Deep learning models perform remarkably well for the same task under the assumption that data is always coming from the same distribution. However, this is generally violated in practice, mainly due to the differences in data acquisition techniques and the lack of information about the underlying source of new data. Domain generalization targets the ability to generalize to test data of an unseen domain; while this problem is well-studied for images, such studies are significantly lacking in spatiotemporal visual content—videos and GIFs. This is due to (1) the challenging nature of misalignment of temporal features and the varying appearance/motion of actors and actions in different domains, and (2) spatiotemporal datasets being laborious to collect and annotate for multiple domains. We collect and present the first synthetic video dataset of Animated GIFs for domain generalization, Ani-GIFs, that is used to study the domain gap of videos vs. GIFs, and animated vs. real GIFs, for the task of action recognition. We provide a training and testing setting for Ani-GIFs, and extend two domain generalization baseline approaches, based on data augmentation and explainability, to the spatiotemporal domain to catalyze research in this direction.
In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques. The methodology utilizes the SMPL(Skinned Multi-Person Linear) model as the 3D human parametric model to establish a unified representation of body shape and pose. This facilitates the accurate capture of intricate human geometry and motion characteristics from source videos. Specifically, we incorporate rendered depth images, normal maps, and semantic maps obtained from SMPL sequences, alongside skeleton-based motion guidance, to enrich the conditions to the latent diffusion model with comprehensive 3D shape and detailed pose attributes. A multi-layer motion fusion module, integrating self-attention mechanisms, is employed to fuse the shape and motion latent representations in the spatial domain. By representing the 3D human parametric model as the motion guidance, we can perform parametric shape alignment of the human body between the reference image and the source video motion. Experimental evaluations conducted on benchmark datasets demonstrate the methodology's superior ability to generate high-quality human animations that accurately capture both pose and shape variations. Furthermore, our approach also exhibits superior generalization capabilities on the proposed in-the-wild dataset. Project page: https://fudan-generative-vision.github.io/champ.
This paper proposes a lightweight method to attract users and increase views of the video by presenting personalized artistic media -- i.e, static thumbnails and animated GIFs. This method analyzes lightweight thumbnail containers (LTC) using computational resources of the client device to recognize personalized events from full-length sports videos. In addition, instead of processing the entire video, small video segments are processed to generate artistic media. This makes the proposed approach more computationally efficient compared to the baseline approaches that create artistic media using the entire video. The proposed method retrieves and uses thumbnail containers and video segments, which reduces the required transmission bandwidth as well as the amount of locally stored data used during artistic media generation. When extensive experiments were conducted on the Nvidia Jetson TX2, the computational complexity of the proposed method was 3.57 times lower than that of the SoA method. In the qualitative assessment, GIFs generated using the proposed method received 1.02 higher overall ratings compared to the SoA method. To the best of our knowledge, this is the first technique that uses LTC to generate artistic media while providing lightweight and high-performance services even on resource-constrained devices.