From Words to Worlds: Transforming One-line Prompt into Immersive Multi-modal Digital Stories with Communicative LLM Agent

Digital storytelling, essential in entertainment, education, and marketing, faces challenges in production scalability and flexibility. The StoryAgent framework, introduced in this paper, utilizes Large Language Models and generative tools to automate and refine digital storytelling. Employing a top-down story drafting and bottom-up asset generation approach, StoryAgent tackles key issues such as manual intervention, interactive scene orchestration, and narrative consistency. This framework enables efficient production of interactive and consistent narratives across multiple modalities, democratizing content creation and enhancing engagement. Our results demonstrate the framework's capability to produce coherent digital stories without reference videos, marking a significant advancement in automated digital storytelling.

An Intrinsic Vector Heat Network

Vector fields are widely used to represent and model flows for many science and engineering applications. This paper introduces a novel neural network architecture for learning tangent vector fields that are intrinsically defined on manifold surfaces embedded in 3D. Previous approaches to learning vector fields on surfaces treat vectors as multi-dimensional scalar fields, using traditional scalar-valued architectures to process channels individually, thus fail to preserve fundamental intrinsic properties of the vector field. The core idea of this work is to introduce a trainable vector heat diffusion module to spatially propagate vector-valued feature data across the surface, which we incorporate into our proposed architecture that consists of vector-valued neurons. Our architecture is invariant to rigid motion of the input, isometric deformation, and choice of local tangent bases, and is robust to discretizations of the surface. We evaluate our Vector Heat Network on triangle meshes, and empirically validate its invariant properties. We also demonstrate the effectiveness of our method on the useful industrial application of quadrilateral mesh generation.

On the Equivalency, Substitutability, and Flexibility of Synthetic Data

We study, from an empirical standpoint, the efficacy of synthetic data in real-world scenarios. Leveraging synthetic data for training perception models has become a key strategy embraced by the community due to its efficiency, scalability, perfect annotations, and low costs. Despite proven advantages, few studies put their stress on how to efficiently generate synthetic datasets to solve real-world problems and to what extent synthetic data can reduce the effort for real-world data collection. To answer the questions, we systematically investigate several interesting properties of synthetic data -- the equivalency of synthetic data to real-world data, the substitutability of synthetic data for real data, and the flexibility of synthetic data generators to close up domain gaps. Leveraging the M3Act synthetic data generator, we conduct experiments on DanceTrack and MOT17. Our results suggest that synthetic data not only enhances model performance but also demonstrates substitutability for real data, with 60% to 80% replacement without performance loss. In addition, our study of the impact of synthetic data distributions on downstream performance reveals the importance of flexible data generators in narrowing domain gaps for improved model adaptability.

The Importance of Multimodal Emotion Conditioning and Affect Consistency for Embodied Conversational Agents

Previous studies regarding the perception of emotions for embodied virtual agents have shown the effectiveness of using virtual characters in conveying emotions through interactions with humans. However, creating an autonomous embodied conversational agent with expressive behaviors presents two major challenges. The first challenge is the difficulty of synthesizing the conversational behaviors for each modality that are as expressive as real human behaviors. The second challenge is that the affects are modeled independently, which makes it difficult to generate multimodal responses with consistent emotions across all modalities. In this work, we propose a conceptual framework, ACTOR (Affect-Consistent mulTimodal behaviOR generation), that aims to increase the perception of affects by generating multimodal behaviors conditioned on a consistent driving affect. We have conducted a user study with 199 participants to assess how the average person judges the affects perceived from multimodal behaviors that are consistent and inconsistent with respect to a driving affect. The result shows that among all model conditions, our affect-consistent framework receives the highest Likert scores for the perception of driving affects. Our statistical analysis suggests that making a modality affect-inconsistent significantly decreases the perception of driving affects. We also observe that multimodal behaviors conditioned on consistent affects are more expressive compared to behaviors with inconsistent affects. Therefore, we conclude that multimodal emotion conditioning and affect consistency are vital to enhancing the perception of affects for embodied conversational agents.

Learning from Synthetic Human Group Activities

The understanding of complex human interactions and group activities has garnered attention in human-centric computer vision. However, the advancement of the related tasks is hindered due to the difficulty of obtaining large-scale labeled real-world datasets. To mitigate the issue, we propose M3Act, a multi-view multi-group multi-person human atomic action and group activity data generator. Powered by the Unity engine, M3Act contains simulation-ready 3D scenes and human assets, configurable lighting and camera systems, highly parameterized modular group activities, and a large degree of domain randomization during the data generation process. Our data generator is capable of generating large-scale datasets of human activities with multiple viewpoints, modalities (RGB images, 2D poses, 3D motions), and high-quality annotations for individual persons and multi-person groups (2D bounding boxes, instance segmentation masks, individual actions and group activity categories). Using M3Act, we perform synthetic data pre-training for 2D skeleton-based group activity recognition and RGB-based multi-person pose tracking. The results indicate that learning from our synthetic datasets largely improves the model performances on real-world datasets, with the highest gain of 5.59% and 7.32% respectively in group and person recognition accuracy on CAD2, as well as an improvement of 6.63 in MOTP on HiEve. Pre-training with our synthetic data also leads to faster model convergence on downstream tasks (up to 6.8% faster). Moreover, M3Act opens new research problems for 3D group activity generation. We release M3Act3D, an 87.6-hour 3D motion dataset of human activities with larger group sizes and higher complexity of inter-person interactions than previous multi-person datasets. We define multiple metrics and propose a competitive baseline for the novel task.

