Related papers: Transforming faces into video stories -- VideoFace…
Face editing methods, essential for tasks like virtual avatars, digital human synthesis and identity preservation, have traditionally been built upon GAN-based techniques, while recent focus has shifted to diffusion-based models due to…
Recent advances have demonstrated compelling capabilities in synthesizing real individuals into generated videos, reflecting the growing demand for identity-aware content creation. Nevertheless, an openly accessible framework enabling…
Navigating the complexities of person re-identification (ReID) in varied surveillance scenarios, particularly when occlusions occur, poses significant challenges. We introduce an innovative Motion-Aware Fusion (MOTAR-FUSE) network that…
We propose a real time deep learning framework for video-based facial expression capture. Our process uses a high-end facial capture pipeline based on FACEGOOD to capture facial expression. We train a convolutional neural network to produce…
The objective of this work is to automatically recognize faces from video sequences in a realistic, unconstrained setup in which illumination conditions are extreme and greatly changing, viewpoint and user motion pattern have a wide…
Person re-identification (ReID) plays a critical role in intelligent surveillance systems by linking identities across multiple cameras in complex environments. However, ReID faces significant challenges such as appearance variations,…
Models based on self-attention mechanisms have been successful in analyzing temporal data and have been widely used in the natural language domain. We propose a new model architecture for video face representation and recognition based on a…
In recent years, video-based person Re-Identification (ReID) has gained attention for its ability to leverage spatiotemporal cues to match individuals across non-overlapping cameras. However, current methods struggle with high-difficulty…
While recent research has progressively overcome the low-resolution constraint of one-shot face video re-enactment with the help of StyleGAN's high-fidelity portrait generation, these approaches rely on at least one of the following:…
The goal of video-based person re-identification is to match two input videos, so that the distance of the two videos is small if two videos contain the same person. A common approach for person re-identification is to first extract image…
Person-generic audio-driven face generation is a challenging task in computer vision. Previous methods have achieved remarkable progress in audio-visual synchronization, but there is still a significant gap between current results and…
Massive amounts of video data are ubiquitously generated in personal devices and dedicated video recording facilities. Analyzing such data would be extremely beneficial in real world (e.g., urban traffic analysis, pedestrian behavior…
Traditional text-based person ReID assumes that person descriptions from witnesses are complete and provided at once. However, in real-world scenarios, such descriptions are often partial or vague. To address this limitation, we introduce a…
Many methods have been developed to help people find the video contents they want efficiently. However, there are still some unsolved problems in this area. For example, given a query video and a reference video, how to accurately localize…
Recently, large-scale vision-language pre-trained models like CLIP have shown impressive performance in image re-identification (ReID). In this work, we explore whether self-supervision can aid in the use of CLIP for image ReID tasks.…
Vehicle re-identification (reID) plays an important role in the automatic analysis of the increasing urban surveillance videos, which has become a hot topic in recent years. However, it poses the critical but challenging problem that is…
Reliable re-identification of individuals within large wildlife populations is crucial for biological studies, ecological research, and wildlife conservation. Classic computer vision techniques offer a promising direction for Animal…
This work proposes TimeChat, a time-sensitive multimodal large language model specifically designed for long video understanding. Our model incorporates two key architectural contributions: (1) a timestamp-aware frame encoder that binds…
This work proposes a novel method to generate realistic talking head videos using audio and visual streams. We animate a source image by transferring head motion from a driving video using a dense motion field generated using learnable…
The datasets of face recognition contain an enormous number of identities and instances. However, conventional methods have difficulty in reflecting the entire distribution of the datasets because a mini-batch of small size contains only a…