Related papers: Video Analytics with Zero-streaming Cameras
This study seeks to automate camera movement control for filming existing subjects into attractive videos, contrasting with the creation of non-existent content by directly generating the pixels. We select drone videos as our test case due…
Existing video domain adaption (DA) methods need to store all temporal combinations of video frames or pair the source and target videos, which are memory cost expensive and can't scale up to long videos. To address these limitations, we…
A growing number of visual computing applications depend on the analysis of large video collections. The challenge is that scaling applications to operate on these datasets requires efficient systems for pixel data access and parallel…
Modern autonomous vehicles rely heavily on mechanical LiDARs for perception. Current perception methods generally require 360{\deg} point clouds, collected sequentially as the LiDAR scans the azimuth and acquires consecutive wedge-shaped…
Streaming video understanding requires processing unbounded video streams with limited memory and computation, posing two key challenges. First, continuously constructing new and evicting old key-value(KV) caches is required for unbounded…
Event-based vision sensors, such as the Dynamic Vision Sensor (DVS), are ideally suited for real-time motion analysis. The unique properties encompassed in the readings of such sensors provide high temporal resolution, superior sensitivity…
We present ViSTA-SLAM as a real-time monocular visual SLAM system that operates without requiring camera intrinsics, making it broadly applicable across diverse camera setups. At its core, the system employs a lightweight symmetric two-view…
Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to…
In this paper we propose a geometry-aware model for video object detection. Specifically, we consider the setting that cameras can be well approximated as static, e.g. in video surveillance scenarios, and scene pseudo depth maps can…
With increasing advancements in technologies for capturing 360{\deg} videos, advances in streaming such videos have become a popular research topic. However, streaming 360{\deg} videos require high bandwidth, thus escalating the need for…
The surge in video and social media content underscores the need for a deeper understanding of multimedia data. Most of the existing mature video understanding techniques perform well with short formats and content that requires only…
Retrieval of live, user-broadcast video streams is an under-addressed and increasingly relevant challenge. The on-line nature of the problem requires temporal evaluation and the unforeseeable scope of potential queries motivates an approach…
Live video analytics (LVA) runs continuously across massive camera fleets, but inference cost with modern vision models remains high. To address this, dynamic model size selection (DMSS) is an attractive approach: it is content-aware but…
The advent of Video Diffusion Transformers (Video DiTs) marks a milestone in video generation. However, directly applying existing video editing methods to Video DiTs often incurs substantial computational overhead, due to…
Deep Learning (DL) combined with advanced model optimization methods such as RC-NN and Edge2Train has enabled offline execution of large networks on the IoT devices. In this paper, we compare the modern Deep Learning (DL) based video…
Millions of cameras at edge are being deployed to power a variety of different deep learning applications. However, the frames captured by these cameras are not always pristine - they can be distorted due to lighting issues, sensor noise,…
Event-based camera is a bio-inspired vision sensor that records intensity changes (called event) asynchronously in each pixel. As an instance of event-based camera, Dynamic and Active-pixel Vision Sensor (DAVIS) combines a standard camera…
Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…
Benefiting from the advancements in large language models and cross-modal alignment, existing multi-modal video understanding methods have achieved prominent performance in offline scenario. However, online video streams, as one of the most…
We propose Compressed Video Aggregator (CVA), a lightweight micro-video recommendation module that decouples video information from preference learning. It aggregates frozen VFM embeddings, and uses latent reasoning without cross-attention…