Despite recent advancements in text-to-image generation, most existing methods struggle to create images with multiple objects and complex spatial relationships in the 3D world. To tackle this limitation, we introduce a generic AI system, namely MUSES, for 3D-controllable image generation from user queries. Specifically, our MUSES develops a progressive workflow with three key components, including (1) Layout Manager for 2D-to-3D layout lifting, (2) Model Engineer for 3D object acquisition and calibration, (3) Image Artist for 3D-to-2D image rendering. By mimicking the collaboration of human professionals, this multi-modal agent pipeline facilitates the effective and automatic creation of images with 3D-controllable objects, through an explainable integration of top-down planning and bottom-up generation. Additionally, existing benchmarks lack detailed descriptions of complex 3D spatial relationships of multiple objects. To fill this gap, we further construct a new benchmark of T2I-3DisBench (3D image scene), which describes diverse 3D image scenes with 50 detailed prompts. Extensive experiments show the state-of-the-art performance of MUSES on both T2I-CompBench and T2I-3DisBench, outperforming recent strong competitors such as DALL-E 3 and Stable Diffusion 3. These results demonstrate a significant step forward for MUSES in bridging natural language, 2D image generation, and 3D world.

Current multimodal large language models (MLLMs) struggle with fine-grained or precise understanding of visuals although they give comprehensive perception and reasoning in a spectrum of vision applications. Recent studies either develop tool-using or unify specific visual tasks into the autoregressive framework, often at the expense of overall multimodal performance. To address this issue and enhance MLLMs with visual tasks in a scalable fashion, we propose Task Preference Optimization (TPO), a novel method that utilizes differentiable task preferences derived from typical fine-grained visual tasks. TPO introduces learnable task tokens that establish connections between multiple task-specific heads and the MLLM. By leveraging rich visual labels during training, TPO significantly enhances the MLLM’s multimodal capabilities and task-specific performance. Through multi-task co-training within TPO, we observe synergistic benefits that elevate individual task performance beyond what is achievable through single-task training methodologies. Our instantiation of this approach with VideoChat and LLaVA demonstrates an overall 14.6% improvement in multimodal performance compared to baseline models. Additionally, MLLM-TPO demonstrates robust zero-shot capabilities across various tasks, performing comparably to state-of-the-art supervised models.

Despite the recent advancement in video stylization, most existing methods struggle to render any video with complex transitions, based on an open style description of user query. To fill this gap, we introduce a generic multi-agent system for video stylization, V-Stylist, by a novel collaboration and reflection paradigm of multi-modal large language models. Specifically, our V-Stylist is a systematical workflow with three key roles: (1) Video Parser decomposes the input video into a number of shots and generates their text prompts of key shot content. Via a concise video-to-shot prompting paradigm, it allows our V-Stylist to effectively handle videos with complex transitions. (2) Style Parser identifies the style in the user query and progressively search the matched style model from a style tree. Via a robust tree-of-thought searching paradigm, it allows our V-Stylist to precisely specify vague style preference in the open user query. (3) Style Artist leverages the matched model to render all the video shots into the required style. Via a novel multi-round self-reflection paradigm, it allows our V-Stylist to adaptively adjust detail control, according to the style requirement. With such a distinct design of mimicking human professionals, our V-Stylist achieves a major breakthrough over the primary challenges for effective and automatic video stylization. Moreover, we further construct a new benchmark Text-driven Video Stylization Benchmark (TVSBench), which fills the gap to assess various stylization of complex videos on open user queries. Extensive experiments show that, V-Stylist achieves the state-of-the-art, e.g.,V-Stylist surpasses FRESCO and ControlVideo by 6.05% and 4.51% respectively in overall average metrics, marking a significant advance in video stylization.

