相关论文: HiTVideo: Hierarchical Tokenizers for Enhancing Te…
Video tokenizers are essential for latent video diffusion models, converting raw video data into spatiotemporally compressed latent spaces for efficient training. However, extending state-of-the-art video tokenizers to achieve a temporal…
Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial…
Recent breakthroughs in video autoencoders (Video AEs) have advanced video generation, but existing methods fail to efficiently model spatio-temporal redundancies in dynamics, resulting in suboptimal compression factors. This shortfall…
In light of recent advances in multimodal Large Language Models (LLMs), there is increasing attention to scaling them from image-text data to more informative real-world videos. Compared to static images, video poses unique challenges for…
The enhanced Deep Hierarchical Video Compression-DHVC 2.0-has been introduced. This single-model neural video codec operates across a broad range of bitrates, delivering not only superior compression performance to representative methods…
We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from…
Video represents the majority of internet traffic today, driving a continual race between the generation of higher quality content, transmission of larger file sizes, and the development of network infrastructure. In addition, the recent…
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…
Text-to-video (T2V) generation technology holds potential to transform multiple domains such as education, marketing, entertainment, and assistive technologies for individuals with visual or reading comprehension challenges, by creating…
This study focuses on a challenging yet promising task, Text-to-Sounding-Video (T2SV) generation, which aims to generate a video with synchronized audio from text conditions, meanwhile ensuring both modalities are aligned with text. Despite…
Video-to-Speech (VTS) generation aims to synthesize speech from a silent video without auditory signals. However, existing VTS methods disregard the hierarchical nature of speech, which spans coarse speaker-aware semantics to fine-grained…
Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…
Generating structured narrations for real-world e-commerce videos requires models to perceive fine-grained visual details and organize them into coherent, high-level stories--capabilities that existing approaches struggle to unify. We…
In this work, we present HieraTok, a novel multi-scale Vision Transformer (ViT)-based tokenizer that overcomes the inherent limitation of modeling single-scale representations. This is realized through two key designs: (1) multi-scale…
Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…
Long-context video modeling is critical for multimodal large language models (MLLMs), enabling them to process movies, online video streams, and so on. Despite its advances, handling long videos remains challenging due to the difficulty in…
Text-to-video (T2V) generation has gained significant attention due to its wide applications to video generation, editing, enhancement and translation, \etc. However, high-quality (HQ) video synthesis is extremely challenging because of the…
Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual…
The fundamental challenge in scaling Video Large Language Models (Video LLMs) to long-form video lies in managing the explosion of visual-token context length. Existing strategies predominantly focus on "post-hoc" token reduction --…
Diffusion-based text-to-video generation has witnessed impressive progress in the past year yet still falls behind text-to-image generation. One of the key reasons is the limited scale of publicly available data (e.g., 10M video-text pairs…