Discrete diffusion models have seen a surge of attention with applications on naturally discrete data such as language and graphs. Although discrete-time discrete diffusion has been established for a while, only recently Campbell et al. (2022) introduced the first framework for continuous-time discrete diffusion. However, their training and sampling processes differ significantly from the discrete-time version, necessitating nontrivial approximations for tractability. In this paper, we first present a series of mathematical simplifications of the variational lower bound that enable more accurate and easy-to-optimize training for discrete diffusion. In addition, we derive a simple formulation for backward denoising that enables exact and accelerated sampling, and importantly, an elegant unification of discrete-time and continuous-time discrete diffusion. Thanks to simpler analytical formulations, both forward and now also backward probabilities can flexibly accommodate any noise distribution, including different noise distributions for multi-element objects. Experiments show that our proposed USD3 (for Unified Simplified Discrete Denoising Diffusion) outperform all SOTA baselines on established datasets. We open-source our unified code at https://github.com/LingxiaoShawn/USD3.
We present VideoPoet, a language model capable of synthesizing high-quality video, with matching audio, from a large variety of conditioning signals. VideoPoet employs a decoder-only transformer architecture that processes multimodal inputs -- including images, videos, text, and audio. The training protocol follows that of Large Language Models (LLMs), consisting of two stages: pretraining and task-specific adaptation. During pretraining, VideoPoet incorporates a mixture of multimodal generative objectives within an autoregressive Transformer framework. The pretrained LLM serves as a foundation that can be adapted for a range of video generation tasks. We present empirical results demonstrating the model's state-of-the-art capabilities in zero-shot video generation, specifically highlighting VideoPoet's ability to generate high-fidelity motions. Project page: http://sites.research.google/videopoet/
We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of $512 \times 896$ resolution at $8$ frames per second.
While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, one crucial component is the visual tokenizer that maps pixel-space inputs to discrete tokens appropriate for LLM learning. In this paper, we introduce MAGVIT-v2, a video tokenizer designed to generate concise and expressive tokens for both videos and images using a common token vocabulary. Equipped with this new tokenizer, we show that LLMs outperform diffusion models on standard image and video generation benchmarks including ImageNet and Kinetics. In addition, we demonstrate that our tokenizer surpasses the previously top-performing video tokenizer on two more tasks: (1) video compression comparable to the next-generation video codec (VCC) according to human evaluations, and (2) learning effective representations for action recognition tasks.
In this work, we introduce Semantic Pyramid AutoEncoder (SPAE) for enabling frozen LLMs to perform both understanding and generation tasks involving non-linguistic modalities such as images or videos. SPAE converts between raw pixels and interpretable lexical tokens (or words) extracted from the LLM's vocabulary. The resulting tokens capture both the semantic meaning and the fine-grained details needed for visual reconstruction, effectively translating the visual content into a language comprehensible to the LLM, and empowering it to perform a wide array of multimodal tasks. Our approach is validated through in-context learning experiments with frozen PaLM 2 and GPT 3.5 on a diverse set of image understanding and generation tasks. Our method marks the first successful attempt to enable a frozen LLM to generate image content while surpassing state-of-the-art performance in image understanding tasks, under the same setting, by over 25%.
Visually-Rich Document Entity Retrieval (VDER) is a type of machine learning task that aims at recovering text spans in the documents for each of the entities in question. VDER has gained significant attention in recent years thanks to its broad applications in enterprise AI. Unfortunately, as document images often contain personally identifiable information (PII), publicly available data have been scarce, not only because of privacy constraints but also the costs of acquiring annotations. To make things worse, each dataset would often define its own sets of entities, and the non-overlapping entity spaces between datasets make it difficult to transfer knowledge between documents. In this paper, we propose a method to collect massive-scale, noisy, and weakly labeled data from the web to benefit the training of VDER models. Such a method will generate a huge amount of document image data to compensate for the lack of training data in many VDER settings. Moreover, the collected dataset named DocuNet would not need to be dependent on specific document types or entity sets, making it universally applicable to all VDER tasks. Empowered by DocuNet, we present a lightweight multimodal architecture named UniFormer, which can learn a unified representation from text, layout, and image crops without needing extra visual pertaining. We experiment with our methods on popular VDER models in various settings and show the improvements when this massive dataset is incorporated with UniFormer on both classic entity retrieval and few-shot learning settings.
We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging Kinetics-600. (ii) MAGVIT outperforms existing methods in inference time by two orders of magnitude against diffusion models and by 60x against autoregressive models. (iii) A single MAGVIT model supports ten diverse generation tasks and generalizes across videos from different visual domains. The source code and trained models will be released to the public at https://magvit.cs.cmu.edu.
Score-based modeling through stochastic differential equations (SDEs) has provided a new perspective on diffusion models, and demonstrated superior performance on continuous data. However, the gradient of the log-likelihood function, i.e., the score function, is not properly defined for discrete spaces. This makes it non-trivial to adapt \textcolor{\cdiff}{the score-based modeling} to categorical data. In this paper, we extend diffusion models to discrete variables by introducing a stochastic jump process where the reverse process denoises via a continuous-time Markov chain. This formulation admits an analytical simulation during backward sampling. To learn the reverse process, we extend score matching to general categorical data and show that an unbiased estimator can be obtained via simple matching of the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
Activity detection is one of the attractive computer vision tasks to exploit the video streams captured by widely installed cameras. Although achieving impressive performance, conventional activity detection algorithms are usually designed under certain constraints, such as using trimmed and/or object-centered video clips as inputs. Therefore, they failed to deal with the multi-scale multi-instance cases in real-world unconstrained video streams, which are untrimmed and have large field-of-views. Real-time requirements for streaming analysis also mark brute force expansion of them unfeasible. To overcome these issues, we propose Argus++, a robust real-time activity detection system for analyzing unconstrained video streams. The design of Argus++ introduces overlapping spatio-temporal cubes as an intermediate concept of activity proposals to ensure coverage and completeness of activity detection through over-sampling. The overall system is optimized for real-time processing on standalone consumer-level hardware. Extensive experiments on different surveillance and driving scenarios demonstrated its superior performance in a series of activity detection benchmarks, including CVPR ActivityNet ActEV 2021, NIST ActEV SDL UF/KF, TRECVID ActEV 2020/2021, and ICCV ROAD 2021.
We focus on the problem of detecting traffic events in a surveillance scenario, including the detection of both vehicle actions and traffic collisions. Existing event detection systems are mostly learning-based and have achieved convincing performance when a large amount of training data is available. However, in real-world scenarios, collecting sufficient labeled training data is expensive and sometimes impossible (e.g. for traffic collision detection). Moreover, the conventional 2D representation of surveillance views is easily affected by occlusions and different camera views in nature. To deal with the aforementioned problems, in this paper, we propose a training-free monocular 3D event detection system for traffic surveillance. Our system firstly projects the vehicles into the 3D Euclidean space and estimates their kinematic states. Then we develop multiple simple yet effective ways to identify the events based on the kinematic patterns, which need no further training. Consequently, our system is robust to the occlusions and the viewpoint changes. Exclusive experiments report the superior result of our method on large-scale real-world surveillance datasets, which validates the effectiveness of our proposed system.