Creating high-quality data for training robust language-instructed agents is a long-lasting challenge in embodied AI. In this paper, we introduce a Self-Refining Data Flywheel (SRDF) that generates high-quality and large-scale navigational instruction-trajectory pairs by iteratively refining the data pool through the collaboration between two models, the instruction generator and the navigator, without any human-in-the-loop annotation. Specifically, SRDF starts with using a base generator to create an initial data pool for training a base navigator, followed by applying the trained navigator to filter the data pool. This leads to higher-fidelity data to train a better generator, which can, in turn, produce higher-quality data for training the next-round navigator. Such a flywheel establishes a data self-refining process, yielding a continuously improved and highly effective dataset for large-scale language-guided navigation learning. Our experiments demonstrate that after several flywheel rounds, the navigator elevates the performance boundary from 70\% to 78\% SPL on the classic R2R test set, surpassing human performance (76\%) for the first time. Meanwhile, this process results in a superior generator, evidenced by a SPICE increase from 23.5 to 26.2, better than all previous VLN instruction generation methods. Finally, we demonstrate the scalability of our method through increasing environment and instruction diversity, and the generalization ability of our pre-trained navigator across various downstream navigation tasks, surpassing state-of-the-art methods by a large margin in all cases.

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in short video understanding. However, understanding long-form videos still remains challenging for MLLMs. This paper proposes TimeSuite, a collection of new designs to adapt the existing short-form video MLLMs for long video understanding, including a simple yet efficient framework to process long video sequence, a high-quality video dataset for grounded tuning of MLLMs, and a carefully-designed instruction tuning task to explicitly incorporate the grounding supervision in the traditional QA format. Specifically, based on VideoChat, we propose our long-video MLLM, coined as VideoChat-T, by implementing a token shuffling to compress long video tokens and introducing Temporal Adaptive Position Encoding (TAPE) to enhance the temporal awareness of visual representation. Meanwhile, we introduce the TimePro, a comprehensive grounding-centric instruction tuning dataset composed of 9 tasks and 349k high-quality grounded annotations. Notably, we design a new instruction tuning task type, called Temporal Grounded Caption, to peform detailed video descriptions with the corresponding time stamps prediction. This explicit temporal location prediction will guide MLLM to correctly attend on the visual content when generating description, and thus reduce the hallucination risk caused by the LLMs. Experimental results demonstrate that our TimeSuite provides a successful solution to enhance the long video understanding capability of short-form MLLM, achieving improvement of 5.6% and 6.8% on the benchmarks of Egoschema and VideoMME, respectively. In addition, VideoChat-T exhibits robust zero-shot temporal grounding capabilities, significantly outperforming the existing state-of-the-art MLLMs. After fine-tuning, it performs on par with the traditional supervised expert models.

Diffusion models have driven the advancement of vision generation over the past years. However, it is often difficult to apply these large models in downstream tasks, due to massive fine-tuning cost. Recently, Low-Rank Adaptation (LoRA) has been applied for efficient tuning of diffusion models. Unfortunately, the capabilities of LoRA-tuned diffusion models are limited, since the same LoRA is used for different timesteps of the diffusion process. To tackle this problem, we introduce a general and concise TimeStep Master (TSM) paradigm with two key fine-tuning stages. In the fostering stage (1-stage), we apply different LoRAs to fine-tune the diffusion model at different timestep intervals. This results in different TimeStep LoRA experts that can effectively capture different noise levels. In the assembling stage (2-stage), we design a novel asymmetrical mixture of TimeStep LoRA experts, via core-context collaboration of experts at multi-scale intervals. For each timestep, we leverage TimeStep LoRA expert within the smallest interval as the core expert without gating, and use experts within the bigger intervals as the context experts with time-dependent gating. Consequently, our TSM can effectively model the noise level via the expert in the finest interval, and adaptively integrate contexts from the experts of other scales, boosting the versatility of diffusion models. To show the effectiveness of our TSM paradigm, we conduct extensive experiments on three typical and popular LoRA-related tasks of diffusion models, including domain adaptation, post-pretraining, and model distillation. Our TSM achieves the state-of-the-art results on all these tasks, throughout various model structures (UNet, DiT and MM-DiT) and visual data modalities (Image, Video), showing its remarkable generalization capacity.

