Fangqiu Yi

Xiangyu Chen, Jixiang Luo, Jingyu Xu et al.

Whether a video can be compressed at an extreme compression rate as low as 0.01%? To this end, we achieve the compression rate as 0.02% at some cases by introducing Generative Video Compression (GVC), a new framework that redefines the limits of video compression by leveraging modern generative video models to achieve extreme compression rates while preserving a perception-centric, task-oriented communication paradigm, corresponding to Level C of the Shannon-Weaver model. Besides, How we trade computation for compression rate or bandwidth? GVC answers this question by shifting the burden from transmission to inference: it encodes video into extremely compact representations and delegates content reconstruction to the receiver, where powerful generative priors synthesize high-quality video from minimal transmitted information. Is GVC practical and deployable? To ensure practical deployment, we propose a compression-computation trade-off strategy, enabling fast inference on consume-grade GPUs. Within the AI Flow framework, GVC opens new possibility for video communication in bandwidth- and resource-constrained environments such as emergency rescue, remote surveillance, and mobile edge computing. Through empirical validation, we demonstrate that GVC offers a viable path toward a new effective, efficient, scalable, and practical video communication paradigm.

Fangqiu Yi, Hongyu Wen, Tingting Jiang

Algorithms for the action segmentation task typically use temporal models to predict what action is occurring at each frame for a minute-long daily activity. Recent studies have shown the potential of Transformer in modeling the relations among elements in sequential data. However, there are several major concerns when directly applying the Transformer to the action segmentation task, such as the lack of inductive biases with small training sets, the deficit in processing long input sequence, and the limitation of the decoder architecture to utilize temporal relations among multiple action segments to refine the initial predictions. To address these concerns, we design an efficient Transformer-based model for action segmentation task, named ASFormer, with three distinctive characteristics: (i) We explicitly bring in the local connectivity inductive priors because of the high locality of features. It constrains the hypothesis space within a reliable scope, and is beneficial for the action segmentation task to learn a proper target function with small training sets. (ii) We apply a pre-defined hierarchical representation pattern that efficiently handles long input sequences. (iii) We carefully design the decoder to refine the initial predictions from the encoder. Extensive experiments on three public datasets demonstrate that effectiveness of our methods. Code is available at \url{https://github.com/ChinaYi/ASFormer}.

Fangqiu Yi, Tingting Jiang

Surgical phase recognition is of particular interest to computer assisted surgery systems, in which the goal is to predict what phase is occurring at each frame for a surgery video. Networks with multi-stage architecture have been widely applied in many computer vision tasks with rich patterns, where a predictor stage first outputs initial predictions and an additional refinement stage operates on the initial predictions to perform further refinement. Existing works show that surgical video contents are well ordered and contain rich temporal patterns, making the multi-stage architecture well suited for the surgical phase recognition task. However, we observe that when simply applying the multi-stage architecture to the surgical phase recognition task, the end-to-end training manner will make the refinement ability fall short of its wishes. To address the problem, we propose a new non end-to-end training strategy and explore different designs of multi-stage architecture for surgical phase recognition task. For the non end-to-end training strategy, the refinement stage is trained separately with proposed two types of disturbed sequences. Meanwhile, we evaluate three different choices of refinement models to show that our analysis and solution are robust to the choices of specific multi-stage models. We conduct experiments on two public benchmarks, the M2CAI16 Workflow Challenge, and the Cholec80 dataset. Results show that multi-stage architecture trained with our strategy largely boosts the performance of the current state-of-the-art single-stage model. Code is available at \url{https://github.com/ChinaYi/casual_tcn}.

Chi Zhang, Yuanzhi Liang, Xi Qiu et al.

Generating high-quality videos from textual descriptions poses challenges in maintaining temporal coherence and control over subject motion. We propose VAST (Video As Storyboard from Text), a two-stage framework to address these challenges and enable high-quality video generation. In the first stage, StoryForge transforms textual descriptions into detailed storyboards, capturing human poses and object layouts to represent the structural essence of the scene. In the second stage, VisionForge generates videos from these storyboards, producing high-quality videos with smooth motion, temporal consistency, and spatial coherence. By decoupling text understanding from video generation, VAST enables precise control over subject dynamics and scene composition. Experiments on the VBench benchmark demonstrate that VAST outperforms existing methods in both visual quality and semantic expression, setting a new standard for dynamic and coherent video generation.

Lei Zhao, Linfeng Feng, Dongxu Ge et al.

With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many are confined to a single task and small-scale datasets. To overcome these limitations, we introduce UniForm, a unified multi-task diffusion transformer that generates both audio and visual modalities in a shared latent space. By using a unified denoising network, UniForm captures the inherent correlations between sound and vision. Additionally, we propose task-specific noise schemes and task tokens, enabling the model to support multiple tasks with a single set of parameters, including video-to-audio, audio-to-video and text-to-audio-video generation. Furthermore, by leveraging large language models and a large-scale text-audio-video combined dataset, UniForm achieves greater generative diversity than prior approaches. Experiments show that UniForm achieves performance close to the state-of-the-art single-task models across three generation tasks, with generated content that is not only highly aligned with real-world data distributions but also enables more diverse and fine-grained generation.

Liying Yang, Jialun Liu, Jiakui Hu et al.

Generating high-quality 4D objects with spatial-temporal consistency is still formidable. Existing diffusion-based methods often struggle with spatial-temporal inconsistency, as they fail to leverage outputs from all previous timesteps to guide the generation at the current timestep. Therefore, we propose a Spatial-Temporal State Propagation AutoRegressive Model (4DSTAR), which generates 4D objects maintaining temporal-spatial consistency. 4DSTAR formulates the generation problem as the prediction of tokens that represent the 4D object. It consists of two key components: (1) The dynamic spatial-temporal state propagation autoregressive model (STAR) is proposed, which achieves spatial-temporal consistent generation. Unlike standard autoregressive models, STAR divides prediction tokens into groups based on timesteps. It models long-term dependencies by propagating spatial-temporal states from previous groups and utilizes these dependencies to guide generation at the next timestep. To this end, a spatial-temporal container is proposed, which dynamically updating the effective spatial-temporal state features from all historical groups, then updated features serve as conditional features to guide the prediction of the next token group. (2) The 4D VQ-VAE is proposed, which implicitly encodes the 4D structure into discrete space and decodes the discrete tokens predicted by STAR into temporally coherent dynamic 3D Gaussians. Experiments demonstrate that 4DSTAR generates spatial-temporal consistent 4D objects, and achieves performance competitive with diffusion models.

Fangqiu Yi, Jingyu Xu, Jiawei Shao et al.

Perceptual studies demonstrate that conditional diffusion models excel at reconstructing video content aligned with human visual perception. Building on this insight, we propose a video compression framework that leverages conditional diffusion models for perceptually optimized reconstruction. Specifically, we reframe video compression as a conditional generation task, where a generative model synthesizes video from sparse, yet informative signals. Our approach introduces three key modules: (1) Multi-granular conditioning that captures both static scene structure and dynamic spatio-temporal cues; (2) Compact representations designed for efficient transmission without sacrificing semantic richness; (3) Multi-condition training with modality dropout and role-aware embeddings, which prevent over-reliance on any single modality and enhance robustness. Extensive experiments show that our method significantly outperforms both traditional and neural codecs on perceptual quality metrics such as Fréchet Video Distance (FVD) and LPIPS, especially under high compression ratios.