Related papers: EVATok: Adaptive Length Video Tokenization for Eff…
Vision-language models (VLMs) have recently expanded from static image understanding to video reasoning, but their scalability is fundamentally limited by the quadratic cost of processing dense frame sequences. Long videos often exceed the…
Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of choice.…
Adaptive bitrate (ABR) using conventional codecs cannot further modify the bitrate once a decision has been made, exhibiting limited adaptation capability. This may result in either overly conservative or overly aggressive bitrate…
Recent advancements in diffusion-based video generation have produced impressive and high-fidelity short videos. To extend these successes to generate coherent long videos, most video diffusion models (VDMs) generate videos in an…
Recently, token-based generation have demonstrated their effectiveness in image synthesis. As a representative example, non-autoregressive Transformers (NATs) can generate decent-quality images in a few steps. NATs perform generation in a…
Text-to-image retrieval is a fundamental task in multimedia processing, aiming to retrieve semantically relevant cross-modal content. Traditional studies have typically approached this task as a discriminative problem, matching the text and…
Video super-resolution (VSR) aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts. Although some progress has been made, there are grand challenges to effectively utilize temporal dependency…
Text-to-video diffusion models enable the generation of high-quality videos that follow text instructions, making it easy to create diverse and individual content. However, existing approaches mostly focus on high-quality short video…
Streaming video clips with large-scale video tokens impede vision transformers (ViTs) for efficient recognition, especially in video action detection where sufficient spatiotemporal representations are required for precise actor…
The vision transformer splits each image into a sequence of tokens with fixed length and processes the tokens in the same way as words in natural language processing. More tokens normally lead to better performance but considerably…
Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compared to continuous video representation. Previous discrete…
Continuous image tokenizers enable efficient visual generation, and those based on variational frameworks can learn smooth, structured latent representations through KL regularization. Yet this often leads to posterior collapse when using…
Recent multi-modal video generation models have achieved high visual quality, but their prohibitive latency and limited temporal stability hinder real-time deployment. Streaming inference exacerbates these issues, leading to pronounced…
State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they still frequently fail to compose complex scenes or follow logical temporal instructions. In this paper, we argue that many errors,…
Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for better learning and generation of diffusion models remain…
Autoregressive models have shown remarkable success in image generation by adapting sequential prediction techniques from language modeling. However, applying these approaches to images requires discretizing continuous pixel data through…
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling…
Auto-regressive (AR) models, initially successful in language generation, have recently shown promise in visual generation tasks due to their superior sampling efficiency. Unlike image generation, video generation requires a substantially…
The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…
Visual Autoregressive (VAR) has emerged as a promising approach in image generation, offering competitive potential and performance comparable to diffusion-based models. However, current AR-based visual generation models require substantial…