Related papers: DeepMag: Source Specific Motion Magnification Usin…
Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as promising solutions.…
Popular approaches for minimizing loss in data-driven learning often involve an abstraction or an explicit retention of the history of gradients for efficient parameter updates. The aggregated history of gradients nudges the parameter…
Diffusion models have achieved impressive performance in video generation, but their iterative denoising process remains computationally expensive due to the large number of tokens processed at each timestep. Recently, progressive…
Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos. However, compared to using appearance, it has some blind spots, such as the fact that objects become invisible if they do not…
Recent advances in video generation have shown remarkable potential for constructing world simulators. However, current models still struggle to produce physically consistent results, particularly when handling large-scale or complex…
Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion…
Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference. Traditional deblurring algorithms leverage the physics of the image formation model and use hand-crafted priors: they usually produce…
Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to…
Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to support fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal…
The novel Dynamic Vision Sensors (DVSs) gained a great amount of attention recently as they are superior compared to RGB cameras in terms of latency, dynamic range and energy consumption. This is particularly of interest for autonomous…
Modern video generators still struggle with complex physical dynamics, often falling short of physical realism. Existing approaches address this using external verifiers or additional training on augmented data, which is computationally…
Music profoundly enhances video production by improving quality, engagement, and emotional resonance, sparking growing interest in video-to-music generation. Despite recent advances, existing approaches remain limited in specific scenarios…
How do humans recognize an object in a piece of video? Due to the deteriorated quality of single frame, it may be hard for people to identify an occluded object in this frame by just utilizing information within one image. We argue that…
Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame; b) utilizing the…
Microexpressions are fast and spatially small facial expressions that are difficult to detect. Therefore motion magnification techniques, which aim at amplifying and hence revealing subtle motion in videos, appear useful for handling such…
Large language models (LLMs) have demonstrated exceptional capabilities in text understanding, which has paved the way for their expansion into video LLMs (Vid-LLMs) to analyze video data. However, current Vid-LLMs struggle to…
Action recognition is a well-established area of research in computer vision. In this paper, we propose S3Aug, a video data augmenatation for action recognition. Unlike conventional video data augmentation methods that involve cutting and…
The recent renaissance in generative models, driven primarily by the advent of diffusion models and iterative improvement in GAN methods, has enabled many creative applications. However, each advancement is also accompanied by a rise in the…
Robust visual tracking is a challenging computer vision problem, with many real-world applications. Most existing approaches employ hand-crafted appearance features, such as HOG or Color Names. Recently, deep RGB features extracted from…
Convolutional video models have an order of magnitude larger computational complexity than their counterpart image-level models. Constrained by computational resources, there is no model or training method that can train long video…