Predicting future trajectories of traffic agents in highly interactive environments is an essential and challenging problem for the safe operation of autonomous driving systems. On the basis of the fact that self-driving vehicles are equipped with various types of sensors (e.g., LiDAR scanner, RGB camera, radar, etc.), we propose a Cross-Modal Embedding framework that aims to benefit from the use of multiple input modalities. At training time, our model learns to embed a set of complementary features in a shared latent space by jointly optimizing the objective functions across different types of input data. At test time, a single input modality (e.g., LiDAR data) is required to generate predictions from the input perspective (i.e., in the LiDAR space), while taking advantages from the model trained with multiple sensor modalities. An extensive evaluation is conducted to show the efficacy of the proposed framework using two benchmark driving datasets.
We address multi-modal trajectory forecasting of agents in unknown scenes by formulating it as a planning problem. We present an approach consisting of three models; a goal prediction model to identify potential goals of the agent, an inverse reinforcement learning model to plan optimal paths to each goal, and a trajectory generator to obtain future trajectories along the planned paths. Analysis of predictions on the Stanford drone dataset, shows generalizability of our approach to novel scenes.
Pedestrian trajectory prediction is an essential task in robotic applications such as autonomous driving and robot navigation. State-of-the-art trajectory predictors use a conditional variational autoencoder (CVAE) with recurrent neural networks (RNNs) to encode observed trajectories and decode multi-modal future trajectories. This process can suffer from accumulated errors over long prediction horizons (>=2 seconds). This paper presents BiTraP, a goal-conditioned bi-directional multi-modal trajectory prediction method based on the CVAE. BiTraP estimates the goal (end-point) of trajectories an…
TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving
LiAuto Inc（LiAuto公司）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动研究所）
Predicting future trajectories of surrounding obstacles is a crucial task for autonomous driving cars to achieve a high degree of road safety. There are several challenges in trajectory prediction in real-world traffic scenarios, including obeying traffic rules, dealing with social interactions, handling traffic of multi-class movement, and predicting multi-modal trajectories with probability. Inspired by people's natural habit of navigating traffic with attention to their goals and surroundings, this paper presents a unique dynamic graph attention network to solve all those challenges. The ne…
Honda Research Institute USA（美国本田研究所）；University of California, Berkeley（加州大学伯克利分校）；Sungkyunkwan University（成均馆大学）
Predicting future trajectories of traffic agents in highly interactive environments is an essential and challenging problem for the safe operation of autonomous driving systems. On the basis of the fact that self-driving vehicles are equipped with various types of sensors (e.g., LiDAR scanner, RGB camera, radar, etc.), we propose a Cross-Modal Embedding framework that aims to benefit from the use of multiple input modalities. At training time, our model learns to embed a set of complementary features in a shared latent space by jointly optimizing the objective functions across different types …
Johns Hopkins University（约翰斯·霍普金斯大学）；Samsung Strategy and Innovation Center, Samsung, Inc.（三星战略与创新中心，三星公司）
Trajectory prediction is crucial for autonomous vehicles. The planning system not only needs to know the current state of the surrounding objects but also their possible states in the future. As for vehicles, their trajectories are significantly influenced by the lane geometry and how to effectively use the lane information is of active interest. Most of the existing works use rasterized maps to explore road information, which does not distinguish different lanes. In this paper, we propose a novel instance-aware representation for lane representation. By integrating the lane features and traje…
University of California, Berkeley（加利福尼亚大学伯克利分校）；Toyota Research Institute（丰田研究所）；Stanford University（斯坦福大学）
Human trajectory forecasting with multiple socially interacting agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction. PECNet infers distant trajectory endpoints to assist in long-range multi-modal trajectory prediction. A novel non-local social pooling layer enables PECNet to infer diverse yet socially compliant trajectories. Additionally, we present a simple "truncation-trick" for improving few-shot multi-…
