Related papers: FRESCO: Spatial-Temporal Correspondence for Zero-S…
Recently, diffusion-based generative models have achieved remarkable success for image generation and edition. However, existing diffusion-based video editing approaches lack the ability to offer precise control over generated content that…
This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available. For this challenging scenario, the current leading approach is to transfer knowledge from the…
Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling. We propose…
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur. Previous approaches exploit to propagate and aggregate features across…
Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing…
We propose a diffusion-based framework for zero-shot image editing that unifies text-guided and reference-guided approaches without requiring fine-tuning. Our method leverages diffusion inversion and timestep-specific null-text embeddings…
In this paper, we investigate the problem of unpaired video-to-video translation. Given a video in the source domain, we aim to learn the conditional distribution of the corresponding video in the target domain, without seeing any pairs of…
Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training…
Text-to-image diffusion models are now capable of generating images that are often indistinguishable from real images. To generate such images, these models must understand the semantics of the objects they are asked to generate. In this…
Diffusion models have been shown to be capable of generating high-quality images, suggesting that they could contain meaningful internal representations. Unfortunately, the feature maps that encode a diffusion model's internal information…
Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-based methods, their reliance on exhaustive annotation limits…
Large-scale video diffusion models show strong world simulation and temporal reasoning abilities, but their use as zero-shot image editors remains underexplored. We introduce IF-Edit, a tuning-free framework that repurposes pretrained…
Understanding human actions from visual observations is essential for human--robot interaction, particularly when semantic interpretation of unfamiliar or hard-to-annotate actions is required. In scenarios such as rapid and less common…
Video restoration aims to reconstruct high quality video sequences from low quality inputs, addressing tasks such as super resolution, denoising, and deblurring. Traditional regression based methods often produce unrealistic details and…
Deep learning has achieved great success in video recognition, yet still struggles to recognize novel actions when faced with only a few examples. To tackle this challenge, few-shot action recognition methods have been proposed to transfer…
Diffusion models have demonstrated remarkable capabilities in text-to-image and text-to-video generation, opening up possibilities for video editing based on textual input. However, the computational cost associated with sequential sampling…
Zero-shot recognition aims to classify an image by selecting the most compatible label description from a set of candidate classes without any task-specific supervision. In fine-grained settings, however, the relevant evidence often lies in…
In this work, we propose a zero-shot learning method to effectively model knowledge transfer between classes via jointly learning visually consistent word vectors and label embedding model in an end-to-end manner. The main idea is to…
The objective of this paper is self-supervised learning of feature embeddings that are suitable for matching correspondences along the videos, which we term correspondence flow. By leveraging the natural spatial-temporal coherence in…
Diffusion models have achieved great progress in image animation due to powerful generative capabilities. However, maintaining spatio-temporal consistency with detailed information from the input static image over time (e.g., style,…