Youfu Li

Bochen Xie, Yongjian Deng, Zhanpeng Shao et al.

Event cameras are neuromorphic vision sensors that record a scene as sparse and asynchronous event streams. Most event-based methods project events into dense frames and process them using conventional vision models, resulting in high computational complexity. A recent trend is to develop point-based networks that achieve efficient event processing by learning sparse representations. However, existing works may lack robust local information aggregators and effective feature interaction operations, thus limiting their modeling capabilities. To this end, we propose an attention-aware model named Event Voxel Set Transformer (EVSTr) for efficient spatiotemporal representation learning on event streams. It first converts the event stream into voxel sets and then hierarchically aggregates voxel features to obtain robust representations. The core of EVSTr is an event voxel transformer encoder that consists of two well-designed components, including the Multi-Scale Neighbor Embedding Layer (MNEL) for local information aggregation and the Voxel Self-Attention Layer (VSAL) for global feature interaction. Enabling the network to incorporate a long-range temporal structure, we introduce a segment modeling strategy (S$^{2}$TM) to learn motion patterns from a sequence of segmented voxel sets. The proposed model is evaluated on two recognition tasks, including object classification and action recognition. To provide a convincing model evaluation, we present a new event-based action recognition dataset (NeuroHAR) recorded in challenging scenarios. Comprehensive experiments show that EVSTr achieves state-of-the-art performance while maintaining low model complexity.

Zhanpeng Shao, Wen Zhou, Wuzhen Wang et al.

Event camera is an emerging bio-inspired vision sensors that report per-pixel brightness changes asynchronously. It holds noticeable advantage of high dynamic range, high speed response, and low power budget that enable it to best capture local motions in uncontrolled environments. This motivates us to unlock the potential of event cameras for human pose estimation, as the human pose estimation with event cameras is rarely explored. Due to the novel paradigm shift from conventional frame-based cameras, however, event signals in a time interval contain very limited information, as event cameras can only capture the moving body parts and ignores those static body parts, resulting in some parts to be incomplete or even disappeared in the time interval. This paper proposes a novel densely connected recurrent architecture to address the problem of incomplete information. By this recurrent architecture, we can explicitly model not only the sequential but also non-sequential geometric consistency across time steps to accumulate information from previous frames to recover the entire human bodies, achieving a stable and accurate human pose estimation from event data. Moreover, to better evaluate our model, we collect a large scale multimodal event-based dataset that comes with human pose annotations, which is by far the most challenging one to the best of our knowledge. The experimental results on two public datasets and our own dataset demonstrate the effectiveness and strength of our approach. Code can be available online for facilitating the future research.

Yongjian Deng, Hao Chen, Bochen Xie et al.

Recent advances in event-based research prioritize sparsity and temporal precision. Approaches using dense frame-based representations processed via well-pretrained CNNs are being replaced by the use of sparse point-based representations learned through graph CNNs (GCN). Yet, the efficacy of these graph methods is far behind their frame-based counterparts with two limitations. ($i$) Biased graph construction without carefully integrating variant attributes ($i.e.$, semantics, spatial and temporal cues) for each vertex, leading to imprecise graph representation. ($ii$) Deficient learning because of the lack of well-pretrained models available. Here we solve the first problem by proposing a new event-based GCN (EDGCN), with a dynamic aggregation module to integrate all attributes of vertices adaptively. To address the second problem, we introduce a novel learning framework called cross-representation distillation (CRD), which leverages the dense representation of events as a cross-representation auxiliary to provide additional supervision and prior knowledge for the event graph. This frame-to-graph distillation allows us to benefit from the large-scale priors provided by CNNs while still retaining the advantages of graph-based models. Extensive experiments show our model and learning framework are effective and generalize well across multiple vision tasks.