XVTP3D: Cross-view Trajectory Prediction Using Shared 3D Queries for Autonomous Driving
University of Chinese Academy of Sciences（中国科学院大学）；SenseTime（商汤科技）；Intuitive Surgical（直觉外科公司）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Evaluation Is All You Need for Multi-Modal Autonomous Driving
School of Vehicle and Mobility & College of AI, Tsinghua University（清华大学车辆与运载学院与人工智能学院）；Dongfeng Motor Corporation Research & Development Institute（东风汽车集团有限公司研发总院）
Part-Whole Relational Fusion Towards Multi-Modal Scene Understanding
School of Computer Science and Artificial Intelligence, Changzhou University（常州大学计算机与人工智能学院）；Department of Computer Science, University of Sheffield（谢菲尔德大学计算机系）
Southern University of Science and Technology（南方科技大学）；University of Birmingham（伯明翰大学）
Pedestrian trajectory forecasting is a fundamental task in multiple utility areas, such as self-driving, autonomous robots, and surveillance systems. The future trajectory forecasting is multi-modal, influenced by physical interaction with scene contexts and intricate social interactions among pedestrians. The mainly existing literature learns representations of social interactions by deep learning networks, while the explicit interaction patterns are not utilized. Different interaction patterns, such as following or collision avoiding, will generate different trends of next movement, thus, th…
Most existing cross-modality person re-identification works rely on discriminative modality-shared features for reducing cross-modality variations and intra-modality variations. Despite some initial success, such modality-shared appearance features cannot capture enough modality-invariant discriminative information due to a massive discrepancy between RGB and infrared images. To address this issue, on the top of appearance features, we further capture the modality-invariant relations among different person parts (referred to as modality-invariant relation features), which are the complement to…
Multi-modal generative models represent an important family of deep models, whose goal is to facilitate representation learning on data with multiple views or modalities. However, current deep multi-modal models focus on the inference of shared representations, while neglecting the important private aspects of data within individual modalities. In this paper, we introduce a disentangled multi-modal variational autoencoder (DMVAE) that utilizes disentangled VAE strategy to separate the private and shared latent spaces of multiple modalities. We specifically consider the instance where the laten…
Computational food analysis (CFA) naturally requires multi-modal evidence of a particular food, e.g., images, recipe text, etc. A key to making CFA possible is multi-modal shared representation learning, which aims to create a joint representation of the multiple views (text and image) of the data. In this work we propose a method for food domain cross-modal shared representation learning that preserves the vast semantic richness present in the food data. Our proposed method employs an effective transformer-based multilingual recipe encoder coupled with a traditional image embedding architectu…
Xidian University（西安电子科技大学）；Tencent AI Lab（腾讯人工智能实验室）；The University of Sydney（悉尼大学）
With explosive growth of data volume and ever-increasing diversity of data modalities, cross-modal similarity search, which conducts nearest neighbor search across different modalities, has been attracting increasing interest. This paper presents a deep compact code learning solution for efficient cross-modal similarity search. Many recent studies have proven that quantization-based approaches perform generally better than hashing-based approaches on single-modal similarity search. In this paper, we propose a deep quantization approach, which is among the early attempts of leveraging deep neur…
School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）；Key Laboratory of Electromagnetic Space Information, Chinese Academy of Science（中国科学院电磁空间信息重点实验室）；Damo Academy, Alibaba Group（阿里巴巴达摩院）；Baidu Research(USA)（百度研究院（美国））
Cross-modality person re-identification (cm-ReID) is a challenging but key technology for intelligent video analysis. Existing works mainly focus on learning common representation by embedding different modalities into a same feature space. However, only learning the common characteristics means great information loss, lowering the upper bound of feature distinctiveness. In this paper, we tackle the above limitation by proposing a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and the modality-sp…
