Baohan Xu

Bingwen Zhu, Yudong Jiang, Baohan Xu et al.

Anime video generation faces significant challenges due to the scarcity of anime data and unusual motion patterns, leading to issues such as motion distortion and flickering artifacts, which result in misalignment with human preferences. Existing reward models, designed primarily for real-world videos, fail to capture the unique appearance and consistency requirements of anime. In this work, we propose a pipeline to enhance anime video generation by leveraging human feedback for better alignment. Specifically, we construct the first multi-dimensional reward dataset for anime videos, comprising 30k human-annotated samples that incorporating human preferences for both visual appearance and visual consistency. Based on this, we develop AnimeReward, a powerful reward model that employs specialized vision-language models for different evaluation dimensions to guide preference alignment. Furthermore, we introduce Gap-Aware Preference Optimization (GAPO), a novel training method that explicitly incorporates preference gaps into the optimization process, enhancing alignment performance and efficiency. Extensive experiment results show that AnimeReward outperforms existing reward models, and the inclusion of GAPO leads to superior alignment in both quantitative benchmarks and human evaluations, demonstrating the effectiveness of our pipeline in enhancing anime video quality. Our code and dataset are publicly available at https://github.com/bilibili/Index-anisora.

Yudong Jiang, Baohan Xu, Siqian Yang et al.

Animation has gained significant interest in the recent film and TV industry. Despite the success of advanced video generation models like Sora, Kling, and CogVideoX in generating natural videos, they lack the same effectiveness in handling animation videos. Evaluating animation video generation is also a great challenge due to its unique artist styles, violating the laws of physics and exaggerated motions. In this paper, we present a comprehensive system, AniSora, designed for animation video generation, which includes a data processing pipeline, a controllable generation model, and an evaluation benchmark. Supported by the data processing pipeline with over 10M high-quality data, the generation model incorporates a spatiotemporal mask module to facilitate key animation production functions such as image-to-video generation, frame interpolation, and localized image-guided animation. We also collect an evaluation benchmark of 948 various animation videos, with specifically developed metrics for animation video generation. Our entire project is publicly available on https://github.com/bilibili/Index-anisora/tree/main.

Lisai Zhang, Baohan Xu, Siqian Yang et al.

We present AniME, a director-oriented multi-agent system for automated long-form anime production, covering the full workflow from a story to the final video. The director agent keeps a global memory for the whole workflow, and coordinates several downstream specialized agents. By integrating customized Model Context Protocol (MCP) with downstream model instruction, the specialized agent adaptively selects control conditions for diverse sub-tasks. AniME produces cinematic animation with consistent characters and synchronized audio visual elements, offering a scalable solution for AI-driven anime creation.

Rui An, Xingtian Shi, Baohan Xu

As one of the most well-known artificial feature sampler, the sliding window is widely used in scenarios where spatial and temporal information exists, such as computer vision, natural language process, data stream, and time series. Among which time series is common in many scenarios like credit card payment, user behavior, and sensors. General feature selection for features extracted by sliding window aggregate calls for time-consuming iteration to generate features, and then traditional feature selection methods are employed to rank them. The decision of key parameter, i.e. the period of sliding windows, depends on the domain knowledge and calls for trivial. Currently, there is no automatic method to handle the sliding window aggregate features selection. As the time consumption of feature generation with different periods and sliding windows is huge, it is very hard to enumerate them all and then select them. In this paper, we propose a general framework using Markov Chain to solve this problem. This framework is very efficient and has high accuracy, such that it is able to perform feature selection on a variety of features and period options. We show the detail by 2 common sliding windows and 3 types of aggregation operators. And it is easy to extend more sliding windows and aggregation operators in this framework by employing existing theory about Markov Chain.

Xingjiao Wu, Baohan Xu, Yingbin Zheng et al.

Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting. With the ubiquitous video capture devices in public safety field, how to effectively apply the crowd counting technique to video content has become an urgent problem. In this paper, we introduce a novel framework based on temporal aware modeling of the relationship between video frames. The proposed network contains a few dilated residual blocks, and each of them consists of the layers that compute the temporal convolutions of features from the adjacent frames to improve the prediction. To alleviate the expensive computation and satisfy the demand of fast video crowd counting, we also introduce a lightweight network to balance the computational cost with representation ability. We conduct experiments on the crowd counting benchmarks and demonstrate its superiority in terms of effectiveness and efficiency over previous video-based approaches.

Baohan Xu, Yanwei Fu, Yu-Gang Jiang et al.

Emotion is a key element in user-generated videos. However, it is difficult to understand emotions conveyed in such videos due to the complex and unstructured nature of user-generated content and the sparsity of video frames expressing emotion. In this paper, for the first time, we study the problem of transferring knowledge from heterogeneous external sources, including image and textual data, to facilitate three related tasks in understanding video emotion: emotion recognition, emotion attribution and emotion-oriented summarization. Specifically, our framework (1) learns a video encoding from an auxiliary emotional image dataset in order to improve supervised video emotion recognition, and (2) transfers knowledge from an auxiliary textual corpora for zero-shot recognition of emotion classes unseen during training. The proposed technique for knowledge transfer facilitates novel applications of emotion attribution and emotion-oriented summarization. A comprehensive set of experiments on multiple datasets demonstrate the effectiveness of our framework.