Qianang Zhou, JunLin Xiong, Youfu Li

The non-maximum suppression (NMS) is widely used in frame-based tasks as an essential post-processing algorithm. However, event-based NMS either has high computational complexity or leads to frequent discontinuities. As a result, the performance of event-based corner detectors is limited. This paper proposes a general-purpose asynchronous non-maximum suppression pipeline (ANMS), and applies it to corner event detection. The proposed pipeline extract fine feature stream from the output of original detectors and adapts to the speed of motion. The ANMS runs directly on the asynchronous event stream with extremely low latency, which hardly affects the speed of original detectors. Additionally, we evaluate the DAVIS-based ground-truth labeling method to fill the gap between frame and event. Evaluation on public dataset indicates that the proposed ANMS pipeline significantly improves the performance of three classical asynchronous detectors with negligible latency. More importantly, the proposed ANMS framework is a natural extension of NMS, which is applicable to other asynchronous scoring tasks for event cameras.

Yu Liu, Zhijie Liu, Zedong Yang et al.

Predicting pedestrian crossing intentions is crucial for the navigation of mobile robots and intelligent vehicles. Although recent deep learning-based models have shown significant success in forecasting intentions, few consider incomplete observation under occlusion scenarios. To tackle this challenge, we propose an Occlusion-Aware Diffusion Model (ODM) that reconstructs occluded motion patterns and leverages them to guide future intention prediction. During the denoising stage, we introduce an occlusion-aware diffusion transformer architecture to estimate noise features associated with occluded patterns, thereby enhancing the model's ability to capture contextual relationships in occluded semantic scenarios. Furthermore, an occlusion mask-guided reverse process is introduced to effectively utilize observation information, reducing the accumulation of prediction errors and enhancing the accuracy of reconstructed motion features. The performance of the proposed method under various occlusion scenarios is comprehensively evaluated and compared with existing methods on popular benchmarks, namely PIE and JAAD. Extensive experimental results demonstrate that the proposed method achieves more robust performance than existing methods in the literature.

Yu Liu, Yuexin Zhang, Kunming Li et al.

Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles. Accurately forecasting crowd trajectories is challenging due to the uncertain nature of human motions in different environments. For training, recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians, among others. This can limit the prediction performance across various scenarios since the discrepancies between training datasets have not been properly incorporated. To overcome this limitation, this paper proposes a graph transformer structure to improve prediction performance, capturing the differences between the various sites and scenarios contained in the datasets. In particular, a self-attention mechanism and a domain adaption module have been designed to improve the generalization ability of the model. Moreover, an additional metric considering cross-dataset sequences is introduced for training and performance evaluation purposes. The proposed framework is validated and compared against existing methods using popular public datasets, i.e., ETH and UCY. Experimental results demonstrate the improved performance of our proposed scheme.

Qianang Zhou, Junhui Hou, Meiyi Yang et al.

Current optical flow methods exploit the stable appearance of frame (or RGB) data to establish robust correspondences across time. Event cameras, on the other hand, provide high-temporal-resolution motion cues and excel in challenging scenarios. These complementary characteristics underscore the potential of integrating frame and event data for optical flow estimation. However, most cross-modal approaches fail to fully utilize the complementary advantages, relying instead on simply stacking information. This study introduces a novel approach that uses a spatially dense modality to guide the aggregation of the temporally dense event modality, achieving effective cross-modal fusion. Specifically, we propose an event-enhanced frame representation that preserves the rich texture of frames and the basic structure of events. We use the enhanced representation as the guiding modality and employ events to capture temporally dense motion information. The robust motion features derived from the guiding modality direct the aggregation of motion information from events. To further enhance fusion, we propose a transformer-based module that complements sparse event motion features with spatially rich frame information and enhances global information propagation. Additionally, a mix-fusion encoder is designed to extract comprehensive spatiotemporal contextual features from both modalities. Extensive experiments on the MVSEC and DSEC-Flow datasets demonstrate the effectiveness of our framework. Leveraging the complementary strengths of frames and events, our method achieves leading performance on the DSEC-Flow dataset. Compared to the event-only model, frame guidance improves accuracy by 10\%. Furthermore, it outperforms the state-of-the-art fusion-based method with a 4\% accuracy gain and a 45\% reduction in inference time.

Qianang Zhou, Zhiyu Zhu, Junhui Hou et al.