Video relation detection problem refers to the detection of the relationship between different objects in videos, such as spatial relationship and action relationship. In this paper, we present video relation detection with trajectory-aware multi-modal features to solve this task. Considering the complexity of doing visual relation detection in videos, we decompose this task into three sub-tasks: object detection, trajectory proposal and relation prediction. We use the state-of-the-art object detection method to ensure the accuracy of object trajectory detection and multi-modal feature represe…
This paper considers the problem of multi-modal future trajectory forecast with ranking. Here, multi-modality and ranking refer to the multiple plausible path predictions and the confidence in those predictions, respectively. We propose Social-STAGE, Social interaction-aware Spatio-Temporal multi-Attention Graph convolution network with novel Evaluation for multi-modality. Our main contributions include analysis and formulation of multi-modality with ranking using interaction and multi-attention, and introduction of new metrics to evaluate the diversity and associated confidence of multi-modal…
Modeling the dynamics of people walking is a problem of long-standing interest in computer vision. Many previous works involving pedestrian trajectory prediction define a particular set of individual actions to implicitly model group actions. In this paper, we present a novel architecture named GP-Graph which has collective group representations for effective pedestrian trajectory prediction in crowded environments, and is compatible with all types of existing approaches. A key idea of GP-Graph is to model both individual-wise and group-wise relations as graph representations. To do this, GP-G…
German Aerospace Center (DLR)（德国航空航天中心）；Technical University of Munich (TUM)（慕尼黑工业大学）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立理工学院）；University of Iceland（冰岛大学）；RIKEN（日本理化学研究所）
Due to the ever-growing diversity of the data source, multi-modality feature learning has attracted more and more attention. However, most of these methods are designed by jointly learning feature representation from multi-modalities that exist in both training and test sets, yet they are less investigated in absence of certain modality in the test phase. To this end, in this letter, we propose to learn a shared feature space across multi-modalities in the training process. By this way, the out-of-sample from any of multi-modalities can be directly projected onto the learned space for a more e…
Imperial College London（帝国理工学院）；Tencent Robotics X（腾讯Robotics X）；Stanford University（斯坦福大学）；Shanghai Jiao Tong University（上海交通大学）
In this paper, we address the problem of forecasting the trajectory of an egocentric camera wearer (ego-person) in crowded spaces. The trajectory forecasting ability learned from the data of different camera wearers walking around in the real world can be transferred to assist visually impaired people in navigation, as well as to instill human navigation behaviours in mobile robots, enabling better human-robot interactions. To this end, a novel egocentric human trajectory forecasting dataset was constructed, containing real trajectories of people navigating in crowded spaces wearing a camera, …
Deep generative models have led to significant advances in cross-modal generation such as text-to-image synthesis. Training these models typically requires paired data with direct correspondence between modalities. We introduce the novel problem of translating instances from one modality to another without paired data by leveraging an intermediate modality shared by the two other modalities. To demonstrate this, we take the problem of translating images to speech. In this case, one could leverage disjoint datasets with one shared modality, e.g., image-text pairs and text-speech pairs, with tex…
Columbia University（哥伦比亚大学）；Microsoft Cloud and AI（微软云与人工智能部门）；Microsoft Research（微软研究院）
Large-scale multi-modal contrastive pre-training has demonstrated great utility to learn transferable features for a range of downstream tasks by mapping multiple modalities into a shared embedding space. Typically, this has employed separate encoders for each modality. However, recent work suggests that transformers can support learning across multiple modalities and allow knowledge sharing. Inspired by this, we investigate a variety of Modality-Shared Contrastive Language-Image Pre-training (MS-CLIP) frameworks. More specifically, we question how many parameters of a transformer model can be…