Procedure-Aware Pretraining for Instructional Video Understanding

Our goal is to learn a video representation that is useful for downstream procedure understanding tasks in instructional videos. Due to the small amount of available annotations, a key challenge in procedure understanding is to be able to extract from unlabeled videos the procedural knowledge such as the identity of the task (e.g., 'make latte'), its steps (e.g., 'pour milk'), or the potential next steps given partial progress in its execution. Our main insight is that instructional videos depict sequences of steps that repeat between instances of the same or different tasks, and that this structure can be well represented by a Procedural Knowledge Graph (PKG), where nodes are discrete steps and edges connect steps that occur sequentially in the instructional activities. This graph can then be used to generate pseudo labels to train a video representation that encodes the procedural knowledge in a more accessible form to generalize to multiple procedure understanding tasks. We build a PKG by combining information from a text-based procedural knowledge database and an unlabeled instructional video corpus and then use it to generate training pseudo labels with four novel pre-training objectives. We call this PKG-based pre-training procedure and the resulting model Paprika, Procedure-Aware PRe-training for Instructional Knowledge Acquisition. We evaluate Paprika on COIN and CrossTask for procedure understanding tasks such as task recognition, step recognition, and step forecasting. Paprika yields a video representation that improves over the state of the art: up to 11.23% gains in accuracy in 12 evaluation settings. Implementation is available at https://github.com/salesforce/paprika.

MSI: Maximize Support-Set Information for Few-Shot Segmentation

FSS(Few-shot segmentation)~aims to segment a target class with a small number of labeled images (support Set). To extract information relevant to target class, a dominant approach in best performing FSS baselines removes background features using support mask. We observe that this support mask presents an information bottleneck in several challenging FSS cases e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method (MSI), which maximizes the support-set information by exploiting two complementary source of features in generating super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS baselines. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves the performance by visible margins and allows faster convergence. Our codes and models will be publicly released.

An Information-Theoretic Approach for Estimating Scenario Generalization in Crowd Motion Prediction

Learning-based approaches to modeling crowd motion have become increasingly successful but require training and evaluation on large datasets, coupled with complex model selection and parameter tuning. To circumvent this tremendously time-consuming process, we propose a novel scoring method, which characterizes generalization of models trained on source crowd scenarios and applied to target crowd scenarios using a training-free, model-agnostic Interaction + Diversity Quantification score, ISDQ. The Interaction component aims to characterize the difficulty of scenario domains, while the diversity of a scenario domain is captured in the Diversity score. Both scores can be computed in a computation tractable manner. Our experimental results validate the efficacy of the proposed method on several simulated and real-world (source,target) generalization tasks, demonstrating its potential to select optimal domain pairs before training and testing a model.

HMFS: Hybrid Masking for Few-Shot Segmentation

We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique, introduced by [1], to discard irrelevant feature activations to facilitate reliable segmentation mask prediction. A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects. In this paper, we develop a simple, effective, and efficient approach to enhance feature masking (FM). We dub the enhanced FM as hybrid masking (HM). Specifically, we compensate for the loss of fine-grained spatial details in FM technique by investigating and leveraging a complementary basic input masking method [2]. To validate the effectiveness of HM, we instantiate it into a strong baseline [3], and coin the resulting framework as HMFS. Experimental results on three publicly available benchmarks reveal that HMFS outperforms the current state-of-the-art methods by visible margins.

MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Prediction

Accurate long-term trajectory prediction in complex scenes, where multiple agents (e.g., pedestrians or vehicles) interact with each other and the environment while attempting to accomplish diverse and often unknown goals, is a challenging stochastic forecasting problem. In this work, we propose MUSE, a new probabilistic modeling framework based on a cascade of Conditional VAEs, which tackles the long-term, uncertain trajectory prediction task using a coarse-to-fine multi-factor forecasting architecture. In its Macro stage, the model learns a joint pixel-space representation of two key factors, the underlying environment and the agent movements, to predict the long and short-term motion goals. Conditioned on them, the Micro stage learns a fine-grained spatio-temporal representation for the prediction of individual agent trajectories. The VAE backbones across the two stages make it possible to naturally account for the joint uncertainty at both levels of granularity. As a result, MUSE offers diverse and simultaneously more accurate predictions compared to the current state-of-the-art. We demonstrate these assertions through a comprehensive set of experiments on nuScenes and SDD benchmarks as well as PFSD, a new synthetic dataset, which challenges the forecasting ability of models on complex agent-environment interaction scenarios.