相关论文: ReXCam: Resource-Efficient, Cross-Camera Video Ana…
Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are…
Multi-target multi-camera tracking (MTMCT), i.e., tracking multiple targets across multiple cameras, is a crucial technique for smart city applications. In this paper, we propose an effective and reliable MTMCT framework for vehicles, which…
Typical attempts to improve the capability of visual place recognition techniques include the use of multi-sensor fusion and integration of information over time from image sequences. These approaches can improve performance but have…
A truly interactive world model requires three key ingredients: real-time long-horizon streaming, consistent spatial memory, and precise user control. However, most existing approaches address only one of these aspects in isolation, as…
The growing need for video surveillance in public spaces has created a demand for systems that can track individuals across multiple cameras feeds in real-time. While existing tracking systems have achieved impressive performance using deep…
We present Xray-Visual, a unified vision model architecture for large-scale image and video understanding trained on industry-scale social media data. Our model leverages over 15 billion curated image-text pairs and 10 billion video-hashtag…
Vision Transformers achieve impressive accuracy across a range of visual recognition tasks. Unfortunately, their accuracy frequently comes with high computational costs. This is a particular issue in video recognition, where models are…
Simultaneous Localization and Mapping (SLAM) plays an important role in many robotics fields, including social robots. Many of the available visual SLAM methods are based on the assumption of a static world and struggle in dynamic…
The quality of the video stream is key to neural network-based video analytics. However, low-quality video is inevitably collected by existing surveillance systems because of poor quality cameras or over-compressed/pruned video streaming…
Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation…
Retrieving images from the same location as a given query is an important component of multiple computer vision tasks, like Visual Place Recognition, Landmark Retrieval, Visual Localization, 3D reconstruction, and SLAM. However, existing…
We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision. DeepCache benefits model execution efficiency by exploiting temporal locality in input video streams. It addresses a key challenge…
Real-time world simulation is becoming a key infrastructure for scalable evaluation and online reinforcement learning of autonomous driving systems. Recent driving world models built on autoregressive video diffusion achieve high-fidelity,…
Hundreds of millions of network cameras have been installed throughout the world. Each is capable of providing a vast amount of real-time data. Analyzing the massive data generated by these cameras requires significant computational…
Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security. Matching persons across disjoint camera views in their video fragments is inherently challenging due to the…
We developed REVEX, a removal-based video explanations framework. This work extends fine-grained explanation frameworks for computer vision data and adapts six existing techniques to video by adding temporal information and local…
We present Recurrent Vision Transformers (RVTs), a novel backbone for object detection with event cameras. Event cameras provide visual information with sub-millisecond latency at a high-dynamic range and with strong robustness against…
Visual place recognition is a critical task in computer vision, especially for localization and navigation systems. Existing methods often rely on contrastive learning: image descriptors are trained to have small distance for similar images…
In multiview applications, multiple cameras acquire the same scene from different viewpoints and generally produce correlated video streams. This results in large amounts of highly redundant data. In order to save resources, it is critical…
Existing multimodal-based human action recognition approaches are computationally intensive, limiting their deployment in real-time applications. In this work, we present a novel and efficient pose-driven attention-guided multimodal network…