Multimodal prediction results are essential for trajectory prediction task as there is no single correct answer for the future. Previous frameworks can be divided into three categories: regression, generation and classification frameworks. However, these frameworks have weaknesses in different aspects so that they cannot model the multimodal prediction task comprehensively. In this paper, we present a novel insight along with a brand-new prediction framework by formulating multimodal prediction into three steps: modality clustering, classification and synthesis, and address the shortcomings of…
CmIVTP: Cross-modal Interaction-based Vessel Trajectory Prediction for Maritime Intelligence
Department of Logistics and Maritime Studies, the Hong Kong Polytechnic University（物流及海运研究系，香港理工大学）；Research Centre for ESG Advancement (RCESGA), the Hong Kong Polytechnic University（ESG进步研究中心（RCESGA），香港理工大学）；School of Navigation, Wuhan University of Technology（航海学院，武汉理工大学）
Shared and Private Information Learning in Multimodal Sentiment Analysis with Deep Modal Alignment and Self-supervised Multi-Task Learning
School of Information Science and Engineering, Shandong University（山东大学信息科学与工程学院）；School of Information Science and Engineering, Lanzhou University（兰州大学信息科学与工程学院）；Geography and Planning, Sun Yat-sen University（中山大学地理科学与规划学院）；Department of Military Medical Psychology, Air Force Medical University（空军军医大学军事医学心理学系）；National University of Singapore（新加坡国立大学）；Assets and Laboratory Management Department, Shandong University（山东大学资产与实验室管理部）
In this paper, we propose THOMAS, a joint multi-agent trajectory prediction framework allowing for an efficient and consistent prediction of multi-agent multi-modal trajectories. We present a unified model architecture for simultaneous agent future heatmap estimation, in which we leverage hierarchical and sparse image generation for fast and memory-efficient inference. We propose a learnable trajectory recombination model that takes as input a set of predicted trajectories for each agent and outputs its consistent reordered recombination. This recombination module is able to realign the initia…
Dual-Stream Cross-Modal Representation Learning via Residual Semantic Decorrelation
School of Information Science & Engineering, Shandong Normal University（信息科学与工程学院，山东师范大学）；Tajikistan State University of Law, Business Sughd（塔吉克斯坦法律、商业大学，苏赫德）；Tajik State University of Law, Business and Politics Sughd（塔吉克斯坦法律、商业与政治大学，苏赫德）
Variational autoencoder (VAE) has widely been utilized for modeling data distributions because it is theoretically elegant, easy to train, and has nice manifold representations. However, when applied to image reconstruction and synthesis tasks, VAE shows the limitation that the generated sample tends to be blurry. We observe that a similar problem, in which the generated trajectory is located between adjacent lanes, often arises in VAE-based trajectory forecasting models. To mitigate this problem, we introduce a hierarchical latent structure into the VAE-based forecasting model. Based on the a…
Robust Harmful Meme Detection under Missing Modalities via Shared Representation Learning
Johannes Kepler University（约翰内斯·开普勒大学）；Aalto University（阿alto大学）；University of Michigan-Flint（密歇根大学弗林特分校）；Macquarie University（麦考瑞大学）；Institute of Computational Perception, Johannes Kepler University Linz（计算感知研究所，约翰内斯·开普勒大学林茨）；Linz Institute of Technology（林茨技术研究所）
To safely and efficiently navigate through complex traffic scenarios, autonomous vehicles need to have the ability to predict the future motion of surrounding vehicles. Multiple interacting agents, the multi-modal nature of driver behavior, and the inherent uncertainty involved in the task make motion prediction of surrounding vehicles a challenging problem. In this paper, we present an LSTM model for interaction aware motion prediction of surrounding vehicles on freeways. Our model assigns confidence values to maneuvers being performed by vehicles and outputs a multi-modal distribution over f…
Indian Institute of Technology Kanpur（坎普尔印度理工学院）；TensorTour Inc.（TensorTour公司）
Cross-modal retrieval is generally performed by projecting and aligning the data from two different modalities onto a shared representation space. This shared space often also acts as a bridge for translating the modalities. We address the problem of learning such representation space by proposing and exploiting the property of Discriminative Semantic Transitive Consistency -- ensuring that the data points are correctly classified even after being transferred to the other modality. Along with semantic transitive consistency, we also enforce the traditional distance minimizing constraint which …
Shanghai Jiao Tong University（上海交通大学）；University of Southern California（南加州大学）；School of Mechanical Engineering, Nanjing University of Science and Technology（南京理工大学机械工程学院）
