Related papers: MotionCFG: Boosting Motion Dynamics via Stochastic…
Despite impressive advancements in diffusion-based video editing models in altering video attributes, there has been limited exploration into modifying motion information while preserving the original protagonist's appearance and…
Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different views of an instance. However, obtaining a tight lower…
Generating videos with content and motion variations is a challenging task in computer vision. While the recent development of GAN allows video generation from latent representations, it is not easy to produce videos with particular content…
Learning effective motion features is an essential pursuit of video representation learning. This paper presents a simple yet effective sample construction strategy to boost the learning of motion features in video contrastive learning. The…
Classifier-Free Guidance (CFG) is widely used to improve conditional fidelity in diffusion models, but its impact on sampling dynamics remains poorly understood. Prior studies, often restricted to unimodal conditional distributions or…
Compositional video generation aims to synthesize multiple instances with diverse appearance and motion. However, current approaches mainly focus on binding semantics, neglecting to understand diverse motion categories specified in prompts.…
Classifier-free guidance (CFG) has become an essential component of modern diffusion models to enhance both generation quality and alignment with input conditions. However, CFG requires specific training procedures and is limited to…
Generating 3D human motions from text is a challenging yet valuable task. The key aspects of this task are ensuring text-motion consistency and achieving generation diversity. Although recent advancements have enabled the generation of…
Transient objects in casual multi-view captures cause ghosting artifacts in 3D Gaussian Splatting (3DGS) reconstruction. Existing solutions relied on scene decomposition at significant memory cost or on motion-based heuristics that were…
Classifier-free guidance (CFG) is a fundamental tool in modern diffusion models for text-guided generation. Although effective, CFG has notable drawbacks. For instance, DDIM with CFG lacks invertibility, complicating image editing;…
Multimodal Aspect-based Sentiment Analysis (MABSA) is a fine-grained Sentiment Analysis task, which has attracted growing research interests recently. Existing work mainly utilizes image information to improve the performance of MABSA task.…
To address the problem of catastrophic forgetting due to the invisibility of old categories in sequential input, existing work based on relatively simple categorization tasks has made some progress. In contrast, video captioning is a more…
The design of diffusion-based audio generation systems has been investigated from diverse perspectives, such as data space, network architecture, and conditioning techniques, while most of these innovations require model re-training. In…
Customized video generation aims to generate high-quality videos guided by text prompts and subject's reference images. However, since it is only trained on static images, the fine-tuning process of subject learning disrupts abilities of…
Medical images are often characterized by their structured anatomical representations and spatially inhomogeneous contrasts. Leveraging anatomical priors in neural networks can greatly enhance their utility in resource-constrained clinical…
Text-motion retrieval systems learn shared embedding spaces from motion-caption pairs via contrastive objectives. However, each caption is not a deterministic label but a sample from a distribution of valid descriptions: different…
Recent works have sought to enhance the controllability and precision of text-driven motion generation. Some approaches leverage large language models (LLMs) to produce more detailed texts, while others incorporate global 3D coordinate…
Flow-based generative models have become a strong framework for high-quality generative modeling, yet pretrained models are rarely used in their vanilla conditional form: conditional samples without guidance often appear diffuse and lack…
Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding, often exhibiting spatial hallucination, attention leakage, and failures in object…
Text-to-image diffusion models have shown impressive capabilities in generating realistic visuals from natural-language prompts, yet they often struggle with accurately binding attributes to corresponding objects, especially in prompts…