Related papers: Real-World Video for Zoom Enhancement based on Spa…
The pursuit of higher compression efficiency continuously drives the advances of video coding technologies. Fundamentally, we wish to find better "predictions" or "priors" that are reconstructed previously to remove the signal dependency…
Super-resolution (SR) is a key technique for improving the visual quality of video content by increasing its spatial resolution while reconstructing fine details. SR has been employed in many applications including video streaming, where…
In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds,…
This paper addresses the problem of how to exploit spatio-temporal information available in videos to improve the object detection precision. We propose a two stage object detector called FANet based on short-term spatio-temporal feature…
In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively…
We propose Spatio-temporal Crop Aggregation for video representation LEarning (SCALE), a novel method that enjoys high scalability at both training and inference time. Our model builds long-range video features by learning from sets of…
Weakly supervised temporal action localization is a challenging task as only the video-level annotation is available during the training process. To address this problem, we propose a two-stage approach to fully exploit multi-resolution…
Our goal in this paper is the adaptation of image-text models for long video retrieval. Recent works have demonstrated state-of-the-art performance in video retrieval by adopting CLIP, effectively hitchhiking on the image-text…
Vision-language models like CLIP have shown impressive capabilities in aligning images and text, but they often struggle with lengthy and detailed text descriptions because of their training focus on short and concise captions. We present…
We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video…
While recent large-scale video-language pre-training made great progress in video question answering, the design of spatial modeling of video-language models is less fine-grained than that of image-language models; existing practices of…
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…
Video Diffusion Models have been developed for video generation, usually integrating text and image conditioning to enhance control over the generated content. Despite the progress, ensuring consistency across frames remains a challenge,…
Thermal cameras offer strong potential for robot perception under challenging illumination and weather conditions. However, thermal Simultaneous Localization and Mapping (SLAM) remains difficult due to unreliable feature extraction,…
Recently, multi-modal large language models have made significant progress. However, visual information lacking of guidance from the user's intention may lead to redundant computation and involve unnecessary visual noise, especially in…
Video deblurring is a challenging task due to the spatially variant blur caused by camera shake, object motions, and depth variations, etc. Existing methods usually estimate optical flow in the blurry video to align consecutive frames or…
A major emerging challenge is how to protect people's privacy as cameras and computer vision are increasingly integrated into our daily lives, including in smart devices inside homes. A potential solution is to capture and record just the…
Although dynamic scene reconstruction has long been a fundamental challenge in 3D vision, the recent emergence of 3D Gaussian Splatting (3DGS) offers a promising direction by enabling high-quality, real-time rendering through explicit…
Within the scope of this contribution we propose a novel efficient spatio-temporal prediction algorithm for video coding. The algorithm operates in two stages. First, motion compensation is performed on the block to be predicted in order to…
Monocular vision-based Simultaneous Localization and Mapping (SLAM) is used for various purposes due to its advantages in cost, simple setup, as well as availability in the environments where navigation with satellites is not effective.…