effectiveness of such tools in quantifying degradations such as noise and blurriness levels, such quantification is loosely coupled with human language. When it comes to more abstract perception about the feel of visual content, existing methods can only rely on supervised models that are explicitly trained with labeled data collected via laborious user study. In this paper, we go beyond the conventional …
Visual Geometry Group, University of Oxford（牛津大学视觉几何组）
Modern discriminative predictors have been shown to match natural intelligences in specific perceptual tasks in image classification, object and part detection, boundary extraction, etc. However, a major advantage that natural intelligences still have is that they work well for "all" perceptual problems together, solving them efficiently and coherently in an "integrated manner". In order to capture some of these advantages in machine perception, we ask two questions: whether deep neural networks can learn universal image representations, useful not only for a single task but for all of them, a…
Modern feedforward convolutional neural networks (CNNs) can now solve some computer vision tasks at super-human levels. However, these networks only roughly mimic human visual perception. One difference from human vision is that they do not appear to perceive illusory contours (e.g. Kanizsa squares) in the same way humans do. Physiological evidence from visual cortex suggests that the perception of illusory contours could involve feedback connections. Would recurrent feedback neural networks perceive illusory contours like humans? In this work we equip a deep feedforward convolutional network …
German Aerospace Center (DLR)（德国航空航天中心）；Technical University of Munich (TUM)（慕尼黑工业大学）
Aerial image classification is of great significance in remote sensing community, and many researches have been conducted over the past few years. Among these studies, most of them focus on categorizing an image into one semantic label, while in the real world, an aerial image is often associated with multiple labels, e.g., multiple object-level labels in our case. Besides, a comprehensive picture of present objects in a given high resolution aerial image can provide more in-depth understanding of the studied region. For these reasons, aerial image multi-label classification has been attractin…
University of Modena and Reggio Emilia（摩德纳和雷焦艾米利亚大学）
Most recent state of the art architectures rely on combinations and variations of three approaches: convolutional, recurrent and self-attentive methods. Our work attempts in laying the basis for a new research direction for sequence modeling based upon the idea of modifying the sequence length. In order to do that, we propose a new method called "Expansion Mechanism" which transforms either dynamically or statically the input sequence into a new one featuring a different sequence length. Furthermore, we introduce a novel architecture that exploits such method and achieves competitive performan…
Exploring Temporal Event Cues for Dense Video Captioning in Cyclic Co-learning
School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）；Engineering Research Center of Sustainable Urban Intelligent Transportation, Ministry of Education, China（中国教育部可持续城市智能交通工程研究中心）
Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation
School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）；State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所信息安全国家重点实验室）；Beihang University（北京航空航天大学）；University of Chinese Academy of Sciences（中国科学院大学）；School of Cyber Science and Technology, Sun Yat-Sen University（中山大学网络空间科学与技术学院）
VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models
College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)（广东省人工智能与数字经济实验室（深圳））
University of British Columbia（英属哥伦比亚大学）；Department of Statistics, University of British Columbia（英属哥伦比亚大学统计系）；Department of Electrical and Computer Engineering, University of British Columbia（英属哥伦比亚大学电气与计算机工程系）；School of Information and Communications Engineering, Xi’an Jiaotong University（西安交通大学信息与通信工程学院）
Recently, generative adversarial networks (GANs) can generate photo-realistic fake facial images which are perceptually indistinguishable from real face photos, promoting research on fake face detection. Though fake face forensics can achieve high detection accuracy, their anti-forensic counterparts are less investigated. Here we explore more \textit{imperceptible} and \textit{transferable} anti-forensics for fake face imagery detection based on adversarial attacks. Since facial and background regions are often smooth, even small perturbation could cause noticeable perceptual impairment in fak…
Institute of Computing Technology, Chinese Academy of Sciences（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）；Peking University（北京大学）
Although significant achievements have been achieved by recurrent neural network (RNN) based video prediction methods, their performance in datasets with high resolutions is still far from satisfactory because of the information loss problem and the perception-insensitive mean square error (MSE) based loss functions. In this paper, we propose a Spatiotemporal Information-Preserving and Perception-Augmented Model (STIP) to solve the above two problems. To solve the information loss problem, the proposed model aims to preserve the spatiotemporal information for videos during the feature extracti…
Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Bonn（波恩大学）
Generating a robust representation of the environment is a crucial ability of learning agents. Deep learning based methods have greatly improved perception systems but still fail in challenging situations. These failures are often not solvable on the basis of a single image. In this work, we present a parameter-efficient temporal filtering concept which extends an existing single-frame segmentation model to work with multiple frames. The resulting recurrent architecture temporally filters representations on all abstraction levels in a hierarchical manner, while decoupling temporal dependencies…
Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations imperceptible is especially challenging for transfer-based black-box adversarial attacks. Often such adversarial examples can be easily spotted due to their unpleasantly poor visual qualities, which compromises the threat of adversarial attacks in practice. In this study, to improve the image quality of black-box adversarial examples perceptually, we propos…
University of Kent（肯特大学）；Universidad Autonoma de Madrid（马德里自治大学）
Biometrics on mobile devices has attracted a lot of attention in recent years as it is considered a user-friendly authentication method. This interest has also been motivated by the success of Deep Learning (DL). Architectures based on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been established to be convenient for the task, improving the performance and robustness in comparison to traditional machine learning techniques. However, some aspects must still be revisited and improved. To the best of our knowledge, this is the first article that intends to explor…
This paper focuses on two key problems for audio-visual emotion recognition in the video. One is the audio and visual streams temporal alignment for feature level fusion. The other one is locating and re-weighting the perception attentions in the whole audio-visual stream for better recognition. The Long Short Term Memory Recurrent Neural Network (LSTM-RNN) is employed as the main classification architecture. Firstly, soft attention mechanism aligns the audio and visual streams. Secondly, seven emotion embedding vectors, which are corresponding to each classification emotion type, are added to…
National University of Singapore（新加坡国立大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Goethe University Frankfurt（法兰克福大学）
Although media content is increasingly produced, distributed, and consumed in multiple combinations of modalities, how individual modalities contribute to the perceived emotion of a media item remains poorly understood. In this paper we present MusicVideos (MuVi), a novel dataset for affective multimedia content analysis to study how the auditory and visual modalities contribute to the perceived emotion of media. The data were collected by presenting music videos to participants in three conditions: music, visual, and audiovisual. Participants annotated the music videos for valence and arousal…
