Related papers: PRISM: Video Dataset Condensation with Progressive…
Video summarization helps turn long videos into clear, concise representations that are easier to review, document, and analyze, especially in high-stakes domains like surgical training. Prior work has progressed from using basic visual…
Text-to-motion generation has advanced rapidly, yet two challenges persist. First, existing motion autoencoders compress each frame into a single monolithic latent vector, entangling trajectory and per-joint rotations in an unstructured…
Scientific and environmental imagery often suffer from complex mixtures of noise related to the sensor and the environment. Existing restoration methods typically remove one degradation at a time, leading to cascading artifacts,…
Robust imitation learning for robot manipulation requires comprehensive 3D perception, yet many existing methods struggle in cluttered environments. Fixed camera view approaches are vulnerable to perspective changes, and 3D point cloud…
With the widespread use of installed cameras, video-based monitoring approaches have seized considerable attention for different purposes like assisted living. Temporal redundancy and the sheer size of raw videos are the two most common…
The inverse problem of multilayer thin-film optical coatings design represents a complex combinatorial-continuous optimization challenge. We present PRISM (Position-encoded Regressive Inverse Spectral Model), a unified decoder-only…
The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vital research area. However, many state-of-the-art methods…
Scene graphs have emerged as accurate descriptive priors for image generation and manipulation tasks, however, their complexity and diversity of the shapes and relations of objects in data make it challenging to incorporate them into the…
Multivariate time series classification supports applications from wearable sensing to biomedical monitoring and demands models that can capture both short-term patterns and multi-scale temporal dependencies. Despite recent advances,…
Modern video codecs and learning-based approaches struggle for semantic reconstruction at extremely low bit-rates due to reliance on low-level spatiotemporal redundancies. Generative models, especially diffusion models, offer a new paradigm…
Recently, dataset condensation has made significant progress in the image domain. Unlike images, videos possess an additional temporal dimension, which harbors considerable redundant information, making condensation even more crucial.…
In this paper, we present a novel robust framework for low-level vision tasks, including denoising, object removal, frame interpolation, and super-resolution, that does not require any external training data corpus. Our proposed approach…
Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, current approaches are often hindered by a reliance on explicit motion engineering or…
We introduce PRISM, a method for real-time filtering in a probabilistic generative model of agent motion and visual perception. Previous approaches either lack uncertainty estimates for the map and agent state, do not run in real-time, do…
Online videos play a central role in shaping political discourse and amplifying cyber social threats such as misinformation, propaganda, and radicalization. Detecting the most impactful or "standout" moments in video content is crucial for…
We present PRISM, a unified framework that enables multiple image generation and editing tasks in a single foundational model. Starting from a pre-trained text-to-image diffusion model, PRISM proposes an effective fine-tuning strategy to…
Training robust deep video representations has proven to be computationally challenging due to substantial decoding overheads, the enormous size of raw video streams, and their inherent high temporal redundancy. Different from existing…
Experience and reasoning occur across multiple temporal scales: milliseconds, seconds, hours or days. The vast majority of computer vision research, however, still focuses on individual images or short videos lasting only a few seconds.…
This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to…
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,…