Open-world video recognition is challenging since traditional networks are not generalized well on complex environment variations. Alternatively, foundation models with rich knowledge have recently shown their generalization power. However, how to apply such knowledge has not been fully explored for open-world video recognition. To this end, we propose a generic knowledge transfer pipeline, which progressively exploits and integrates external multimodal knowledge from foundation models to boost open-world video recognition. We name it PCA , based on three stages of P ercept, C hat, and A dapt. First, we perform Percept process to reduce the video domain gap and obtain external visual knowledge. Second, we generate rich linguistic semantics as external textual knowledge in Chat stage. Finally, we blend external multimodal knowledge in Adapt stage, by inserting multimodal knowledge adaptation modules into networks. We conduct extensive experiments on three challenging open-world video benchmarks, i.e., TinyVIRAT, ARID, and QV-Pipe. Our approach achieves state-of-the-art performance on all three datasets.

With the rapid development of Multi-modal Large language Models (MLLMs), a number of diagnostic bench-marks have recently emerged to evaluate the comprehension capabilities of these models. However, most bench-marks predominantly assess spatial understanding in the static image tasks, while overlooking temporal understanding in the dynamic video tasks. To alleviate this issue, we introduce a comprehensive Multi-modal Video understanding Benchmark, namely MVBench, which covers 20 chal-lenging video tasks that cannot be effectively solved with a single frame. Specifically, we first introduce a novel static-to-dynamic method to define these temporal-related tasks. By transforming various static tasks into dynamic ones, we enable the systematic generation of video tasks that require a broad spectrum of temporal skills, ranging from perception to cognition. Then, guided by the task definition, we au-tomatically convert public video annotations into multiple-choice QA to evaluate each task. On one hand, such a distinct paradigm allows us to build MVBench efficiently, without much manual intervention. On the other hand, it guarantees evaluation fairness with ground-truth video an-notations, avoiding the biased scoring of LLMs. More-over, we further develop a robust video MLLM baseline, i.e., VideoChat2, by progressive multi-modal training with di-verse instruction-tuning data. The extensive results on our MVBench reveal that, the existing MLLMs are far from sat-isfactory in temporal understanding, while our VideoChat2 largely surpasses these leading models by over 15% on MVBench. All models and data are available at https://github.com/OpenGVLab/Ask-Anything.

In this work, we present Vlogger, a generic AI systemfor generating a minute-level video blog (i.e., vlog) of user de-scriptions. Different from short videos with a few seconds, vlog often contains a complex storyline with diversified scenes, which is challenging for most existing video generation approaches. To break through this bottleneck, our Vlogger smartly leverages Large Language Model (LLM) as Director and decomposes a long video generation task of vlog into four key stages, where we invoke various foundation models to play the critical roles of vlog profession-als, including (1) Script, (2) Actor, (3) ShowMaker, and (4) Voicer. With such a design of mimicking human beings, our Vlogger can generate vlogs through explainable cooperation of top-down planning and bottom-up shooting. More-over, we introduce a novel video diffusion model, Show-Maker, which serves as a videographer in our Vlogger for generating the video snippet of each shooting scene. By incorporating Script and Actor attentively as textual and visual prompts, it can effectively enhance spatial-temporal coherence in the snippet. Besides, we design a concise mixed training paradigm for ShowMaker, boosting its ca-pacity for both T2V generation and prediction. Finally, the extensive experiments show that our method achieves state-of-the-art performance on zero-shot T2V generation and prediction tasks. More importantly, Vlogger can generate over 5-minute vlogs from open-world descriptions, without loss of video coherence on script and actor.

This paper introduces InternVid, a large-scale video-centric multimodal dataset that enables learning powerful and transferable video-text representations for multimodal understanding and generation. InternVid contains over 7 million videos lasting nearly 760K hours, yielding 234M video clips accompanied by detailed descriptions of total 4.1B words. Our core contribution is to develop a scalable approach to autonomously build a high-quality video-text dataset with large language models (LLM), thereby showcasing its efficacy in learning video-language representation at scale. Specifically, we utilize a multi-scale approach to generate video-related descriptions. Furthermore, we introduce ViCLIP, a video-text representation learning model based on ViT-L. Learned on InternVid via contrastive learning, this model demonstrates leading zero-shot action recognition and competitive video retrieval performance. Beyond basic video understanding tasks like recognition and retrieval, our dataset and model have broad applications. They are particularly beneficial for generating interleaved video-text data for learning a video-centric dialogue system, advancing video-to-text and text-to-video generation research. These proposed resources provide a tool for researchers and practitioners interested in multimodal video understanding and generation.

