Related papers: TokenDial: Continuous Attribute Control in Text-to…
We present TokenCompose, a Latent Diffusion Model for text-to-image generation that achieves enhanced consistency between user-specified text prompts and model-generated images. Despite its tremendous success, the standard denoising process…
Our research presents a novel motion generation framework designed to produce whole-body motion sequences conditioned on multiple modalities simultaneously, specifically text and audio inputs. Leveraging Vector Quantized Variational…
Recent advancements in personalized Text-to-Video (T2V) generation have made significant strides in synthesizing character-specific content. However, these methods face a critical limitation: the inability to perform fine-grained control…
Image-to-video adaptation seeks to efficiently adapt image models for use in the video domain. Instead of finetuning the entire image backbone, many image-to-video adaptation paradigms use lightweight adapters for temporal modeling on top…
Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising…
Large text-to-video models trained on internet-scale data have demonstrated exceptional capabilities in generating high-fidelity videos from arbitrary textual descriptions. However, adapting these models to tasks with limited…
We present a novel framework for compositional video synthesis that leverages temporally consistent object-centric representations, extending our previous work, SlotAdapt, from images to video. While existing object-centric approaches…
Text-driven human motion generation has recently attracted considerable attention, allowing models to generate human motions based on textual descriptions. However, current methods neglect the influence of human attributes-such as age,…
Text-to-image diffusion models have shown remarkable capabilities of generating high-quality images closely aligned with textual inputs. However, the effectiveness of text guidance heavily relies on the CLIP text encoder, which is trained…
In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…
Dialog systems need to understand dynamic visual scenes in order to have conversations with users about the objects and events around them. Scene-aware dialog systems for real-world applications could be developed by integrating…
Recent advances in Text-To-Speech (TTS) synthesis have seen the popularity of multi-stage approaches that first predict semantic tokens and then generate acoustic tokens. In this paper, we extend the coarse-to-fine generation paradigm to…
Current video generation models usually convert signals indicating appearance and motion received from inputs (e.g., image, text) or latent spaces (e.g., noise vectors) into consecutive frames, fulfilling a stochastic generation process for…
Text-to-motion (T2M) generation is becoming a practical tool for animation and interactive avatars. However, modifying specific body parts while maintaining overall motion coherence remains challenging. Existing methods typically rely on…
Dialogue models falter in noisy, multi-speaker environments, often producing irrelevant responses and awkward turn-taking. We present AV-Dialog, the first multimodal dialog framework that uses both audio and visual cues to track the target…
We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…
Video-language pre-trained models have shown remarkable success in guiding video question-answering (VideoQA) tasks. However, due to the length of video sequences, training large-scale video-based models incurs considerably higher costs…
Audio-driven 3D facial animation has several virtual humans applications for content creation and editing. While several existing methods provide solutions for speech-driven animation, precise control over content (what) and style (how) of…
The spherical domain representation of 360 video/image presents many challenges related to the storage, processing, transmission and rendering of omnidirectional videos (ODV). Models of human visual attention can be used so that only a…
We address the task of video style transfer with diffusion models, where the goal is to preserve the context of an input video while rendering it in a target style specified by a text prompt. A major challenge is the lack of paired video…