Related papers: PRISM: Video Dataset Condensation with Progressive…
Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…
Although block compressive sensing (BCS) makes it tractable to sense large-sized images and video, its recovery performance has yet to be significantly improved because its recovered images or video usually suffer from blurred edges, loss…
In recent years, the demand of image compression models for machine vision has increased dramatically. However, the training frameworks of image compression still focus on the vision of human, maintaining the excessive perceptual details,…
In this paper, we present PRISM, a Promptable and Robust Interactive Segmentation Model, aiming for precise segmentation of 3D medical images. PRISM accepts various visual inputs, including points, boxes, and scribbles as sparse prompts, as…
Thanks to the advances in the technology of low-cost digital cameras and the popularity of the self-recording culture, the amount of visual data on the Internet is going to the opposite side of the available time and patience of the users.…
Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these datasets introduces significant redundancy, leading to…
Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…
Every day around the world, interminable terabytes of data are being captured for surveillance purposes. A typical 1-2MP CCTV camera generates around 7-12GB of data per day. Frame-by-frame processing of such enormous amount of data requires…
Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compression method in which an image is first represented as a…
Image matching aims at identifying corresponding points between a pair of images. Currently, detector-free methods have shown impressive performance in challenging scenarios, thanks to their capability of generating dense matches and global…
Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing…
Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos based on text queries that describe only partial events. Existing methods suffer from incomplete global contextual perception, struggling with query ambiguity and…
The online reconstruction of dynamic scenes from multi-view streaming videos faces significant challenges in training, rendering and storage efficiency. Harnessing superior learning speed and real-time rendering capabilities, 3D Gaussian…
We present a method to estimate human motion in a global scene from moving cameras. This is a highly challenging task due to the coupling of human and camera motions in the video. To address this problem, we propose a joint optimization…
Autoregressive (AR) diffusion enables streaming, interactive long-video generation by producing frames causally, yet maintaining coherence over minute-scale horizons remains challenging due to accumulated errors, motion drift, and content…
Human Motion Segmentation (HMS), which aims to partition a video into non-overlapping segments corresponding to different human motions, has recently attracted increasing research attention. Existing HMS approaches are predominantly based…
Segment Anything Model 2 (SAM 2) serves as a core foundation model in the field of video segmentation. Building upon the original SAM model, it introduces a memory bank mechanism and demonstrates outstanding performance in tasks such as…
Diffusion models have quickly risen in popularity for their ability to model complex distributions and perform effective posterior sampling. Unfortunately, the iterative nature of these generative models makes them computationally expensive…
Text image super-resolution (Text-SR) requires more than visually plausible detail synthesis: slight errors in stroke topology may alter character identity and break readability. Existing methods improve text fidelity with stronger…
Deep learning models have become pivotal in the field of video processing and is increasingly critical in practical applications such as autonomous driving and object detection. Although Vision Transformers (ViTs) have demonstrated their…