Vision-language foundation models (such as CLIP) have recently shown their power in transfer learning, owing to large-scale image-text pre-training. However, target domain data in the downstream tasks can be highly different from the pre-training phase, which makes it hard for such a single model to generalize well. Alternatively, there exists a wide range of expert models that contain diversified vision and/or language knowledge pre-trained on different modalities, tasks, networks, and datasets. Unfortunately, these models are "isolated agents" with heterogeneous structures, and how to integrate their knowledge for generalizing CLIP-like models has not been fully explored. To bridge this gap, we propose a general and concise TransAgent framework, which transports the knowledge of the isolated agents in a unified manner, and effectively guides CLIP to generalize with multi-source knowledge distillation. With such a distinct framework, we flexibly collaborate with 11 heterogeneous agents to empower vision-language foundation models, without further cost in the inference phase. Finally, our TransAgent achieves state-of-the-art performance on 11 visual recognition datasets. Under the same low-shot setting, it outperforms the popular CoOp with around 10\% on average, and 20\% on EuroSAT which contains large domain shifts.

Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain. Although VideoMAE has trained a robust ViT from limited data, its low-level reconstruction poses convergence difficulties and conflicts with high-level cross-modal alignment. This paper proposes a training-efficient method for temporal-sensitive VFMs that integrates the benefits of existing methods. To increase data efficiency, we mask out most of the low-semantics video tokens, but selectively align the unmasked tokens with IFM, which serves as the UnMasked Teacher (UMT). By providing semantic guidance, our method enables faster convergence and multi-modal friendliness. With a progressive pre-training framework, our model can handle various tasks including scene-related, temporal-related, and complex video-language understanding. Using only public sources for pre-training in 6 days on 32 A100 GPUs, our scratch-built ViT-L/16 achieves state-of-the-art performances on various video tasks.

The prolific performances of Vision Transformers (ViTs) in image tasks have prompted research into adapting the image ViTs for video tasks. However, the substantial gap between image and video impedes the spatiotemporal learning of these image-pretrained models. Though video-specialized models like UniFormer can transfer to the video domain more seamlessly, their unique architectures require prolonged image pretraining, limiting the scalability. Given the emergence of powerful open-source image ViTs, we propose unlocking their potential for video understanding with efficient UniFormer designs. We call the resulting model UniFormerV2, since it inherits the concise style of the Uni-Former block, while redesigning local and global relation aggregators that seamlessly integrate advantages from both ViTs and UniFormer. Our UniFormerV2 achieves state-of-the-art performances on 8 popular video benchmarks, including scene-related Kinetics-400/600/700, heterogeneous Moments in Time, temporal-related Something-Something V1/V2, and untrimmed ActivityNet and HACS. It is note-worthy that to the best of our knowledge, UniFormerV2 is the first to elicit 90% top-1 accuracy on Kinetics-400.

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have been two dominant frameworks in the past few years. Though CNNs can efficiently decrease local redundancy by convolution within a small neighborhood, the limited receptive field makes it hard to capture global dependency. Alternatively, ViTs can effectively capture long-range dependency via self-attention, while blind similarity comparisons among all the tokens lead to high redundancy. To resolve these problems, we propose a novel Unified transFormer (UniFormer), which can seamlessly integrate the merits of convolution and self-attention in a concise transformer format. Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing tackling both redundancy and dependency for efficient and effective representation learning. Finally, we flexibly stack our blocks into a new powerful backbone, and adopt it for various vision tasks from image to video domain, from classification to dense prediction. Without any extra training data, our UniFormer achieves 86.3 top-1 accuracy on ImageNet-1 K classification task. With only ImageNet-1 K pre-training, it can simply achieve state-of-the-art performance in a broad range of downstream tasks. It obtains 82.9/84.8 top-1 accuracy on Kinetics-400/600, 60.9/71.2 top-1 accuracy on Something-Something V1/V2 video classification tasks, 53.8 box AP and 46.4 mask AP on COCO object detection task, 50.8 mIoU on ADE20 K semantic segmentation task, and 77.4 AP on COCO pose estimation task. Moreover, we build an efficient UniFormer with a concise hourglass design of token shrinking and recovering, which achieves 2-4[Formula: see text] higher throughput than the recent lightweight models.

