相关论文: SpatialVID: A Large-Scale Video Dataset with Spati…
Current video editing models often rely on expensive paired video data, which limits their practical scalability. In essence, most video editing tasks can be formulated as a decoupled spatiotemporal process, where the temporal dynamics of…
Publishing open-source academic video recordings is an emergent and prevalent approach to sharing knowledge online. Such videos carry rich multimodal information including speech, the facial and body movements of the speakers, as well as…
Annotating object ground truth in videos is vital for several downstream tasks in robot perception and machine learning, such as for evaluating the performance of an object tracker or training an image-based object detector. The accuracy of…
Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we…
Automatic detection of natural disasters and incidents has become more important as a tool for fast response. There have been many studies to detect incidents using still images and text. However, the number of approaches that exploit…
This paper introduces VideoMind, a video-centric omni-modal dataset designed for deep video content cognition and enhanced multi-modal feature representation. The dataset comprises 103K video samples (3K reserved for testing), each paired…
The remarkable success of deep learning in various domains relies on the availability of large-scale annotated datasets. However, obtaining annotations is expensive and requires great effort, which is especially challenging for videos.…
Modern computational science and engineering applications are being improved by the advances in scientific machine learning. Data-driven methods such as Dynamic Mode Decomposition (DMD) can extract coherent structures from spatio-temporal…
User engagement is greatly enhanced by fully immersive multi-modal experiences that combine visual and auditory stimuli. Consequently, the next frontier in VR/AR technologies lies in immersive volumetric videos with complete scene capture,…
Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…
Missions to small celestial bodies rely heavily on optical feature tracking for characterization of and relative navigation around the target body. While deep learning has led to great advancements in feature detection and description,…
Realistic human surveillance datasets are crucial for training and evaluating computer vision models under real-world conditions, facilitating the development of robust algorithms for human and human-interacting object detection in complex…
Human perception is at the core of lossy video compression, with numerous approaches developed for perceptual quality assessment and improvement over the past two decades. In the determination of perceptual quality, different…
Object localization, and more specifically object pose estimation, in large industrial spaces such as warehouses and production facilities, is essential for material flow operations. Traditional approaches rely on artificial artifacts…
Semantic segmentation has been one of the leading research interests in computer vision recently. It serves as a perception foundation for many fields, such as robotics and autonomous driving. The fast development of semantic segmentation…
Dataset distillation aims to synthesize compact yet informative datasets that allow models trained on them to achieve performance comparable to training on the full dataset. While this approach has shown promising results for image data,…
Video Anomaly Detection (VAD) finds widespread applications in security surveillance, traffic monitoring, industrial monitoring, and healthcare. Despite extensive research efforts, there remains a lack of concise reviews that provide…
Our ability to train end-to-end systems for 3D human pose estimation from single images is currently constrained by the limited availability of 3D annotations for natural images. Most datasets are captured using Motion Capture (MoCap)…
Manual spatio-temporal annotation of human action in videos is laborious, requires several annotators and contains human biases. In this paper, we present a weakly supervised approach to automatically obtain spatio-temporal annotations of…
Video Large Language Models have demonstrated strong video understanding capabilities, yet their practical deployment is hindered by substantial inference costs caused by redundant video tokens. Existing pruning techniques fail to…