Event cameras hold significant promise for high-temporal-resolution (HTR) motion estimation. However, estimating event-based HTR optical flow faces two key challenges: the absence of HTR ground-truth data and the intrinsic sparsity of event data. Most existing approaches rely on the flow accumulation paradigms to indirectly supervise intermediate flows, often resulting in accumulation errors and optimization difficulties. To address these challenges, we propose a residual-based paradigm for estimating HTR optical flow with event data. Our approach separates HTR flow estimation into two stages: global linear motion estimation and HTR residual flow refinement. The residual paradigm effectively mitigates the impacts of event sparsity on optimization and is compatible with any LTR algorithm. Next, to address the challenge posed by the absence of HTR ground truth, we incorporate novel learning strategies. Specifically, we initially employ a shared refiner to estimate the residual flows, enabling both LTR supervision and HTR inference. Subsequently, we introduce regional noise to simulate the residual patterns of intermediate flows, facilitating the adaptation from LTR supervision to HTR inference. Additionally, we show that the noise-based strategy supports in-domain self-supervised training. Comprehensive experimental results demonstrate that our approach achieves state-of-the-art accuracy in both LTR and HTR metrics, highlighting its effectiveness and superiority.

Yuhan Liu, Yongjian Deng, Hao Chen et al.

Video frame interpolation, the process of synthesizing intermediate frames between sequential video frames, has made remarkable progress with the use of event cameras. These sensors, with microsecond-level temporal resolution, fill information gaps between frames by providing precise motion cues. However, contemporary Event-Based Video Frame Interpolation (E-VFI) techniques often neglect the fact that event data primarily supply high-confidence features at scene edges during multi-modal feature fusion, thereby diminishing the role of event signals in optical flow (OF) estimation and warping refinement. To address this overlooked aspect, we introduce an end-to-end E-VFI learning method (referred to as EGMR) to efficiently utilize edge features from event signals for motion flow and warping enhancement. Our method incorporates an Edge Guided Attentive (EGA) module, which rectifies estimated video motion through attentive aggregation based on the local correlation of multi-modal features in a coarse-to-fine strategy. Moreover, given that event data can provide accurate visual references at scene edges between consecutive frames, we introduce a learned visibility map derived from event data to adaptively mitigate the occlusion problem in the warping refinement process. Extensive experiments on both synthetic and real datasets show the effectiveness of the proposed approach, demonstrating its potential for higher quality video frame interpolation.

Yu Liu, Zhijie Liu, Xiao Ren et al.

Predicting pedestrian motion trajectories is critical for the path planning and motion control of autonomous vehicles. Recent diffusion-based models have shown promising results in capturing the inherent stochasticity of pedestrian behavior for trajectory prediction. However, the absence of explicit semantic modelling of pedestrian intent in many diffusion-based methods may result in misinterpreted behaviors and reduced prediction accuracy. To address the above challenges, we propose a diffusion-based pedestrian trajectory prediction framework that incorporates both short-term and long-term motion intentions. Short-term intent is modelled using a residual polar representation, which decouples direction and magnitude to capture fine-grained local motion patterns. Long-term intent is estimated through a learnable, token-based endpoint predictor that generates multiple candidate goals with associated probabilities, enabling multimodal and context-aware intention modelling. Furthermore, we enhance the diffusion process by incorporating adaptive guidance and a residual noise predictor that dynamically refines denoising accuracy. The proposed framework is evaluated on the widely used ETH, UCY, and SDD benchmarks, demonstrating competitive results against state-of-the-art methods.

Yongjian Deng, Hao Chen, Hai Liu et al.

Event cameras attract researchers' attention due to their low power consumption, high dynamic range, and extremely high temporal resolution. Learning models on event-based object classification have recently achieved massive success by accumulating sparse events into dense frames to apply traditional 2D learning methods. Yet, these approaches necessitate heavy-weight models and are with high computational complexity due to the redundant information introduced by the sparse-to-dense conversion, limiting the potential of event cameras on real-life applications. This study aims to address the core problem of balancing accuracy and model complexity for event-based classification models. To this end, we introduce a novel graph representation for event data to exploit their sparsity better and customize a lightweight voxel graph convolutional neural network (\textit{EV-VGCNN}) for event-based classification. Specifically, (1) using voxel-wise vertices rather than previous point-wise inputs to explicitly exploit regional 2D semantics of event streams while keeping the sparsity;(2) proposing a multi-scale feature relational layer (\textit{MFRL}) to extract spatial and motion cues from each vertex discriminatively concerning its distances to neighbors. Comprehensive experiments show that our model can advance state-of-the-art classification accuracy with extremely low model complexity (merely 0.84M parameters).

