Related papers: PeriphAR: Fast and Accurate Real-World Object Sele…
Bird's-Eye View (BEV) features are popular intermediate scene representations shared by the 3D backbone and the detector head in LiDAR-based object detectors. However, little research has been done to investigate how to incorporate…
Augmented reality (AR) has gained increasingly attention from both research and industry communities. By overlaying digital information and content onto the physical world, AR enables users to experience the world in a more informative and…
This study comprehensively evaluates tuning methods for autofocal glasses using virtual reality (VR), addressing the challenge of presbyopia. With aging, presbyopia diminishes the eye's ability to focus on nearby objects, impacting the…
Lidar-based perception pipelines rely on 3D object detection models to interpret complex scenes. While multiple representations for lidar exist, the range-view is enticing since it losslessly encodes the entire lidar sensor output. In this…
Text-to-video retrieval (TVR) aims to find the most relevant video in a large video gallery given a query text. The intricate and abundant context of the video challenges the performance and efficiency of TVR. To handle the serialized video…
Cross-view object correspondence involves matching objects between egocentric (first-person) and exocentric (third-person) views. It is a critical yet challenging task for visual understanding. In this work, we propose the Dense Object…
Traditionally, an object detector is applied to every part of the scene of interest, and its accuracy and computational cost increases with higher resolution images. However, in some application domains such as remote sensing, purchasing…
The ability to predict future outcomes conditioned on observed video frames is crucial for intelligent decision-making in autonomous systems. Recently, deep recurrent architectures have been applied to the task of video prediction. However,…
The integration of extended reality (XR) with artificial intelligence (AI) introduces a new paradigm for user interaction, enabling AI to perceive user intent, stimulate the senses, and influence decision-making. We explored the impact of…
Extended Reality (XR) technologies are becoming integral to daily life. However, password-based authentication in XR disrupts immersion due to poor usability, as entering credentials with XR controllers is cumbersome and error-prone. This…
3D object detection from monocular images has proven to be an enormously challenging task, with the performance of leading systems not yet achieving even 10\% of that of LiDAR-based counterparts. One explanation for this performance gap is…
Region-based image retrieval (RBIR) technique is revisited. In early attempts at RBIR in the late 90s, researchers found many ways to specify region-based queries and spatial relationships; however, the way to characterize the regions, such…
Periocular biometrics has been established as an independent modality due to concerns on the performance of iris or face systems in uncontrolled conditions. Periocular refers to the facial region in the eye vicinity, including eyelids,…
Detecting poorly textured objects and estimating their 3D pose reliably is still a very challenging problem. We introduce a simple but powerful approach to computing descriptors for object views that efficiently capture both the object…
Searching for small objects in large images is a task that is both challenging for current deep learning systems and important in numerous real-world applications, such as remote sensing and medical imaging. Thorough scanning of very large…
We consider detecting objects in an image by iteratively selecting from a set of arbitrarily shaped candidate regions. Our generic approach, which we term visual chunking, reasons about the locations of multiple object instances in an image…
3D object detection is an important capability needed in various practical applications such as driver assistance systems. Monocular 3D detection, as a representative general setting among image-based approaches, provides a more economical…
State-of-the-art methods for computer vision rely heavily on the translation equivariance and spatial sharing properties of convolutional layers without explicitly taking into consideration the input content. Modern techniques employ deep…
Low-cost autonomous agents including autonomous driving vehicles chiefly adopt monocular 3D object detection to perceive surrounding environment. This paper studies 3D intermediate representation methods which generate intermediate 3D…
In visual recognition, both the object of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) play an important role. However, standard supervised learning often leads to unintended…