相关论文: Separate Motion from Appearance: Customizing Motio…

Text-driven human motion generation aims to synthesize realistic motion sequences that follow textual descriptions. Despite recent advances, accurately aligning motion dynamics with textual semantics remains a fundamental challenge. In this…

Videos contain rich spatio-temporal information. Traditional methods for extracting motion, used in tasks such as action recognition, often rely on visual contents rather than precise motion features. This phenomenon is referred to as…

Human behavior understanding in videos is a complex, still unsolved problem and requires to accurately model motion at both the local (pixel-wise dense prediction) and global (aggregation of motion cues) levels. Current approaches based on…

We present a target-aware video diffusion model that generates videos from an input image, in which an actor interacts with a specified target while performing a desired action. The target is defined by a segmentation mask, and the action…

Talking head video generation aims to generate a realistic talking head video that preserves the person's identity from a source image and the motion from a driving video. Despite the promising progress made in the field, it remains a…

Ever-increasing smartphone-generated video content demands intelligent techniques to edit and enhance videos on power-constrained devices. Most of the best performing algorithms for video understanding tasks like action recognition,…

Video personalization aims to generate videos that faithfully reflect a user-provided subject while following a text prompt. However, existing approaches often rely on heavy video-based finetuning or large-scale video datasets, which impose…

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing…

For recent diffusion-based generative models, maintaining consistent content across a series of generated images, especially those containing subjects and complex details, presents a significant challenge. In this paper, we propose a new…

Given a source image and a driving video depicting the same object type, the motion transfer task aims to generate a video by learning the motion from the driving video while preserving the appearance from the source image. In this paper,…

Video-based human pose transfer is a video-to-video generation task that animates a plain source human image based on a series of target human poses. Considering the difficulties in transferring highly structural patterns on the garments…

Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion.Recent advances in diffusion models have enabled significant…

Vision-language models bridge visual and linguistic understanding and have proven to be powerful for video recognition tasks. Existing approaches primarily rely on parameter-efficient fine-tuning of image-text pre-trained models, yet they…

The evolution of diffusion models has greatly impacted video generation and understanding. Particularly, text-to-video diffusion models (VDMs) have significantly facilitated the customization of input video with target appearance, motion,…

While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training samples are limited, compromising both generalization…

Customization techniques for text-to-image models have paved the way for a wide range of previously unattainable applications, enabling the generation of specific concepts across diverse contexts and styles. While existing methods…

Transferring human motion and appearance between videos of human actors remains one of the key challenges in Computer Vision. Despite the advances from recent image-to-image translation approaches, there are several transferring contexts…

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$% of diffusion models' parameters, all contained in…

Recent advances in text-guided video editing have showcased promising results in appearance editing (e.g., stylization). However, video motion editing in the temporal dimension (e.g., from eating to waving), which distinguishes video…

This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos. Previous work suggests potential bias in existing datasets and emphasizes the need for a new data creation schema to better model…