Hao Chen, Youfu Li

The goal of this work is to present a systematic solution for RGB-D salient object detection, which addresses the following three aspects with a unified framework: modal-specific representation learning, complementary cue selection and cross-modal complement fusion. To learn discriminative modal-specific features, we propose a hierarchical cross-modal distillation scheme, in which the well-learned source modality provides supervisory signals to facilitate the learning process for the new modality. To better extract the complementary cues, we formulate a residual function to incorporate complements from the paired modality adaptively. Furthermore, a top-down fusion structure is constructed for sufficient cross-modal interactions and cross-level transmissions. The experimental results demonstrate the effectiveness of the proposed cross-modal distillation scheme in zero-shot saliency detection and pre-training on a new modality, as well as the advantages in selecting and fusing cross-modal/cross-level complements.

Ariyam Das, Youfu Li, Jin Wang et al.

In the past, the semantic issues raised by the non-monotonic nature of aggregates often prevented their use in the recursive statements of logic programs and deductive databases. However, the recently introduced notion of Pre-mappability (PreM) has shown that, in key applications of interest, aggregates can be used in recursion to optimize the perfect-model semantics of aggregate-stratified programs. Therefore we can preserve the declarative formal semantics of such programs while achieving a highly efficient operational semantics that is conducive to scalable implementations on parallel and distributed platforms. In this paper, we show that with PreM, a wide spectrum of classical algorithms of practical interest, ranging from graph analytics and dynamic programming based optimization problems to data mining and machine learning applications can be concisely expressed in declarative languages by using aggregates in recursion. Our examples are also used to show that PreM can be checked using simple techniques and templatized verification strategies. A wide range of advanced BigData applications can now be expressed declaratively in logic-based languages, including Datalog, Prolog, and even SQL, while enabling their execution with superior performance and scalability.

Hao Chen, Y. F. Li, Dan Su

In this work, we propose to utilize Convolutional Neural Networks to boost the performance of depth-induced salient object detection by capturing the high-level representative features for depth modality. We formulate the depth-induced saliency detection as a CNN-based cross-modal transfer problem to bridge the gap between the "data-hungry" nature of CNNs and the unavailability of sufficient labeled training data in depth modality. In the proposed approach, we leverage the auxiliary data from the source modality effectively by training the RGB saliency detection network to obtain the task-specific pre-understanding layers for the target modality. Meanwhile, we exploit the depth-specific information by pre-training a modality classification network that encourages modal-specific representations during the optimizing course. Thus, it could make the feature representations of the RGB and depth modalities as discriminative as possible. These two modules are pre-trained independently and then stitched to initialize and optimize the eventual depth-induced saliency detection model. Experiments demonstrate the effectiveness of the proposed novel pre-training strategy as well as the significant and consistent improvements of the proposed approach over other state-of-the-art methods.

Yao Guo, Youfu Li, Zhanpeng Shao

Motion behaviors of a rigid body can be characterized by a 6-dimensional motion trajectory, which contains position vectors of a reference point on the rigid body and rotations of this rigid body over time. This paper devises a Rotation and Relative Velocity (RRV) descriptor by exploring the local translational and rotational invariants of motion trajectories of rigid bodies, which is insensitive to noise, invariant to rigid transformation and scaling. A flexible metric is also introduced to measure the distance between two RRV descriptors. The RRV descriptor is then applied to characterize motions of a human body skeleton modeled as articulated interconnections of multiple rigid bodies. To illustrate the descriptive ability of the RRV descriptor, we explore it for different rigid body motion recognition tasks. The experimental results on benchmark datasets demonstrate that this simple RRV descriptor outperforms the previous ones regarding recognition accuracy without increasing computational cost.