While large-scale human motion capture datasets have advanced human motion generation, modeling and generating dynamic 3D human-object interactions (HOIs) remain challenging due to dataset limitations. Existing datasets often lack extensive, high-quality motion and annotation and exhibit artifacts such as contact penetration, floating, and incorrect hand motions. To address these issues, we introduce InterAct, a large-scale 3D HOI benchmark featuring dataset and methodological advancements. First, we consolidate and standardize 21.81 hours of HOI data from diverse sources, enriching it with detailed textual annotations. Second, we propose a unified optimization framework to enhance data quality by reducing artifacts and correcting hand motions. Leveraging the principle of contact invariance, we maintain human-object relationships while introducing motion variations, expanding the dataset to 30.70 hours. Third, we define six benchmarking tasks and develop a unified HOI generative modeling perspective, achieving state-of-the-art performance. Extensive experiments validate the utility of our dataset as a foundational resource for advancing 3D human-object interaction generation. The dataset will be publicly accessible to support further research in the field.

Text-conditioned human motion generation has experienced significant advancements with diffusion models trained on extensive motion capture data and corresponding textual annotations. However, extending such success to 3D dynamic human-object interaction (HOI) generation faces notable challenges, primarily due to the lack of large-scale interaction data and comprehensive descriptions that align with these interactions. This paper takes the initiative and showcases the potential of generating human-object interactions without direct training on text-interaction pair data. Our key insight in achieving this is that interaction semantics and dynamics can be decoupled. Being unable to learn interaction semantics through supervised training, we instead leverage pre-trained large models, synergizing knowledge from a large language model and a text-to-motion model. While such knowledge offers high-level control over interaction semantics, it cannot grasp the intricacies of low-level interaction dynamics. To overcome this issue, we introduce a world model designed to comprehend simple physics, modeling how human actions influence object motion. By integrating these components, our novel framework, InterDreamer, is able to generate text-aligned 3D HOI sequences without relying on paired text-interaction data. We apply InterDreamer to the BEHAVE, OMOMO, and CHAIRS datasets, and our comprehensive experimental analysis demonstrates its capability to generate realistic and coherent interaction sequences that seamlessly align with the text directives.

The natural language processing community has had a major interest in auto-regressive [4, 13] and span-prediction based language models [7] recently, while knowledge graphs are often referenced for common-sense based reasoning and fact-checking models. In this paper, we present an equivalence representation of span-prediction based language models and knowledge-graphs to better leverage recent developments of language modelling for multi-modal problem statements. Our method performed well, especially with sentiment understanding for multi-modal inputs, and discovered potential bias in naturally occurring videos when compared with movie-data interaction-understanding. We also release a dataset of an auto-generated questionnaire with ground-truths consisting of labels spanning across 120 relationships, 99 sentiments, and 116 interactions, among other labels for finer-grained analysis of model comparisons in the community.

We consider the problem of building semantic relationship of unseen entities from free-form multi-modal sources. This intelligent agent understands semantic properties by creating (1) logical segments from sources, (2) finds interacting objects, (3) infers their interaction actions using (4) extracted textual, auditory, visual, and tonal information. The conversational dialogue discourses are automatically mapped to interacting co-located objects, and fused with their Kinetic action embeddings at each scene of occurrence. This generates a combined probability distribution representation for interacting entities spanning over every semantic relation class. Using these probabilities, we create knowledge graphs capable of answering semantic queries and infer missing properties in a given context.

We present a method for clustering data streams incrementally, designed to discover all valid density peaks in a single pass, in a non-parametric fashion. It detects emerging clusters along the stream by dynamically locating kernels in the most promising areas and performing a Stochastic Mean Shift procedure to find clustering centers. We present a density estimation approach for dynamic initialization, considering every sub-stream that follows `emerging data' as a sample set and applying Hypothesis Testing (p-value approach) to estimate its local density. The sub-stream size and the p-value are determined in a way that provides provable accuracy guarantee. We compare our method with the state-of-the-art, on realistic and complex datasets. We show that it outperforms not only stream algorithms but also their more complex, non-stream foundational paradigms.

We present a fast and accurate center-based, singlepass clustering method, with main focus on improving the trade-off between accuracy and speed in computer vision problems, such as creating visual vocabularies. We use a stochastic Mean-shift procedure to seek the local density peaks within a single pass of the data. We also present a dynamic kernel generation along with a density test procedure that finds the most promising kernel initializations. In our algorithm, we use two data structures, namely a dictionary of permanent kernels, and a 'short memory' that is used to determine emerging kernels to be maintained and outliers to be discarded. In our experiments we make extensive comparisons with popular clustering algorithms, with respect to accuracy and efficiency.

In this paper, a dynamical recurrent artificial neural network (ANN) is proposed and studied. Inspired from a recent research in neuroscience, we introduced nonsynaptic coupling to form a dynamical component of the network. We mathematically proved that, with adequate neurons provided, this dynamical ANN model is capable of approximating any continuous dynamic system with an arbitrarily small error in a limited time interval. Its extreme concise Jacobian matrix makes the local stability easy to control. We designed this ANN for fitting and forecasting dynamic data and obtained satisfied results in simulation. The fitting performance is also compared with those of both the classic dynamic ANN and the state-of-the-art models. Sufficient trials and the statistical results indicated that our model is superior to those have been compared. Moreover, we proposed a robust approximation problem, which asking the ANN to approximate a cluster of input-output data pairs in large ranges and to forecast the output of the system under previously unseen input. Our model and learning scheme proposed in this paper have successfully solved this problem, and through this, the approximation becomes much more robust and adaptive to noise, perturbation, and low-order harmonic wave. This approach is actually an efficient method for compressing massive external data of a dynamic system into the weight of the ANN.