Related papers: Motion Robust High-Speed Light-Weighted Object Det…
Recent proposed neural network-based Temporal Action Detection (TAD) models are inherently limited to extracting the discriminative representations and modeling action instances with various lengths from complex scenes by shared-weights…
Despite recent advances in video-based action recognition and robust spatio-temporal modeling, most of the proposed approaches rely on the abundance of computational resources to afford running huge and computation-intensive convolutional…
Scene flow provides crucial motion information for autonomous driving. Recent LiDAR scene flow models utilize the rigid-motion assumption at the instance level, assuming objects are rigid bodies. However, these instance-level methods are…
Line segment extraction is effective for capturing geometric features of human-made environments. Event-based cameras, which asynchronously respond to contrast changes along edges, enable efficient extraction by reducing redundant data.…
Event cameras offer many advantages over standard cameras due to their distinctive principle of operation: low power, low latency, high temporal resolution and high dynamic range. Nonetheless, the success of many downstream visual…
In Intelligent Transportation Systems (ITS), multi-object tracking is primarily based on frame-based cameras. However, these cameras tend to perform poorly under dim lighting and high-speed motion conditions. Event cameras, characterized by…
Detecting objects reliably under extreme low-light conditions is an open problem in computer vision, with practical urgency in applications ranging from nighttime surveillance to search-and-rescue robotics. Conventional RGB cameras degrade…
Robust 3D object detection in extreme weather and illumination conditions is a challenging task. While radars and thermal cameras are known for their resilience to these conditions, few studies have been conducted on radar-thermal fusion…
In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos. Starting from a handful of coarse-scale proposal cuboids, our approach…
Object tracking based on retina-inspired and event-based dynamic vision sensor (DVS) is challenging for the noise events, rapid change of event-stream shape, chaos of complex background textures, and occlusion. To address these challenges,…
Multimodal object detection leverages diverse modal information to enhance the accuracy and robustness of detectors. By learning long-term dependencies, Transformer can effectively integrate multimodal features in the feature extraction…
The dynamic range limitation of conventional RGB cameras reduces global contrast and causes loss of high-frequency details such as textures and edges in complex traffic environments (e.g., nighttime driving, tunnels), hindering…
Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD). Existing studies on CAOD predominantly…
Tracking any point based on image frames is constrained by frame rates, leading to instability in high-speed scenarios and limited generalization in real-world applications. To overcome these limitations, we propose an image-event fusion…
Modern image-based object detection models, such as YOLOv7, primarily process individual frames independently, thus ignoring valuable temporal context naturally present in videos. Meanwhile, existing video-based detection methods often…
This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach combines fast single-image object detection with convolutional long short term memory…
Making line segment detectors more reliable under motion blurs is one of the most important challenges for practical applications, such as visual SLAM and 3D reconstruction. Existing line segment detection methods face severe performance…
Tracking any point (TAP) recently shifted the motion estimation paradigm from focusing on individual salient points with local templates to tracking arbitrary points with global image contexts. However, while research has mostly focused on…
In this work, we present LaserFlow, an efficient method for 3D object detection and motion forecasting from LiDAR. Unlike the previous work, our approach utilizes the native range view representation of the LiDAR, which enables our method…
Contrary to conventional frame-based imaging, event-based vision (EBV) or dynamic vision sensing (DVS) asynchronously records binary signals of intensity changes for given pixels with microsecond resolution. The present work explores the…