Visual tempos show the dynamics of action instances, characterizing the diversity of the actions, such as walking slowly and running quickly. To facilitate action recognition, it is essential to capture visual tempos. To this end, previous methods sample raw videos at multiple frame rates or integrate multi-scale temporal features. These methods inevitably introduce two-stream networks or feature-level pyramid structures, leading to expensive computation. In this work, we propose a progressive difference method to capture visual tempos for efficient action recognition, by computing coarse-to-fine motion information within a small neighborhood around temporal frames. Specifically, the uniform sampling method is first applied to each video, and then first-order temporal differences around each frame are calculated to describe local motions. On the basis of differences, further computing the variations of differences, namely second-order differences, can gradually capture fine-grained spatiotemporal features and characterize the areas where the motion cues are more prominent. On one hand, multi-order motion differences can be combined with raw input to describe the diversity of the actions. On the other hand, the variations of first-order differences information can be used to activate first-order salient motion regions, thereby facilitating the discrimination of finer-grained actions. Our method can be combined with existing backbones in a plug-and-play manner. Extensive experiments are conducted on several video benchmarks, including Kinetics400, HMDB51, UCF101, UAV-Human, Something-Something V1 and V2. We also give detailed analysis and qualitative experiments to demonstrate the effectiveness of our method.

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in open-vocabulary settings. However, it remains under explored that whether CLIP, pre-trained by large-scale image-text pairs in 2D, can be generalized to 3D recognition. In this paper, we identify such a setting is feasible by proposing PointCLIP, which conducts alignment between CLIP-encoded point clouds and 3D category texts. Specifically, we encode a point cloud by projecting it onto multi-view depth maps and aggregate the view-wise zero-shot prediction in an end-to-end manner, which achieves efficient knowledge transfer from 2D to 3D. We further design an inter-view adapter to better extract the global feature and adaptively fuse the 3D few-shot knowledge into CLIP pre-trained in 2D. By just fine-tuning the adapter under few-shot settings, the performance of PointCLIP could be largely improved. In addition, we observe the knowledge complementary property between PointCLIP and classical 3D-supervised networks. Via simple ensemble during inference, PointCLIP contributes to favorable performance enhancement over state-of-the-art 3D networks. Therefore, PointCLIP is a promising alternative for effective 3D point cloud understanding under low data regime with marginal resource cost. We conduct thorough experiments on Model-NetlO, ModelNet40 and ScanObjectNN to demonstrate the effectiveness of PointCLIP. Code is available at https://github.com/ZrrSkywalker/PointCLIP.

We focus on the problem of novel-view human action synthesis. Given an action video, the goal is to generate the same action from an unseen viewpoint. Naturally, novel view video synthesis is more challenging than image synthesis. It requires the synthesis of a sequence of realistic frames with temporal coherency. Besides, transferring different actions to a novel target view requires awareness of action category and viewpoint change simultaneously. To address these challenges we propose a novel framework named Pose-guided Action Separable Generative Adversarial Net (PAS-GAN), which utilizes pose to alleviate the difficulty of this task. First, we propose a recurrent pose-transformation module which transforms actions from the source view to the target view and generates novel view pose sequence in 2D coordinate space. Second, a well-transformed pose sequence enables us to separate the action and background in the target view. We employ a novel local-global spatial transformation module to effectively generate sequential video features in the target view using these action and background features. Finally, the generated video features are used to synthesize human action with the help of a 3D decoder. Moreover, to focus on dynamic action in the video, we propose a novel multi-scale action-separable loss which further improves the video quality. We conduct extensive experiments on two large-scale multi-view human action datasets, NTU-RGBD and PKU-MMD, demonstrating the effectiveness of PAS-GAN which outperforms existing approaches. The codes and models will be available on https://github.com/xhl-video/PAS-GAN.