Related papers: Towards Performance Clarity of Edge Video Analytic…
Video Anomaly Detection (VAD) involves detecting anomalous events in videos, presenting a significant and intricate task within intelligent video surveillance. Existing studies often concentrate solely on features acquired from limited…
The rapid evolution of generative video foundation models has propelled the field toward professional-grade cinematic synthesis. To achieve such demanding quality, the community transitions towards Reinforcement Learning (RL) and agentic…
Recent advances in Visual Anomaly Detection (VAD) have introduced sophisticated algorithms leveraging embeddings generated by pre-trained feature extractors. Inspired by these developments, we investigate the adaptation of such algorithms…
In recent years, we have witnessed an explosive growth of data. Much of this data is video data generated by security cameras, smartphones, and dash cams. The timely analysis of such data is of great practical importance for many emerging…
Visual SLAM shows significant progress in recent years due to high attention from vision community but still, challenges remain for low-textured environments. Feature based visual SLAMs do not produce reliable camera and structure estimates…
Video Anomaly Detection (VAD) represents a challenging and prominent research task within computer vision. In recent years, Pose-based Video Anomaly Detection (PAD) has drawn considerable attention from the research community due to several…
We introduce CAPA, a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion, using sparse geometric cues. Unlike prior methods that train task-specific encoders for…
Most existing benchmarks for understanding egocentric vision focus primarily on daytime scenarios, overlooking the low-light conditions that are inevitable in real-world applications. To investigate this gap, we present EgoNight, the first…
Localizing predefined 3D keypoints in a 2D image is an effective way to establish 3D-2D correspondences for instance-level 6DoF object pose estimation. However, unreliable localization results of invisible keypoints degrade the quality of…
Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict the action categories. The previous works greatly rely upon…
As video generation models advance rapidly, assessing the quality of generated videos has become increasingly critical. Existing metrics, such as Fr\'echet Video Distance (FVD), Inception Score (IS), and ClipSim, measure quality primarily…
Real-time measurements are important for in-depth control of manufacturing processes, which, for modern AI methods, need integration with high-level languages. In our last SSP paper we investigated the performance of a Python and a Java-JNA…
While language models have become impactful in many real-world applications, video generation remains largely confined to entertainment. Motivated by video's inherent capacity to demonstrate physical-world information that is difficult to…
The popularity of streaming videos with live, high-action content has led to an increased interest in High Frame Rate (HFR) videos. In this work we address the problem of frame rate dependent Video Quality Assessment (VQA) when the videos…
Existing collision prediction methods often fail to distinguish between ego-vehicle threats and random accidents not involving the ego vehicle, leading to excessive false alerts in real-world deployment. We present BADAS, a family of…
Voice Activity Detection (VAD) refers to the problem of distinguishing speech segments from background noise. Numerous approaches have been proposed for this purpose. Some are based on features derived from the power spectral density,…
Video-based human pose estimation models aim to address scenarios that cannot be effectively solved by static image models such as motion blur, out-of-focus and occlusion. Most existing approaches consist of two stages: detecting human…
Recent breakthroughs in video generation have demonstrated an emerging capability termed Chain-of-Frames (CoF) reasoning, where models resolve complex tasks through the generation of continuous frames. While these models show promise for…
Data valuation is a ML field that studies the value of training instances towards a given predictive task. Although data bias is one of the main sources of downstream model unfairness, previous work in data valuation does not consider how…
Video action models are an appealing foundation for Vision--Language--Action systems because they can learn visual dynamics from large-scale video data and transfer this knowledge to downstream robot control. Yet current diffusion-based…